# Portfolio & Quantitative Analysis Stock analysis, portfolio performance reports, AI technical analysis, Yahoo Finance data. QRep security analytics reports, security performance reviews. ## Apps (5) ### Quants Suite - Combined QuantStats, Security Performance, Technical Analysis - App: https://portfolio-iframe.tigzig.com - Docs: https://tigzig.com/app-documentation/portfolio-analysis-suite.html - GitHub: https://github.com/amararun/shared-portfolio-analysis-googleui - AI Docs: https://www.tigzig.com/ai/apps/portfolio-analysis-suite.md - Quants Suite - Combined QuantStats, Security Performance, Technical Analysis ### QRep - Security Analytics Reports powered by QuantStats. Multi-security comparison with 23 metric blocks, 70+ KPIs, technical analysis charts, PDF/HTML exports. - App: https://qrep.tigzig.com - Docs: https://tigzig.com/app-documentation/qrep.html - GitHub: https://github.com/amararun/qrep-security-analytics - AI Docs: https://www.tigzig.com/ai/apps/qrep.md - QRep - Security Analytics Reports powered by QuantStats. Multi-security comparison with 23 metric blocks, 70+ KPIs, technical analysis charts, PDF/HTML exports. ### Custom GPT for Portfolio stats, Technical Analysis, Yahoo Finance - App: https://chatgpt.com/g/g-680a0fba9cd481919073d474bee520fb-quantstats-and-technical-analysis - Docs: https://tigzig.com/app-documentation/quantstats-portfolio-gpt.html - AI Docs: https://www.tigzig.com/ai/apps/quantstats-portfolio-gpt.md - Custom GPT for Portfolio stats, Technical Analysis, Yahoo Finance ### Technical analysis with Yahoo Finance, Finta, Gemini Vision (OLD) - App: https://chat.openai.com/g/g-680a0fba9cd481919073d474bee520fb-technical-analysis-report - Docs: https://tigzig.com/app-documentation/technical-analysis-gpt.html - AI Docs: https://www.tigzig.com/ai/apps/technical-analysis-gpt.md - Technical analysis with Yahoo Finance, Finta, Gemini Vision (OLD) ### Financial analysis and data retrieval from Yahoo Finance - App: https://chatgpt.com/g/g-I8qaXJauP-get-equity-data-balance-sheet-p-l-cash-flow - Docs: https://tigzig.com/app-documentation/yfin-bot.html - AI Docs: https://www.tigzig.com/ai/apps/yfin-bot.md - Financial analysis and data retrieval from Yahoo Finance ## Blog Posts (149) - [What Has Trump Been Buying and Selling? His Latest Trade Reports, Extracted and Downloadable](https://www.tigzig.com/post/trump-trades-reports-oct2026) - Tags: portfolio-quants, database-ai President Trump's OGE trade reports through the one posted 22 September 2026, extracted into an interactive tool and CSV download on TREMOR: 19 reports with 10,100 trades worth $948 million to $3.12 billion, a shift from mostly municipal bonds to 95% stocks since May 2026, the biggest 2026 trading days in Microsoft, Amazon and Meta, and the 2025 annual disclosure with 21,285 trades. Notes on value ranges and how the scanned reports were read. AI-readable: https://www.tigzig.com/ai/posts/trump-trades-reports-oct2026.md - [Explore the Tigzig Data Surface With Your AI: What Is New in October 2026](https://www.tigzig.com/post/tigzig-agent-data-surface-oct2026) - Tags: database-ai, mutual-funds, vigil, portfolio-quants October 2026 update on the Tigzig data surface for AI agents, reachable at api.tigzig.com. New: mutual fund scheme details (60 fields for about 2,100 funds), 26 new global macro indicators including US jobs, Japan 10-year yield and India IIP and WPI on the new base, 29 more cricket SQL functions, and FY26 related party transactions. Notes on fund_dedup_flag, AUM versus AAUM, TER matching, the October 2025 shutdown gap and links to API error guides. AI-readable: https://www.tigzig.com/ai/posts/tigzig-agent-data-surface-oct2026.md - [US Jobs, September 2026: Fewer New Jobs, Longer Searches, Pay Barely Keeping Up](https://www.tigzig.com/post/us-jobs-september-2026-update-oct2026) - Tags: portfolio-quants The US added 29,000 jobs in September 2026, and the 12 months to August were revised down from 827,000 to 543,000, a fourth straight year of downward first-report revisions, the longest run in records back to 1956. Health care carries job growth, unemployment is 4.2 per cent, spells of unemployment are longer, more claimants exhaust benefits, and hourly pay has trailed prices since April. Eleven-page deck rating 11 measures against 2023 and 2018-19. Personal analysis. AI-readable: https://www.tigzig.com/ai/posts/us-jobs-september-2026-update-oct2026.md - [FY 2025-26 BRSR Data Is Live on VIGIL: ESG Disclosures for 663 of the 750 Nifty Total Market Companies](https://www.tigzig.com/post/vigil-brsr-esg-fy2026-oct2026) - Tags: vigil VIGIL now has FY 2025-26 BRSR (Business Responsibility and Sustainability Report) data for 663 of the 750 Nifty Total Market companies, covering workforce, pay and complaints: headcount by type and gender, women on boards and in key management, median pay by gender, minimum wage compliance, and POSH and other complaints. Charts by index and sector, a Data Explorer, five-company compare, an XBRL viewer, data quality flags and a full CSV download. Explains CY and PY year views and December year-ends. AI-readable: https://www.tigzig.com/ai/posts/vigil-brsr-esg-fy2026-oct2026.md - [Jev Rank on TREMOR News Scores Every Headline Against What You Want to Read](https://www.tigzig.com/post/tremor-news-jev-rank-oct2026) - Tags: portfolio-quants, ai-coders TREMOR's news section now has Jev Rank, which scores about 800 headlines from 64 feeds from 0 to 100 against a reader's interests and sorts the page, in under 2 seconds. Three ways to use it: Run Jev Rank on default or saved interests, Edit interests with your own topics and example headlines, or a Focus box for a quick topic. Jev is TypeSafe's System One model; each headline is a yes or no question and the probability of yes is the score. Free, no signup. AI-readable: https://www.tigzig.com/ai/posts/tremor-news-jev-rank-oct2026.md - [Anthropic IPO Could Reach $2T. The Headwinds Are Already Here](https://www.tigzig.com/post/anthropic-ipo-2-trillion-headwinds-sep2026) - Tags: portfolio-quants Reuters reports Anthropic's IPO could value it at more than 2 trillion dollars. A personal note on the market it would list into: a 2025 net loss of 42 billion dollars, mostly a non-cash charge, on 4.6 billion of revenue; a positive adjusted operating profit reported for Q2 2026; about 414 of 518 billion of computing commitments that must be paid; bond yields at a 2007 high, inflation, diesel, data centre opposition and a free Chinese model close behind in cyber. Nine-page deck. Personal views, not investment advice. AI-readable: https://www.tigzig.com/ai/posts/anthropic-ipo-2-trillion-headwinds-sep2026.md - [GLM-5.3 From Z.ai, Like Claude Mythos Preview, Can Build Cyber Exploits on Its Own, Anthropic Finds](https://www.tigzig.com/post/anthropic-glm53-open-weight-cyber-sep2026) - Tags: ai-coders, portfolio-quants Anthropic's Frontier Red Team tested GLM-5.3, an open-weight model from Zhipu AI, known outside China as Z.ai, and found it built a working Chrome exploit in 50 of 410 attempts against 56 for Claude Mythos Preview. NIST calls it the most cyber-capable open-weight model to date, about four months behind the best US models. Anthropic's tests show its refusals give way 64% of the time to a cover story and 100% once the refusals are edited out, which cost about 4,400 dollars of computing. Ten-page deck with the key findings and a link to the full report. AI-readable: https://www.tigzig.com/ai/posts/anthropic-glm53-open-weight-cyber-sep2026.md - [The Biggest Tech Build Meets the Bond Rout of 2026](https://www.tigzig.com/post/ai-hyperscalers-debt-bond-rout-sep2026) - Tags: portfolio-quants Goldman expects the five hyperscalers to spend $3.4 trillion on AI over the next three years, nearly 3x the prior seven, just as the 2026 bond rout pushes yields to their highest since 2007. Free cash flow has gone negative at Alphabet, Oracle and Amazon; capital spending took 99% of the five hyperscalers operating cash flow in the June quarter; their borrowing has nearly doubled since 2023 to $483 billion, with J.P. Morgan Asset Management expecting $279 billion more in bond sales this year. Twelve-page deck covers the off-balance-sheet leases and guarantees, and the wider $5 trillion data centre build through 2030. AI-readable: https://www.tigzig.com/ai/posts/ai-hyperscalers-debt-bond-rout-sep2026.md - [Foreign Buying of US Stocks Hit a Record. Then July Went Quiet.](https://www.tigzig.com/post/foreign-buying-us-stocks-record-sep2026) - Tags: portfolio-quants Foreigners bought a record $942 billion of US stocks in the 12 months to July, then bought only $4 billion in July as Canada alone sold $60 billion. Money tilted from Treasuries to stocks: Treasury buying fell to $247 billion from $541 billion two years earlier. Private money did 85% of the stock buying, and official money (governments, central banks, sovereign funds) holds only 11% of foreign-held US stocks, with its share of long-term Treasuries down from 61% in 2020 to 44%. The 10-year yield then closed at 5.17% on 25 September, last seen in 2007. Fifteen-page deck with full country tables, sourced from US Treasury TIC files. AI-readable: https://www.tigzig.com/ai/posts/foreign-buying-us-stocks-record-sep2026.md - [US Diesel Is Above $6 a Gallon for the First Time, and the Cost Is Already Moving Through the Economy](https://www.tigzig.com/post/diesel-above-six-dollars-sep2026) - Tags: portfolio-quants US diesel hit $6.53 a gallon on 21 September, up 74% on a year ago, and the cost is already moving through the economy: truck freight rates up 14%, airfares up 23%, heating oil forecast up to 31% higher this winter. The squeeze is in refining, with diesel about $3.60 a gallon above Brent crude, wider than at any point in 2022, as Russian refining stays about 30% below its pre-war level for the next 18 months. Washington is weighing a ban on diesel exports, with no decision yet. AI-readable: https://www.tigzig.com/ai/posts/diesel-above-six-dollars-sep2026.md - [All Five US Credit Datasets on TREMOR Now Run to Q2 2026](https://www.tigzig.com/post/us-credit-data-q2-2026-tremor-sep2026) - Tags: portfolio-quants, database-ai All five US credit datasets on TREMOR now run to Q2 2026: US banks (FDIC), credit unions (NCUA), household debt (NY Fed), insurers' investments (Federal Reserve) and bank loans to non-banks (FFIEC), with up to 106 quarters of history. Covers the interactive tool's tree view, cross-section comparisons across up to four quarters, and how each source's own delinquency basis differs. Plus how each dataset is built and reconciled, and Q2 2026 notes: FDIC charge-offs down to 0.56 percent from a 0.70 percent peak, NY Fed's 90+ flow down to 2.57 percent, credit union charge-offs at 0.76 percent above the pre-crisis level, and 2.8 trillion dollars in bank commitments to non-bank lenders. AI-readable: https://www.tigzig.com/ai/posts/us-credit-data-q2-2026-tremor-sep2026.md - [All the Macro Data You Need to Track the Bond Market Rout, in One Place on TREMOR](https://www.tigzig.com/post/tremor-bond-data-macro-fallout-sep2026) - Tags: portfolio-quants, database-ai TREMOR carries 340+ macro and rate series from 25 sources, updated three times a day, covering bond yields, credit stress, jobs, inflation, oil, GDP and housing, as the US 10-year closes at 5.18 per cent and touches 5.21 intraday. Three ways in: the interactive charting tool with overlays, YoY and MoM views and moving averages, the API and MCP server for an AI agent or a script, and full database downloads as CSV, Parquet, DuckDB or SQLite. Links to the day's bond rout post and four earlier pieces on bonds, jobs and AI valuations. AI-readable: https://www.tigzig.com/ai/posts/tremor-bond-data-macro-fallout-sep2026.md - [Bond Markets Have Been Warning for Months. Now They Have Started Acting.](https://www.tigzig.com/post/bond-market-rout-sep2026) - Tags: portfolio-quants A follow-on to the 6 September bond markets post. The US 10-year closed above 5 per cent for the first time since 2007, a level seen since 2000 only in the dot-com years and the run-up to 2008. Almost all of the rise is the real yield, the TIPS measure of the return lenders want above inflation: over one year the 10-year rose 0.99 points while expected inflation fell 0.02. Japan's 10-year is at its highest since August 1996. Links to earlier analysis on the Fed, banks and AI valuations. AI-readable: https://www.tigzig.com/ai/posts/bond-market-rout-sep2026.md - [On the Headline Numbers the US Job Market Looks Fine. The Story Changes When You Dig Deeper.](https://www.tigzig.com/post/us-jobs-calm-before-storm-sep2026) - Tags: portfolio-quants A 16-page deck on the US job market as of September 2026. The August jobs report beat expectations and the Fed called the economy solid, but payroll growth has slowed from 3.2 per cent a year in January 2023 to 0.4 per cent, the August 2024 and 2025 counts were each revised down by about a million, hiring is near its lowest on record and the median time out of work rose from 9.6 to 11.4 weeks. Hourly pay has trailed prices five months running and the saving rate is 3.0 per cent, while layoffs stay low. Plus the survey quirks that trip up labour data. AI-readable: https://www.tigzig.com/ai/posts/us-jobs-calm-before-storm-sep2026.md - [Everything I Built for Market Reports Now Sits in One App. QDESK, and Three Ways In.](https://www.tigzig.com/post/qdesk-one-app-three-ways-in-sep2026) - Tags: portfolio-quants, mcp-servers The quant and portfolio reports that used to live in three separate apps now sit in one, called QDESK. Three ways in: ask the agent in plain English, fill a form and hit generate, or point your own code or your own agent at the API and MCP, which is what the first two call underneath. The agent now looks up the symbol live, having previously recalled tickers from memory. Covers the report set and the Indian mutual fund NAV history route through MFPRO. AI-readable: https://www.tigzig.com/ai/posts/qdesk-one-app-three-ways-in-sep2026.md - [August 2026 Portfolios Are Live on MFPRO Composition. Eleven Month-End Snapshots Across 24 of India's Larger Equity Funds.](https://www.tigzig.com/post/mfpro-composition-august-portfolios-sep2026) - Tags: mutual-funds, portfolio-quants August 2026 portfolios are live on the MFPRO composition tool, taking it to eleven month-end snapshots across 24 of India's larger equity funds. Covers reading the change in market value and the change in quantity together, the ISIN remapping, why money market lines are grouped, and the four rows holding everything that is not a listed Indian share. Validation is published: 251 of 264 fund-months match the AMC's own printed grand total, the other 13 listed with the amount and the reason. AI-readable: https://www.tigzig.com/ai/posts/mfpro-composition-august-portfolios-sep2026.md - [India Bank Credit Is Up 19 Percent, and the Biggest Single Contributor Is Lending to NBFCs](https://www.tigzig.com/post/india-sectoral-credit-jul2026-nbfc-sep2026) - Tags: portfolio-quants, database-ai India's July 2026 sectoral credit data is live on TREMOR. Non-food bank credit is Rs 219.6 lakh crore, up 19.1 percent over the year, and bank lending to NBFCs is the single biggest contributor, at Rs 21.3 lakh crore and Rs 5.6 lakh crore of the Rs 35.2 lakh crore the book added. RBI's extra 25 point risk weight on that lending came off in April 2025 and growth went 11, then 3, then 36 percent across the three Julys. Also covers why the Rs 5.5 lakh crore gold jewellery line is banks only against ICRA's Rs 18 lakh crore organised market, the credit deposit ratio coming off its 83.38 high, and the FCNR(B) window and record reserves rise that land in the fortnights after the last deposit reading. AI-readable: https://www.tigzig.com/ai/posts/india-sectoral-credit-jul2026-nbfc-sep2026.md - [Credit Union Q2 2026: Losses Above Pre-Crisis, and Delinquency Above Pre-COVID in Every Segment](https://www.tigzig.com/post/credit-union-q2-2026-losses-delinquency-sep2026) - Tags: portfolio-quants, database-ai NCUA published Q2 2026 credit union data on 14 September and it is now on the TREMOR interactive tool and downloadable as a file. Charge-offs across all lending are 0.76 percent on a for-the-quarter annualised basis, above the 0.49 percent of Q3 2007 and the 0.56 percent pre-COVID level, against a 1.33 percent crisis peak. Sixty plus day delinquency is above its pre-COVID level in every segment. Consumer is doing most of the loss, at 1.74 percent against 1.09 before COVID, while property delinquency has risen from 0.58 to 0.83 with charge-offs unmoved at 0.02 percent. Also covers the changing shape of the 1.76 trillion dollar book, with property and commercial growing while auto shrinks in dollars, and the measurement basis behind each comparison. AI-readable: https://www.tigzig.com/ai/posts/credit-union-q2-2026-losses-delinquency-sep2026.md - [Point Your AI Agent at api.tigzig.com. 40 Million Rows of Public Data, and Half the Bytes Are One File](https://www.tigzig.com/post/tigzig-agent-data-surface-sep2026) - Tags: database-ai, mutual-funds, vigil, portfolio-quants The agent data surface at api.tigzig.com now spans over 40 million rows across Indian mutual fund NAVs, ball-by-ball cricket, global macro indicators and India company filings, refreshed daily and free with no signup or key. Cricket is the addition since the August post, covering Tests, ODIs, T20s and the IPL for men and women from December 2001. Over seven days the surface served more than 110,000 API calls and more than 1,700 file downloads, about 40 GB in all, and one file alone, the complete NAV history in Parquet, accounts for more than half those bytes. Also covers the four routes in, the downloads manifest with its row counts and generated_at stamp, conditional requests returning 304, and how to pick between CSV, Parquet, SQLite and DuckDB. AI-readable: https://www.tigzig.com/ai/posts/tigzig-agent-data-surface-sep2026.md - [Pull 81 Risk and Performance Metrics Into Excel With One Formula](https://www.tigzig.com/post/qrep-excel-webservice-81-metrics-sep2026) - Tags: portfolio-quants, excel One Excel formula pulls 81 risk and performance metrics for any Yahoo Finance ticker straight into a sheet, using WEBSERVICE against the QREP API and TEXTSPLIT to lay the tab-separated response out across cells. Covers the working formula, the two troubleshooting steps, and how to read the same data in a browser as TSV or JSON. Also sets out the limits: WEBSERVICE fires every cell at once so a few hundred symbols runs into the host rate limit, and Power Query or Python in Excel is the route for that. Parameters explained: the risk free rate is a decimal fraction so 0.05 means 5 percent and 5 is rejected, six symbols is the maximum per call, and the benchmark sits outside that count. Backend is the Python QuantStats library with documented changes to the calculations. AI-readable: https://www.tigzig.com/ai/posts/qrep-excel-webservice-81-metrics-sep2026.md - [The Fed Is Caught. The Market Has Already Made Most of the Decision for It.](https://www.tigzig.com/post/fed-caught-rate-decision-sep2026) - Tags: portfolio-quants The FOMC decides on Wednesday 16 September and the market has largely priced it: a quarter point rise sits at 86 per cent on CME FedWatch against 33 per cent a month ago, and the three month Treasury bill is already at 4.00 per cent, exactly where that rise would put the top of the range. Over the past year the ten year Treasury rose 91 basis points and ten year TIPS rose 86, so the gap the market reads as expected inflation moved just 5 basis points and almost the whole rise is the real cost of money. That cost is paid on mortgages, refinancing and every government bond rolled over, whether the Fed moves or holds. A rate rise also does not reach the supply side pushing prices up, with diesel up 59.8 per cent over the year and petrol 30.8. Also covers the political campaign around the decision, Fed Chairman Warsh's breadth and duration case from his Jackson Hole keynote, and the two things in that same speech that cut the other way. AI-readable: https://www.tigzig.com/ai/posts/fed-caught-rate-decision-sep2026.md - [QDESK: A Reporting Desk for Portfolio Reports and Financial Data. Just Ask in Plain Language.](https://www.tigzig.com/post/qdesk-reporting-desk-sep2026) - Tags: portfolio-quants, mcp QDESK is an agent-driven reporting desk: ask in plain language and it looks up the symbol then runs the report, so you never need the ticker. It produces a security performance report, daily and weekly technical analysis, a QPulse tearsheet against a benchmark, and QREP metrics with around eighty risk and return figures for up to six securities. Also pulls company financials, prices and Indian mutual fund NAV history, with REST and MCP endpoints behind each report. AI-readable: https://www.tigzig.com/ai/posts/qdesk-reporting-desk-sep2026.md - [YFIN API Now Returns Plain CSV on Most Endpoints. Add format=csv to the Same URL.](https://www.tigzig.com/post/yfin-api-csv-format-multiple-tickers-sep2026) - Tags: portfolio-quants, excel The free YFIN Yahoo Finance API now answers with a plain CSV table on most endpoints: add format=csv to the same URL and skip unwrapping JSON. Every endpoint also takes a comma-separated list of up to 25 symbols, so a whole watchlist comes back in one request. Includes the data pull agent at quants.tigzig.com, what it will and will not do, and its separate AI technical analysis report. AI-readable: https://www.tigzig.com/ai/posts/yfin-api-csv-format-multiple-tickers-sep2026.md - [Many of These Macro Charts Are Showing the Same Stress They Showed Before 2007. The AI Layer Is What Is New.](https://www.tigzig.com/post/macro-signals-back-at-2007-levels-sep2026) - Tags: portfolio-quants Twelve macro charts pulled from TREMOR, read against 2007. The US 30 year is back at July 2007 levels, the UK 10 year gilt at July 2008, the German Bund at May 2011. Consumer debt 90 days late is 3.31% and bank C&I noncurrent loans sit above every quarter of 2007, while core PCE at 3.34% leaves the Fed no easy move. With Warsh at Jackson Hole, and what the AI layer adds on top. AI-readable: https://www.tigzig.com/ai/posts/macro-signals-back-at-2007-levels-sep2026.md - [The FSB Chair Is Not Hedging. Andrew Bailey's Blunt Warning Note to the G20.](https://www.tigzig.com/post/fsb-chair-bailey-warning-sep2026) - Tags: portfolio-quants Andrew Bailey, chair of the Financial Stability Board and Governor of the Bank of England, warned the G20 on 28 August 2026 that markets remain vulnerable to a potentially disorderly correction that could spread across borders. Covers the factors he names - sovereign debt, private credit, stretched AI valuations, rising equity leverage - his section on frontier AI and cyber risk, and the July collapse of a leveraged AI fund. Ten-slide deck attached. AI-readable: https://www.tigzig.com/ai/posts/fsb-chair-bailey-warning-sep2026.md - [Bond Markets Are Sounding an Alarm. The US Thirty Year Is at 5.25 Per Cent and the Fed Has Been Cutting Through All of It.](https://www.tigzig.com/post/bond-markets-alarm-sep2026) - Tags: portfolio-quants Long-term borrowing costs are rising across the developed world while central banks cut. The US thirty year is at 5.25 per cent, above 5.2 for the first time since 2007, and since the Fed began cutting the ten year is up 106 basis points and the thirty year 122. Sets out why the long rate is what prices a mortgage, a refinancing and a long-payback project, and the combination of pressures around it. Sixteen-slide deck attached. AI-readable: https://www.tigzig.com/ai/posts/bond-markets-alarm-sep2026.md - [US Bank Loan Data Is Now Updated Through Q2 2026 on TREMOR. NY Fed, FDIC and the FFIEC Call Reports, All Three in One Place.](https://www.tigzig.com/post/us-bank-loan-data-q2-2026-tremor-sep2026) - Tags: portfolio-quants, database-ai All three US bank and household credit datasets on TREMOR are now current to Q2 2026: FDIC industry aggregates back to 2001, FFIEC Call Report data for 754 individual banks with their capital and non-bank lending, and the NY Fed Equifax consumer credit panel back to 1999. Covers the Q2 delinquency moves on both sides, and why FDIC and NY Fed delinquency rates are not comparable. AI-readable: https://www.tigzig.com/ai/posts/us-bank-loan-data-q2-2026-tremor-sep2026.md - [The Portfolio Agent Now Looks Up Live Symbols for Stocks and Securities, Instead of Guessing From Memory.](https://www.tigzig.com/post/portfolio-agent-symbol-lookup-sep2026) - Tags: portfolio-quants, mutual-funds The Tigzig portfolio agent at quants.tigzig.com now resolves stock and security symbols against the live Yahoo Finance lookup rather than recalling them, the same pattern already used for Indian mutual fund schemes. Prompted by log review, which showed symbol guessing as a point of friction and users asking the agent to pull NAVs. Five reports are available: a QRep performance and risk report for one security against a benchmark, a chart-based technical analysis report, a multi-security performance comparison with HTML and CSV output, a Yahoo Finance data pull covering prices, profiles, financials, holders, estimates, dividends, splits, actions and ticker lookup, and Indian mutual fund scheme lookup with NAV history. AI-readable: https://www.tigzig.com/ai/posts/portfolio-agent-symbol-lookup-sep2026.md - [A Correction in AI Valuations Is Looking More Likely, and That View Now Comes From a Central Bank, an Asset Manager and a Bond Investor.](https://www.tigzig.com/post/ai-valuation-correction-aug2026) - Tags: portfolio-quants The case that AI valuations are due a correction, now argued in print by the European Central Bank, and two weeks later by Andrew Bailey to the G20 in his capacity as chair of the Financial Stability Board, who points at leverage and the cross-investment between AI companies and hyperscalers as amplifiers. The whole structure rests on free cash flow arriving from 2028 while the current direction is the opposite, with Alphabet posting its first negative free cash flow quarter as a public company. Sets that alongside the wider pressure: employment, delinquencies and inflation, US banks with $2.8 trillion committed to non-bank lenders, and Fitch's private credit default rate at a record. Includes a twenty-slide deck and links to earlier pieces on valuations, private credit and household debt. AI-readable: https://www.tigzig.com/ai/posts/ai-valuation-correction-aug2026.md - [US Banks Had $2.8 Trillion Committed to Non-Bank Lenders at the End of Q2 2026, and $1.7 Trillion of It Was Already Drawn.](https://www.tigzig.com/post/us-banks-nonbank-lending-q2-2026) - Tags: portfolio-quants, database-ai Q2 2026 FFIEC Call Report data on US bank lending to non-bank financial institutions, now live on TREMOR bank by bank. Banks had $2.8 trillion committed at the end of the quarter with $1.7 trillion drawn, equal to 14.3 percent of the lending banks' own loan book, up from 11.1 percent seven quarters earlier and higher in every quarter since separate reporting began in Q4 2024. 754 banks are named across the seven quarters, 633 reporting in the latest, with 37 fields each covering drawn balances, undrawn commitments, the five lending categories, capital ratios and credit quality. The 633 are about one in seven US banks by count but hold 88.7 percent of banking assets. Includes notes on the $10 billion reporting threshold that leaves $32 billion unallocated, blank capital fields under the CBLR framework, and the FDIC cross-check. AI-readable: https://www.tigzig.com/ai/posts/us-banks-nonbank-lending-q2-2026.md - [My Portfolio Agent Could Not Look Up an Indian Mutual Fund NAV. Now It Can.](https://www.tigzig.com/post/portfolio-agent-mutual-fund-nav-aug2026) - Tags: portfolio-quants, mutual-funds The Tigzig portfolio agent at quants.tigzig.com can now resolve and fetch Indian mutual fund NAVs. Give it a fund name roughly as you would say it and it searches the AMFI scheme master, resolves the real scheme code, and where a name matches more than one scheme it lists the candidates and asks before fetching, because a fund typically exists as Direct and Regular plans with Growth and IDCW options on separate series. Short windows come back in the chat and longer histories as a CSV link. The agent also pulls prices, company profiles and financial statements for Yahoo Finance symbols, finds tickers by name, runs quant reports against a benchmark, produces technical analysis reports as HTML and PDF, and compares securities on return and risk. It does not give investment advice. AI-readable: https://www.tigzig.com/ai/posts/portfolio-agent-mutual-fund-nav-aug2026.md - [FDIC Q2 2026 Numbers Are Live on TREMOR. 102 Quarters of Bank Balances, Delinquency and Charge-Offs.](https://www.tigzig.com/post/fdic-q2-2026-bank-credit-tremor-aug2026) - Tags: portfolio-quants, database-ai FDIC Q2 2026 Quarterly Banking Profile data is now on TREMOR, 102 quarters of balances, delinquency and charge-offs for every FDIC-insured bank back to Q1 2001, queryable in the browser or downloadable in full. Net charge-offs peaked at 0.70% in Q4 2024 and are now 0.56%, almost exactly the Q3 2007 level and still above 2019's 0.50%. Lending to other financial firms is 18.6% of the book at $2.6 trillion against 3.3% before the last crisis, and supplied 54% of loan growth over the year. Sector detail on C&I, real estate, auto and cards, plus an explanation of the noncurrent measure and how it splits between 90+ days past due and nonaccrual. AI-readable: https://www.tigzig.com/ai/posts/fdic-q2-2026-bank-credit-tremor-aug2026.md - [Reading Macro Charts on TREMOR? Send Them to the AI Agent Sitting There and Get a Read With the Latest News.](https://www.tigzig.com/post/tremor-ask-claude-agent-aug2026) - Tags: portfolio-quants, ai-coders An AI agent now sits inside the TREMOR macro dashboard and will read the charts in front of you, with three ways to ask. What changed this week sends every chart on the dashboard as one briefing, Analyze selected charts takes up to five and looks for trends, inflection points and correlations between them, and Deep research does the same while going out to newswires, ratings agencies and central bank releases and citing what it finds. The prompt is editable before it sends, output copies as markdown or prints to PDF, and past runs persist in browser storage. Each chart reaches the agent as its series, values, dates and source label, so it knows the provenance and how much history it has. Also the honest caveats: this is commentary rather than a research note, and the read is heavily shaped by the prompt, which is why the prompt is left customizable. AI-readable: https://www.tigzig.com/ai/posts/tremor-ask-claude-agent-aug2026.md - [Pulling Yahoo Finance Data Into Your Own Trackers. Excel, Sheets, a Web Tool, or Straight From an AI Agent.](https://www.tigzig.com/post/yfin-integrate-your-tools-aug2026) - Tags: excel, portfolio-quants Getting Yahoo Finance prices, calendars, financials and recommendations into whatever you already work in, through the free keyless Tigzig YFIN API. In Excel that means Power Query, Python-in-Excel via xlwings Lite, VBA or a WEBSERVICE formula, each with its own trade-off; Google Sheets needs a few lines of Apps Script; a web tool needs one JavaScript call; and an AI agent needs no code at all because it is on MCP. The practical route for most people is to hand the API docs to an agent with a desktop app, which edits the workbook directly. Also four things worth knowing: Yahoo wants the exchange ticker rather than the company name, there is now a search endpoint aimed at agents that stops them guessing symbols from memory, the /v1/excel/ statement endpoints return sheet-ready rows while the plain ones are pipe delimited, and WEBSERVICE should batch 25 tickers a call rather than firing one cell each. AI-readable: https://www.tigzig.com/ai/posts/yfin-integrate-your-tools-aug2026.md - [What Trump Has Been Buying, Selling and Holding. The Filings, Extracted and Searchable.](https://www.tigzig.com/post/trump-trades-filings-aug2026) - Tags: portfolio-quants, database-ai Trump's public financial filings, extracted and made searchable: trades, assets, income, liabilities and gifts. Two different documents sit behind it. The periodic trade reports, filed within 30 to 45 days of each trade and covering securities only, run to 15 filings and 5,368 trades, though the distribution is lopsided, with fourteen filings holding 1,726 trades between them and a single 14 May filing carrying 3,642, almost all equities. The annual disclosure is a separate 927 page document with 28,007 records including 21,285 trades, and because OGE rules let it omit trades already reported, neither document alone is the full year. Also the extraction method for each, which differed sharply because one arrives as a scan and the other as a digital document, and the caveats that matter before analysis, including that form values are ranges rather than exact figures. AI-readable: https://www.tigzig.com/ai/posts/trump-trades-filings-aug2026.md - [TREMOR Opened With Sixteen Charts in a Fixed Grid. That Was My View. Now You Can Change All of It.](https://www.tigzig.com/post/tremor-chart-layout-aug2026) - Tags: portfolio-quants, database-ai The TREMOR macro dashboard used to open on a fixed grid of sixteen charts chosen by its author, and that grid is now fully editable: delete a chart, drag two side by side, swap one series for another, resize or expand, overlay two series on one axis, switch to year-on-year or month-on-month, apply a moving average of any period, extend the window to thirty years, hide labels, copy the underlying data, export a PNG for a deck, or add something new from around three hundred indicators. Behind it sit roughly 330 series, about 250 US and 50 India, weighted heavily towards credit through FDIC bank aggregates, NCUA credit union data and NY Fed household debt, alongside FRED macro, MoSPI and RBI for India, and odds and ends like Shiller, Manheim and European bond yields. Free, no signup, and reachable by an AI agent through the API or MCP. AI-readable: https://www.tigzig.com/ai/posts/tremor-chart-layout-aug2026.md - [Three Fixes on the Yahoo Finance API This Week, All of Them Found by Reading My Own Error Logs.](https://www.tigzig.com/post/yfin-three-fixes-aug2026) - Tags: portfolio-quants, excel Three fixes to the free Tigzig Yahoo Finance API, each one found by reading the server's own error logs rather than waiting for a report. The worst of them had price history failing and then blaming the caller's ticker symbol or date range when both were fine and the real fault was upstream, so someone at the other end would have sat re-typing a symbol that was correct all along. Detailed company info could also run long and return nothing, throwing away the tickers that had already come back cleanly, and it now returns whatever it managed to fetch. A single ISIN dropped into a symbol list used to fail the entire request, and the rest of the list now comes back regardless. Also why a WEBSERVICE-based Excel tracker trips rate limits, the xlwings Lite workbook that avoids it, and why Indian tickers need the exchange symbol. AI-readable: https://www.tigzig.com/ai/posts/yfin-three-fixes-aug2026.md - [Shiller CAPE Is at 41.2. In 145 Years the Only Period Higher Was the Dot-Com Peak.](https://www.tigzig.com/post/tremor-monthly-update-aug2026) - Tags: portfolio-quants, database-ai This month's Tremor update, with the valuation reading leading it: Shiller CAPE at 41.2, a level exceeded only during the dot-com peak across 145 years of history. Alongside it, the US 30-year Treasury at 5.23% makes 2026 the first year since 2007 that the long bond has traded above 5.2%, US auto loans are running a 90+ day delinquency flow of 3.00% which is the highest since the first quarter of 2010, and Brent has recovered to the mid nineties after a spike above 138 in April and a fall to around 70 by late June. On the data side, India bank credit history extends back to February 2017 giving 113 months across 33 sectors, NY Fed household debt for Q2 2026 is loaded across 64 series, and BSE Sensex daily prices now reach back to 1997. Free, no signup, usable as an interactive tool, an API, over MCP or as a full database download. AI-readable: https://www.tigzig.com/ai/posts/tremor-monthly-update-aug2026.md - [NY Fed Q2 2026 Household Debt. The Headline Delinquency Flow Fell, but Auto and Mortgage Went the Other Way.](https://www.tigzig.com/post/nyfed-household-debt-q2-2026) - Tags: portfolio-quants, database-ai The Q2 2026 NY Fed household debt release read better at the headline and worse underneath. The overall flow into 90+ day delinquency fell from 3.26% two quarters ago to 2.57%, but almost all of that improvement is student loans unwinding after the reporting restart. Mortgage, which is about 70% of what households owe, has seen its 90+ flow rise in six of the last seven quarters to 1.52%, back around 2005-06 levels even though the stock at 0.99% is far below the 2.23% of Q3 2007. Auto is the stretched one: a 90+ stock of 5.49% is the second highest reading since the series began in 2003, and its flow at 3.00% now exceeds the 2.34% of Q3 2007. Cards sit above their 2007 flow too. Full then-and-now comparison against the quarter before the GFC cycle turned, plus why the NY Fed credit-file panel, FDIC and NCUA do not reconcile with each other. AI-readable: https://www.tigzig.com/ai/posts/nyfed-household-debt-q2-2026.md - [Point Your AI Agent at api.tigzig.com and It Works Out Which Dataset It Needs. 38 Million Rows Across India and the US, Free.](https://www.tigzig.com/post/tigzig-agent-data-surface-aug2026) - Tags: mutual-funds, vigil, portfolio-quants One address an AI agent can be pointed at, api.tigzig.com, from which it works out which dataset a question needs and pulls the file itself. Close to 38 million rows across India and the US, curated and refreshed daily, free with no signup or key: twenty years of Indian mutual fund NAVs, around 330 macro, credit and valuation indicators across eight groups, and seven filing datasets for Indian listed companies covering credit ratings, insider trading, promoter pledge, encumbrance, takeover, surveillance flags and related party transactions. Usable three ways, by hand in the apps, through the API from code, or as whole-table downloads in CSV, Parquet, SQLite or DuckDB. Includes a downloads manifest carrying row counts and a generated_at stamp so a script can tell whether anything changed before re-pulling, and practical notes on renamed schemes still resolving from an old ISIN. AI-readable: https://www.tigzig.com/ai/posts/tigzig-agent-data-surface-aug2026.md - [MFPRO Composition Analytics Is Live. Portfolios for 24 of India's Largest Equity Funds, Reconciled Against the AMC's Own Printed Totals.](https://www.tigzig.com/post/mfpro-composition-analytics-aug2026) - Tags: mutual-funds, portfolio-quants Portfolio composition analytics for 24 of India's largest equity funds across large cap, mid cap, small cap, flexi cap, focused and value, spanning ten snapshots from June 2025 to July 2026. Compare one fund over time, several against each other, or against a benchmark, with copy-to-Excel, the original disclosures, ISIN remaps and the reconciliation notes alongside. The work that makes months comparable is the interesting part: a face-value split moves a company to a new ISIN and looks like a position appearing from nowhere unless the two are stitched, and money market instruments arrive as dozens of separate lines that need grouping. Cash is the real divergence between fund houses, some folding it into the printed grand total and others listing it below, which is worth several per cent of a fund. Every fund-month is reconciled against the AMC's own printed total, 228 of 240 to the rupee with the remainder published with reasons. AI-readable: https://www.tigzig.com/ai/posts/mfpro-composition-analytics-aug2026.md - [Is a Large Investor Building a Position or Selling Down in Your Stock? Takeover Filings on VIGIL, Refreshed Four Times a Day.](https://www.tigzig.com/post/vigil-takeover-sast-filings-aug2026) - Tags: vigil SEBI takeover disclosures for Indian listed companies on the free VIGIL app, refreshed four times a day, showing who has been building or cutting a large stake. Anyone crossing 5% of a company has to tell the exchange, and every 2% move after that. Pull up a company to see who has been buying into it, or search an acquirer to see everywhere they have been active. About 12,000 filings across 1,500 companies from January 2024, of which around 3,600 come from outside the promoter group, where mutual funds, insurers and private equity show up. Includes the caution that debenture trustees also sit in that non-promoter group holding shares as security rather than as a view on the company. Downloadable as CSV, Parquet or SQLite, or hand the open no-key API straight to an AI agent with the prompt included. AI-readable: https://www.tigzig.com/ai/posts/vigil-takeover-sast-filings-aug2026.md - [667 Stocks Are Under NSE and SEBI Surveillance. Almost All of Them Sit Outside the Nifty 500.](https://www.tigzig.com/post/nse-sebi-surveillance-667-stocks-aug2026) - Tags: vigil As of 7 August 2026 there are 667 Indian listed companies carrying an NSE or SEBI surveillance flag, and the breakdown shows it is overwhelmingly a small and micro cap story. Only 20 sit in the Nifty 500, two of those in the Nifty 100 and none in the Nifty 50. Another 24 are in the Microcap 250. The remaining 623 fall outside the Nifty Total Market entirely, including roughly 171 on the SME platform and 41 in the suspended or Z group. Flags also stack: 62 companies carry two, 27 carry three and 4 carry four. ASM, GSM and ESM cover price and volume surveillance, with separate fundamental flags. Checkable per stock in the VIGIL app, updated daily, and downloadable via a free API. AI-readable: https://www.tigzig.com/ai/posts/nse-sebi-surveillance-667-stocks-aug2026.md - [An Excel Tracker for Hundreds of Yahoo Finance Tickers, Built with xlwings Lite. For When WEBSERVICE Keeps Failing.](https://www.tigzig.com/post/sp500-excel-tracker-xlwings-yfin-aug2026) - Tags: excel, xlwings-lite, python-in-excel A downloadable Excel workbook that pulls dividend and earnings calendar data and prices for hundreds of Yahoo Finance tickers through the free Tigzig YFIN API, built for the case where a WEBSERVICE formula keeps failing because it is volatile and fires every cell at once. Built with xlwings Lite, which runs Python inside Excel as an add-in you install once. It uses the API's batching at up to 25 tickers per call with a configurable batch size, and each batch writes back to the sheet as it arrives with a spinner and a running status cell so the load is visible in progress. An important data caveat is documented: all dates are UTC calendar dates in YYYY-MM-DD with no time of day, because Yahoo timestamps each event to an exact instant and the UTC date of that instant is reported, so a US company reporting after roughly 8 PM Eastern crosses midnight UTC and lands on the next date, meaning readers should convert from UTC rather than assume the US trading date. Ships configured for S&P 500 tickers and takes about nine minutes for a full calendar pull and about two minutes for four trading days of prices, with the ticker list swappable and the Python source editable in place, so any AI assistant can modify it. Also points to the API error guide and notes the same pattern works against the India mutual fund APIs, including adding risk, return and benchmark calculations. AI-readable: https://www.tigzig.com/ai/posts/sp500-excel-tracker-xlwings-yfin-aug2026.md - [Technical Analysis on Any Ticker Without Visiting My Site. Just Ask Your AI Agent.](https://www.tigzig.com/post/tigzig-technical-analysis-ask-your-ai-aug2026) - Tags: technical-analysis, mcp, ai-coders The TigZig technical analysis API produces a formatted PDF and web report with charts, indicator readings and an outlook for any Yahoo Finance ticker, covering stocks, indices, FX, crypto and commodities, and it can be reached entirely through an AI agent without opening the site: paste a plain-English request naming the ticker and the tigzig API, and the agent discovers the API catalog, picks the right endpoint and reads the rate limits itself. Model choice is available on request. How it is built: prices from Yahoo Finance on daily and weekly timeframes, indicators computed with finta (EMAs, MACD, RSI, Bollinger Bands), two charts drawn with matplotlib, then both the numbers and the chart images passed to a vision model that reads the chart and writes the interpretation, with the returned markdown converted to PDF and HTML by a second ReportLab-based service. One FastAPI app serves the web front end, the REST endpoint and the MCP endpoint, so a browser and an agent execute the same code, and the whole thing is open source for anyone wanting to self-host or customise it. Closes with an explicit scope statement: this is a reporting tool rather than investment advice or research, models can misread a chart confidently, and the author's own practice is to use AI for the heavy lift and alternative angles while validating every deterministic output, the numbers and formulas, against more than one source. AI-readable: https://www.tigzig.com/ai/posts/tigzig-technical-analysis-ask-your-ai-aug2026.md - [Comparing Securities on Returns, Risk and Drawdowns. Four Routes into QuantStats, Depending on What Your AI Can Do.](https://www.tigzig.com/post/quantstats-four-routes-qrep-agent-aug2026) - Tags: portfolio-analytics, mcp, ai-coders Four ways to get portfolio and security analytics out of QuantStats, the open-source library by Ran Aroussi who also wrote yfinance, with the right route depending on what your AI can actually do. An AI chat such as ChatGPT cannot install Python, so it connects through an MCP server, and the open-source QREP MCP server is one option. An AI agent such as Claude Cowork, Claude in Excel or PowerPoint, or ChatGPT Work, installs the package itself, runs the numbers and formats the output or builds a dashboard, and can equally call the QREP API directly for a fixed set of 81 metrics with no setup, or connect over MCP. For interactive work on screen, the QREP browser tool runs the cuts and generates a QuantStats-format tear sheet. Tool and API are both QuantStats-powered and both open source, with a few QREP implementation choices that shift a handful of numbers slightly, documented in the methodology page. Also notes that an agent with Python can be asked to write the metric functions from scratch, which is useful for validation and for metrics such as rolling returns. Adds a clarification on what a chat app can actually run in its Python sandbox, where ChatGPT is more restricted than Claude.ai and the desktop cowork apps are more capable again, with the practical advice being to ask the assistant what it can do and test it. Includes copy-paste agent prompts for both the run-it-yourself and the API route, using the Mag 7 against the S&P 500 over five years, plus practical notes for the browser tool: ticker search rather than typing, CSV export of the metrics table and raw prices, adjustable omega threshold and var/cvar confidence and tail cutoff, and browser-computed EMA, RSI and MACD technicals with the formulas in the docs. AI-readable: https://www.tigzig.com/ai/posts/quantstats-four-routes-qrep-agent-aug2026.md - [MFPRO Scheme Master: Every India Mutual Fund Scheme in One Small File, Free](https://www.tigzig.com/post/mfpro-scheme-master-download-aug2026) - Tags: mutual-funds, portfolio-analytics A free, keyless one-row-per-scheme master file covering every India mutual fund scheme in AMFI's public records from April 2006 onward, about 38,000 rows and 22 columns at roughly 9 MB as CSV, 1.1 MB gzipped and 1.6 MB as parquet, downloadable in one click from the MFPRO app or over HTTP at /mf/v1/download?format=latest with pandas reading straight off the URL. Columns cover identity (scheme_code, isin, isin2, scheme_name, amc, txic_code), classification (scheme_type, raw category, category_sub, category_group and the four-value category_group_clean), how it is sold (scheme_plan, scheme_option), lifespan (first_date, last_date, is_active, is_stale) and size and price (aaum_cr_quarterly_avg with its quarter label and ISO quarter-end, nav_date, nav). About 8,600 schemes are live and roughly 29,000 matured or merged are kept in deliberately, so long-run studies can be run survivorship-bias free. Includes a worked pandas filter that shortlists 39 large long-track-record Direct Growth equity schemes across three fund houses, guidance on moving from scheme codes to NAVs (single call, 50-code batch, or the 37-million-row full history file), and a join recipe pairing the master with the full NAV history to hold the whole universe locally. Documents six data quirks that produce plausible wrong answers rather than errors: the NAV column being each scheme's last NAV rather than today's, one scheme code being a plan-and-option variant rather than a fund, meaningful blanks in category_sub, aaum_cr_quarterly_avg and isin, sorting quarters on the ISO column rather than the text label, AAUM being a quarterly average rather than a balance, and about 2,300 matured schemes carrying a closing NAV of zero. AI-readable: https://www.tigzig.com/ai/posts/mfpro-scheme-master-download-aug2026.md - [Pulling Company Financials Straight From SEC Filings. Free, No Vendor, No API Key. Three Routes Tested Head to Head.](https://www.tigzig.com/post/sec-financials-three-ways-xbrl-edgartools-jul2026) - Tags: portfolio-quants, ai-coders Three routes to company financials from SEC filings, tested head to head in a Claude Cowork session on the same seven companies and six quarters: the SEC XBRL API directly, the edgartools Python library, and yfinance. All three agreed on the numbers; they differ on coverage and traceability. Verdict: edgartools first - it ships a statement API that pulls a full statement in one shot with indent level and parent, a customizable tag-standardization layer, de-cumulation, EDGAR full-text search, 13F institutional holdings, TTM calculations and segment facts, plus Claude skills and an MCP server. The raw SEC API stays for raw SEC API for cross-sectional screening of thousands of filers and as an independent second path - a check that earned its keep when the one disagreeing figure turned out to be a mishandled restatement. Links to a full 17-section write-up covering XBRL concepts/tags/facts, the four API routes as slices of a cube, frames coverage, taxonomies, saving filings, R-pages, standardisation, duration vs instant, the yfinance reconciliation, edgartools capabilities and its shipped Claude skills, and limits - with every Python script, JSON dataset and source filing published alongside so any number can be traced to the code that produced it. edgartools is by Dwight Gunning, MIT licensed, 2,000+ stars, ships Claude skills and an MCP server. AI-readable: https://www.tigzig.com/ai/posts/sec-financials-three-ways-xbrl-edgartools-jul2026.md - [Yahoo Finance MCP Backend Upgraded. 25 Tickers in One Request, Answers in Seconds, Clear Errors Instead of Slow Failures.](https://www.tigzig.com/post/yahoo-finance-mcp-backend-upgrade-jul2026) - Tags: mcp Short release note: the TigZig Yahoo Finance MCP backend has been upgraded - batch requests now take up to 25 tickers in one call, responses return in seconds instead of stalling, and a bad or slow ticker returns a short note while the rest of the batch still comes through, a clear message instead of a slow failure. Applies to any MCP client (Claude, ChatGPT, LM Studio). Errors on any TigZig app surface on the author's monitoring and get root-caused. Links: Yahoo Finance MCP docs page, api.tigzig.com agent entry point, the API-errors practical fix guide, and the Streamable HTTP migration note for anyone still on an older SSE URL. AI-readable: https://www.tigzig.com/ai/posts/yahoo-finance-mcp-backend-upgrade-jul2026.md - [Jamie Dimon's Six Warnings. Record JPMorgan Profits, but a Very Different Macro Outlook From the Chairman Himself.](https://www.tigzig.com/post/jamie-dimon-six-warnings-jul2026) - Tags: portfolio-quants Jamie Dimon's hour-long Master Investor Podcast interview (Wilfred Frost, July 2026) distilled: JPMorgan posts its highest-ever quarterly profit on a trading rebound while the chairman's own macro outlook runs the other way. Six warnings: early AI-boom entrants may not be the winners (dot-com parallel), the real AI challenge is retooling training systems rather than job-loss panic, he would not buy long government bonds or broad indices at current prices, he distrusts official monthly inflation prints, geopolitical risk from conflicts and remilitarization is larger than markets price, and 100% debt-to-GDP with 6% deficits outside wartime will become a problem via rates and bond-market pressure. 8-slide summary deck (browsable carousel + PDF download) and the full best-effort cleaned interview transcript below the deck, with the YouTube source linked and caption-quality disclaimer stated. AI-readable: https://www.tigzig.com/ai/posts/jamie-dimon-six-warnings-jul2026.md - [Three Warnings on the AI Valuation Boom in the Past Two Weeks: Warren Buffett, S&P Global & BIS](https://www.tigzig.com/post/ai-boom-warnings-jul2026) - Tags: portfolio-quants Three warnings on the AI valuation boom in the past two weeks - Warren Buffett, S&P Global and BIS (the bank for central banks). A legendary investor, a rater and a regulator. The BIS modelled the AI build-out and found the race over-invests 1.5 to 3 times the efficient level. Buffett is sitting on a record $397bn in cash and calls the market gambling. S&P cut Oracle to one notch above junk on the cost of its AI build-out. Nobody is questioning the technology - the parallel is dotcom (huge valuations on page views with no profit); this time it is users and revenue, better, but still no cash profit. Until the profit is real, the valuation is the exposed part. Seven-slide PDF deck attached (browsable carousel + PDF download). Also includes a one-month supervisor drills roundup - ECB doubled its private-credit probe, France ran its first system-wide non-bank stress test across Banque de France, ACPR and AMF, and the Bank of England sent 46 firms a five-year recession to model with Sarah Breeden invoking Akerlof's market-for-lemons on private credit - and an agent-first pitch for tigzig.com (dozens of analyses + several live tools; point ChatGPT / Gemini / Claude at the site with example prompts). AI-readable: https://www.tigzig.com/ai/posts/ai-boom-warnings-jul2026.md - [Trump's 2025 annual financial disclosure: all 28,007 records, extracted and searchable](https://www.tigzig.com/post/trump-2025-annual-disclosure-jul2026) - Tags: portfolio-quants Release post announcing that OGE certified and released President Trump's 2025 annual public financial disclosure (Form 278e, 927 pages) on June 30, 2026, and the whole thing has been extracted into a structured, searchable, downloadable dataset - 28,007 records across eight tables - and added to the Trump Trades tool on tigzig alongside the periodic 278-T trade reports. What is now on the tool: an Overview landing page explaining the two filing types, an At-a-glance dashboard, a Companies tab with ticker rollup, a vs S&P 500 tab that plots all 142 trading days on the index chart, full table viewers with search / filters / sort / pagination for Transactions / Holdings / Business & Income, a Liabilities & Gifts tab, a Data tab with record counts + per-table CSVs + the full JSON + the source PDF, and an About & Validation tab. Extraction breakdown: Transactions Part 7 = 21,285; Holdings Part 6 = 6,181; Business entities Part 2 Schedule 1 = 501; Liabilities Part 8 = 11; Gifts Part 9 = 11; Spouse assets and income Part 5 = 11; Positions Part 1 = 4; Agreements Part 3 = 3. Excludes the 54-page Exhibit A trademark schedule (unstructured) and Part 4 (filed not applicable). Non-obvious rule flagged in the post: the annual's transaction section does NOT repeat trades already disclosed on the 278-T trade reports (OGE rule, and this filing uses it), so the 21,285 trades in the annual are ones the public had not seen before (mostly from the managed stock accounts), while the municipal and corporate bond trades are only on the 278-Ts - neither document alone is the full 2025 trading record, the union is; empirically the two sets are essentially disjoint, and the filing's own cover notes that late filing fees were paid for transactions not previously reported on 278-Ts. Trading detail: 15,524 purchases against 5,761 sales, midpoint ~$942M bought vs $286M sold (net buyers all year), across 8 managed accounts (uneven - Account 7 alone holds 10,311 trades, Account 8 has 3,972, Account 6 has 2,130, Account 1 has 1,757), 2,148 distinct securities, 51% of trades in the $1,001-$15,000 disclosure band and 83% under $50,000 (pattern of professionally-managed direct-indexing / diversified accounts, not concentrated stock-picking), trades on 142 trading days including net buying near the bottom of the April 2025 drawdown. Top securities by gross midpoint volume with tickers consolidated: Microsoft (~$43.7M bought / $1.7M sold, 84 trades), NVIDIA ($42.0M bought, 65 trades), Apple ($41.4M bought, 71 trades), Amazon ($21.6M bought, 74 trades), Alphabet ($18.5M bought, 93 trades); by trade count Alphabet 93 / Meta 86 / Microsoft 84 / Amazon 74 / Apple 71; money-market sweeps excluded. Business income: 97 exact-dollar business lines totaling $2.16B - Celebration Coins royalties $635,068,835, World Liberty Financial token sales $526.8M across token-sale lines (main $236.25M + per-wallet distributions of $150.6M ETH / $56.0M USDC / $42.3M USD / $33.5M BTC), stablecoin-related DT Marks SC LLC $196.9M, Trump Endeavor 12 (Doral golf resort) $121.9M, Mar-a-Lago Club $77.5M, WLF Holdco equity sale $65.6M. Litigation settlements $86.5M - Twitter/X $8M, ABC $16M, CBS $16M, Meta $24.5M, YouTube $22M. Melania Trump entities separately $17.2M exact license proceeds in Part 5 (film $10.71M + NFTs $6.01M + book $0.52M). Note that press coverage generally aggregates crypto items to ~$1.4B total but the tool lists each line as filed rather than as one combined number. Holdings: 6,181 lines totaling ~$1.86B midpoint across the 8 investment accounts + a revocable trust + a family trust + direct holdings - heavy in municipal bonds and blue-chip equities. Revocable trust holds a ladder of brokerage money-market accounts including two reported at 'Over $50,000,000' each, and the direct holdings include a line reading 'INVESTMENT IN GOLD BARS' in the $500K-$1M band. Liabilities: 11 lines including the two E. Jean Carroll judgments (one over $50M stayed pending appeal + bonded), the NY AG judgment noted as overturned on appeal, a Charles Schwab pledged-asset line over $50M opened in 2025, and several mortgages three of which are marked paid off in 2025. Gifts: 11 gifts totaling $372,050 - mostly event tickets (Super Bowl, FIFA World Cup Final, Ryder Cup, UFC) plus a $250,000 sculpture. Convention flagged: securities values and trade amounts are disclosed as ranges so every dollar total involving securities uses the midpoint of each range and 'Over $X' ranges use the lower bound - treat those totals as approximations; business income figures are exact dollar amounts as filed. Validation methodology on the tool: (1) two independent extraction methods with unrelated parsing engines reconciled field-by-field across every row to 100% agreement, (2) completeness gates on the filing's own row numbering + every amount / type / date matched against the official OGE vocabulary, (3) independent AI vision cross-reads on sampled pages + the full business-entity schedule blind to the dataset with disagreements adjudicated against a high-resolution page image (zero extraction errors found), (4) external tallies checked against reported figures (exact-dollar match on the $635M Celebration Coins line). Filing quirks preserved as filed (inconsistent capitalization, occasional typos, filer-truncated names). Author flags plainly that OGE publishes the filing only as a PDF with no machine-readable version, and this dataset is a best-effort reproduction of a 927-page government document not the document itself - the source PDF is one click away on the tool for verification. Sources: the OGE-certified 278e PDF (927 pages) and the OGE release note of June 30, 2026. Analytical release post - single-image, one-pager PNG at the bottom. AI-readable: https://www.tigzig.com/ai/posts/trump-2025-annual-disclosure-jul2026.md - [India bank credit, May 2026: up 18%, and the mix is where the story is](https://www.tigzig.com/post/india-bank-credit-may2026) - Tags: portfolio-quants Analytical commentary on RBI Sectoral Deployment of Bank Credit for May 2026 - total bank credit at about Rs 215 lakh crore, up 18% year-on-year with banks adding roughly Rs 32 lakh crore over twelve months. The mix is where the story is: loans against gold jewellery grew about 105% (more than doubled to ~Rs 5.1 lakh crore, share moving from 1.4% to 2.4%), and bank lending to NBFCs grew about 34% (share 8.5% to 9.7%) - gold loan companies sit inside the NBFC bucket so both banks and NBFCs are lending more against gold at the same time (Equifax independently confirms gold loan originations up ~103% YoY for the quarter to March 2026). Slow lane: housing (largest consumer segment at ~Rs 33.7 lakh crore, ~16% of all bank credit) grew only 11%, well under the 18% average, and lost the most share; credit card outstanding essentially flat, up 1%. The mechanism is not household preference - it is capital rules. RBI's November 2023 risk-weight hike on unsecured lending (personal loans and credit cards) and on bank lending to NBFCs deliberately excluded loans secured by gold, plus housing, education and vehicle loans - so one type of lending became costlier on capital while gold stayed cheap. February 2025 partly reversed the NBFC and microfinance weights, which is part of why the NBFC number is as high as it is. Second driver: gold price up around 39% YoY through end-May 2026 boosted collateral value on gold loans - but gold peaked near USD 5,370 in early March 2026 and has since fallen ~23% to around USD 4,130 by early July 2026, so loans given near the top are the tight ones on LTV (still not a segment-wide problem because gold is higher than a year ago, but the group of at-risk loans grows if the price keeps falling). One important correction: NBFC and microfinance did NOT both boom - microfinance actually shrank ~9% YoY to roughly Rs 3.33 lakh crore after a stressed stretch and is only now recovering. Post explicitly is NOT claiming households are consciously swapping credit cards for gold loans - only that the flat cards and fast-growing gold share a common cause (capital rules + gold price). Includes pointer to the interactive tool on tigzig -> Tremor -> India Credit for sorting by growth / share / share of new credit added, with CSV download. Full source list: RBI Capital Adequacy Directions 2025 (RBI/DOR/2025-26/151 for banks, /345 for NBFCs), the three superseded risk-weight circulars from 2023 and 2025, the RBI 4-Dec-2025 consolidation of 9000 circulars into 238 Master Directions (unchanged values), the forthcoming Standardised Approach Directions 2026 effective 1 April 2027, plus Equifax gold + microfinance releases and COMEX gold futures via Tremor. Single-image analytical post - one-pager PNG at the bottom. AI-readable: https://www.tigzig.com/ai/posts/india-bank-credit-may2026.md - [New Hub - Private Credit Stress on Tigzig.com. 19 Analyses, 3 Live Tools, Regulator Reports on One Page.](https://www.tigzig.com/post/tigzig-private-credit-hub-jul2026) - Tags: portfolio-quants Announcement post for the new Private Credit Stress hub on tigzig.com (/private-credit) that consolidates the author's ongoing coverage - 19 analyses, 3 live tools, and the underlying regulator reports on one page. Framing set at the top: 'is private credit cracking? Depends who you ask' - 2008 mortgage-market analogy where the market was either perfectly stable or falling apart depending on the source, right up to Lehman. What the last 30 days added: $14B of investor money sitting behind 5% redemption gates, one Blue Owl fund with redemption requests for 38% of its shares, a BlackRock BDC chief exiting mid federal valuation probe, and PIMCO calling out a 'confidence gap' where NAVs reflect manager marks rather than a shared clearing price - so the question has moved from 'are borrowers defaulting' to 'can we trust the marks'. Post also carries two LinkedIn-comment sections. Section one - 'The real story: in just one month supervisors moved from writing warnings to running drills' - the June regulator drills: ECB doubled its private credit probe to 20+ banks with annual reporting (Jun 15), France ran its first ever system-wide NBFI stress test with Banque de France + ACPR + AMF, 25 institutions, fire-sale and interconnection risk (Jun 17), Bank of England sent 46 firms a hypothetical five-year recession (Jun 19), and at Sintra both Lagarde and Bailey flagged non-bank oversight in the same week. Warnings are cheap; stress tests cost money and staff, so three central banks funding drills in one month is not idle curiosity. Bull case acknowledged - gates working as designed so far, no fire sales, Goldman and Oaktree saw redemption demand below their caps. Section two - 'Market for lemons' - Sarah Breeden (Bank of England deputy governor for financial stability) April warning that private credit could tip into an Akerlof-style lemons market: no market price (the manager's own mark IS the price), stacked leverage at borrower + fund + sponsor, sliced structures too complex for anyone outside to see through - same features 2008 CDOs ran on. Same worry echoing across FSB (data gaps + valuation opacity), OCC (PIK masking credit deterioration), PIMCO (confidence gap). Ties back to the author's May 2026 'private credit market for lemons' post. 2-page overview PDF carousel included. AI-readable: https://www.tigzig.com/ai/posts/tigzig-private-credit-hub-jul2026.md - [BIS, the Central Bank of Central Banks, Just Red-Flagged the AI Boom. Railway Mania, Roaring 20s, Dotcom - Same Chart.](https://www.tigzig.com/post/bis-ai-boom-red-flag-central-banks-jun2026) - Tags: portfolio-quants Commentary on the Bank for International Settlements' (BIS - owned by 63 central banks) June 2026 Annual Economic Report that flagship-red-flags the AI boom. BIS charts today's AI boom next to canal mania, railway mania, roaring 20s and dotcom - each of which attracted 'capital in excess of what commercial returns could ultimately justify' and ended in economy-wide recessions. Six BIS red flags: $1trn+ hyperscaler AI capex outpacing free cash flow (part funded by debt); circular financing with 'the same asset being pledged multiple times' (2008 language, in print before the event); valuations pricing growth above anything these firms have ever delivered; the bust is modelled in the BIS adverse scenario (sector surplus goes negative); direct lenders quadrupled AI/IT lending to ~15% of books; firms signalling automation on earnings calls (BIS 'demand bottleneck' scenario - every displaced worker is a lost consumer). Charles Mackay's 1841 book 'Extraordinary Popular Delusions' invoked as historical parallel. Ties to author's earlier documented calls since March (Tremor Early Warning, Irrational Exuberance at S&P 7,400, Private Credit as Market for Lemons). Post also carries two companion pieces from Ashwinder Singh Bakhshi (22 years fixed-income, former MD Barings): 'phantom collateral' on the same BIS sentence about pledged assets, and 'Margin Called' on Korea's KOSPI 100% rally with W148 trillion of foreign-institutional selling absorbed by retail on record margin debt. 10-slide deck with BIS charts + author's read on each. AI-readable: https://www.tigzig.com/ai/posts/bis-ai-boom-red-flag-central-banks-jun2026.md - [QREP in Excel: 81 Risk and Return Metrics Inside Your Sheet Through Claude in Excel.](https://www.tigzig.com/post/qrep-claude-in-excel-mcp-jun2026) - Tags: mcp, claude-in-excel, portfolio-analytics, excel Standalone one-pager release: QREP, a Tigzig MCP server, brings 81 risk and return metrics straight into Excel through Claude in Excel - asset returns, drawdowns, Sharpe, Sortino, alpha, beta, volatility and more. Just ask Claude in Excel things like 'Compare gold and bitcoin, last 10 years' or 'compare Mag 7 past 10 years' - any stock, commodity or crypto that's on Yahoo Finance. Change symbols, time period, run cuts your own way, format it your way, push it into a deck, or do it directly in PowerPoint. MCP guide at tigzig.com -> MCP -> QREP. For AI-coders, just ask Gemini / ChatGPT / Claude to help connect Claude in Excel to QRep from tigzig.com - it walks through. Wary of someone else's MCP server? The code is open source, a single Python file - ask your AI to deploy the QREP MCP server from tigzig.com. Free to use. Powered by Ran Aroussi's QuantStats. Three companion guides linked: Claude Cowork Guide, Claude in Excel & PowerPoint 26 working tips, and Claude as the universal agent. AI-readable: https://www.tigzig.com/ai/posts/qrep-claude-in-excel-mcp-jun2026.md - [Tigzig Tremor v2 Is Live. 330+ Macro + Credit Indicators Behind an MCP. 83% Lighter Startup. Just Ask Your AI Agent.](https://www.tigzig.com/post/tigzig-tremor-v2-mcp-330-indicators-jun2026) - Tags: mcp, portfolio-quants Release announcement for Tigzig Tremor v2 - the MCP behind tigzig.com's 330+ macro and credit indicators across US, India, global macro, credit, markets and FX (17+ official publishers). Pulling macro data for analysis is mostly grunt work - finding the series, downloading, cleaning - so it now sits behind an MCP that AI agents (Claude Cowork, Claude in Excel, any agent) can ask in plain English. Sample asks in the post: 'US consumer net charge-offs, banks vs credit unions, last 15 years, chart it', 'S&P 500 and CAPE past 25 years, dual axis', 'Overlay Brent and WTI crude past 5 years'. The headline v2 change: catalog discovery split from tool calls. v1 stuffed the whole catalog into one ~8,000-token tool description the agent loaded up front; v2 surfaces an 8-category menu, the agent drills into only the tables it needs and pulls only the relevant bits - startup load cut from 7,854 to 1,352 tokens, 83% lighter. The discovery layer also carries house notes on each series (e.g. 'this charge-off is quarterly, multiply by 4 to annualize') so the AI does not quietly get it wrong. Free, open, no sign-up - use the live MCP, install your own, hit the APIs directly, or download the whole DB in your chosen format. Humans: tigzig.com -> TREMOR -> API / MCP. AI agents: api.tigzig.com. AI-readable: https://www.tigzig.com/ai/posts/tigzig-tremor-v2-mcp-330-indicators-jun2026.md - [Euro-Area NPLs Look Calm. Split by Bank Size, the Small-Bank Corporate Book Is at 5.16% and Climbing.](https://www.tigzig.com/post/ecb-npl-small-bank-corporate-strain-jun2026) - Tags: portfolio-quants Euro-area non-performing loans are near a decade low - but the calm headline hides where the stress is. Split by bank size and the small banks (less significant institutions, LSI - the Sparkassen, cooperative and savings banks; ~15% of euro-area bank assets) have pulled ahead of the big banks (significant institutions, SII, ~85% of assets). Big-bank NPLs sit near 2%; the small-bank corporate book has climbed to 5.16%, up about a third since 2023 and still rising. The consumer book is steady; the corporate book is the engine, and within that the two stressed corners are commercial real estate and small-business loans. Germany, Austria and Italy carry most of it - right where corporate insolvencies are running hot (Germany +57% vs the 2016-19 pre-pandemic May average per IWH; Austria 6,810 full-year 2025, +3.4%, property failures +35%; Italy ~+38% YoY per Allianz Trade). Households stay calm in the big systems (Germany 1.6% NPL, Netherlands 0.7%); the euro-area signal is corporate. Supervisors agree (ECB SREP 2025, OeNB FSR 51, ECB FSR May 2026) and tailored letters have gone to banks. Cycle to watch, not a system in trouble. 10-slide deck pulled live from the ECB SDMX REST API on 20 Jun 2026 (Q1 2026 release for SII / Q4 2025 for LSI - LSI lags one quarter by design, so SII vs LSI comparisons all use Q4 2025). Full 8-table copy-as-markdown dataset published at tigzig.com/ecb-npl-data-tables. Plus the parallel for the US: bank headline is also calm but the strain sits on the consumer (cards + autos) and in private credit, where losses hit the P&L directly and never show as a bank charge-off. AI-readable: https://www.tigzig.com/ai/posts/ecb-npl-small-bank-corporate-strain-jun2026.md - [May 2026's Record US Retail Sales Number Is Hiding the Pain. Real Spending Hasn't Grown in Five Years. The Consumer Is Squeezed.](https://www.tigzig.com/post/us-consumer-squeeze-real-retail-jun2026) - Tags: portfolio-quants The May 2026 record US retail sales headline ($763.7bn, +6.9% YoY) is hiding the pain of a consumer being squeezed - and the squeeze was here long before the Iran war. Strip out inflation and real goods spending has not grown in five years: of the $763.7bn rung up in May 2026, only $605.9bn is real 2021 goods - the other $157.8bn is pure inflation. Households are holding the line by stretching: personal saving rate back to pre-2008 lows, NY Fed HELOC balances up 40% since 2021. The strain is starting to show: University of Michigan consumer sentiment collapsed to 44.8 (near the lowest on record), and 90+ day delinquencies on all consumer debt are back to 3.4% - past the 2007 mark. Real GDP still grows ~2% on services, AI investment and government, so this is a squeeze on the household goods budget, not an economy-wide downturn. The proof is the balance sheet: thinning savings, more borrowing, delinquencies past 2007. Companion piece: jobs market softening since 2024 (unemployment 4.3%, underemployment 8.1%, long-term joblessness near a 3-year high). Cheaper oil is real relief on the price side, but it does not refill a drained savings account or put the long-term unemployed back to work. 6-slide deck with every series live on tigzig.com -> Tremor (retail RSAFS + RRSFS, saving rate BEA, HELOC + delinquency NY Fed, sentiment U-Mich), pullable by API, Excel, or AI agent. Real retail definition: nominal Advance Retail & Food Services Sales deflated by headline CPI (the honest test of volume vs price). AI-readable: https://www.tigzig.com/ai/posts/us-consumer-squeeze-real-retail-jun2026.md - [Agentic Coding and Persistent Returns to Expertise - Anthropic's 400k Claude Code Sessions, Summarized](https://www.tigzig.com/post/anthropic-claude-code-expertise-survey-jun2026) - Tags: portfolio-quants Anthropic just published 'Agentic coding and persistent returns to expertise' - a privacy-preserving analysis of ~400,000 interactive Claude Code sessions from ~235,000 people, October 2025 to April 2026. Three takeaways pulled into a 9-slide summary deck with every headline a direct quotation: (1) coding background is becoming less relevant - every major occupation succeeds at rates within a few points of software-related occupations (software engineers verified at 34%; all ten largest groups within seven points); (2) management occupations show the highest verified success, slightly above software engineering, which Anthropic reads as management skills transferring to directing an agent (with a measurement caveat); (3) the more domain expertise a person brings, the more work Claude does per instruction (more than twice the actions, five times the output from the same prompt) and the more often the session ends in success (verified success doubles 15% to 33%, novice-to-intermediate is where most of the jump happens, and only 5-7% of expert sessions end abandoned vs 19% for novices). Bonus: the share of sessions spent fixing broken code fell from 33% to 19% while average task value rose 27% vs a freelance-market benchmark. Anthropic's honest caveat: classifiers remain challenging to validate at scale; they cannot measure whether the code is actually used. Matches the author's 25 years as an analyst - on coding the agents win by multiples, on deep domain the human still wins. AI-readable: https://www.tigzig.com/ai/posts/anthropic-claude-code-expertise-survey-jun2026.md - [The Fastest Way to Use Tigzig.com? Don't Click. Point Your Claude / AI Agent at It.](https://www.tigzig.com/post/tigzig-agent-first-just-point-your-claude-jun2026) - Tags: portfolio-quants, mcp The fastest way to use tigzig.com is to not click - point your Claude or AI agent at it. The site is built AI-agent-ready: 40+ analytics apps, open analytics APIs, MCP servers, 200+ guides, plus a repos shelf - all free, no sign-up. An agent pointed at the site can find the right tool / guide / dataset for the task, read app and database data and run the analysis, call the analytics APIs, set up MCP servers, and even download / install / deploy an open-source repo. Claude Cowork is particularly good at this - it runs its own sandbox inside the Claude desktop app, so once a domain is enabled it makes the API calls itself, pulls the data, runs the analysis and hands back a PDF. Codex, Cursor, any agent works the same way. Rather explore yourself? The whole site is still right there - the agent just gets you there faster. Don't believe it? Point your agent at tigzig.com, let it explore, then ask it 'how do you like the site?' AI-readable: https://www.tigzig.com/ai/posts/tigzig-agent-first-just-point-your-claude-jun2026.md - [Why Trump Is Going After Jamie Dimon Right Now. Two Fronts - Debanking + Crypto. The DOJ Subpoena Made It Real.](https://www.tigzig.com/post/trump-vs-dimon-debanking-crypto-two-fronts-jun2026) - Tags: portfolio-quants Why is Trump going after Jamie Dimon right now, five years after JPMorgan shut his accounts weeks after Jan 6, and why this particular week? The legal war front: Feb 2021 debanking, Aug 2025 Fair Banking order, Jan 2026 Trump sues Dimon for $5 billion, and for months the lawsuit just sat there - lawyers filing papers, nothing moving. This week it got teeth: on 10 Jun 2026 the DOJ (through Jeanine Pirro's office) subpoenaed JPMorgan, Bank of America and Wells Fargo over the debanking. Private lawsuits limping along are one thing; the federal machinery moving in behind them is a different beast. Running alongside is the crypto fight - Trump signed the GENIUS Act last summer (the big stablecoin law) and wants the US to be 'the crypto capital of the world'; his family has crypto ventures of their own. Dimon has been the loudest bank voice fighting the next bill (CLARITY Act) and told the Coinbase CEO to his face he is full of it. Then on 5 Jun 2026 - days before the subpoenas landed - the big banks announced they are building their own blockchain money, a shared tokenized deposit network, so customer deposits stay locked in the regulated banking system and do not bleed out into the stablecoins Trump has been backing. Did the crypto fight cause the DOJ to move? No paper trail. But the incidents line up too close to wave away - read the motive for yourself. AI-readable: https://www.tigzig.com/ai/posts/trump-vs-dimon-debanking-crypto-two-fronts-jun2026.md - [The Fable 5 Shutdown Isn't About a Jailbreak. It's the Anthropic vs US Government Standoff Coming to a Head.](https://www.tigzig.com/post/anthropic-vs-us-government-fable5-shutdown-jun2026) - Tags: portfolio-quants This week's Fable 5 shutdown is not really about a jailbreak. It is the Anthropic vs US government standoff coming to a head. Months ago Anthropic refused to give the Pentagon 'all lawful use' of its models, holding two red lines - no fully autonomous weapons, no domestic surveillance. Trump ordered every federal agency to stop using Anthropic, and the Pentagon branded it a 'supply chain risk', a label normally reserved for foreign adversaries - the first American company to get it. The defense work went to OpenAI. A federal judge called the blacklisting 'classic illegal First Amendment retaliation' and 'Orwellian', but an appeals court let the blacklist stand while the case runs. Meanwhile the NSA - under the same Pentagon - is reported (per Axios) to be using Anthropic's most powerful model anyway: too dangerous to allow, too useful to drop. This week Commerce blocked all foreign nationals from Fable 5 and Mythos 5 over a jailbreak Anthropic says is minor and doable on other models. To comply, Anthropic switched both models off worldwide. The irony: the Pentagon's whole fear was that Anthropic could pull the plug on its own model. This week, Anthropic pulled the plug. A standoff between a company that draws red lines on its own tech and a state that treats frontier AI as too strategic to leave to a company. The company has the model. The government has the machinery. AI-readable: https://www.tigzig.com/ai/posts/anthropic-vs-us-government-fable5-shutdown-jun2026.md - [Markets Are Celebrating an Iran Deal. Nobody Has Agreed Which Deal. Peace Is Balanced on Loss of Face.](https://www.tigzig.com/post/iran-deal-fragility-peace-on-loss-of-face-jun2026) - Tags: portfolio-quants Markets are celebrating an Iran deal, but nobody has agreed which deal. Trump says the war is 'ended'; Tehran calls the reports 'merely speculation' and says there is no final decision yet. CNN counts ~40 times Trump has called a deal imminent. ~100 days into the war the macro damage is real: UK GDP at -0.1% in April (released today), US gasoline $4.65, stressed US consumer, global economy showing cracks. Two drafts in circulation, and they look almost nothing alike. Tehran's 14-point version (leaked to Iranian state media, picked up by CNBC): ceasefire on all fronts, naval blockade lifted, Hormuz reopened on Iran's arrangements, oil sanctions suspended, $12bn unfrozen before talks even begin, $300bn reconstruction plans, US forces out, missiles and proxies off the agenda - and the nuclear negotiation only after all of that, with a 60-day window. Washington's version (via diplomat to CNN): Hormuz reopened immediately with no Iranian fees, sanctions relief with no set date, deal 'satisfies all US requirements on the nuclear issue.' Each side's plan reads like the other side's surrender. Stocks jumped ~2%; Brent futures fell 4%. Whichever version gets signed as written, the other side loses face. My read: whatever gets signed will be brittle - this peace has already cracked four times since March. If it survives its own 60-day window, we are through to the other side. AI-readable: https://www.tigzig.com/ai/posts/iran-deal-fragility-peace-on-loss-of-face-jun2026.md - [There Is No Modern Playbook for This. US Core Inflation at 3.3%, Re-Accelerating. Producer Prices at 6.4%. Consumer Delinquencies Past 2007.](https://www.tigzig.com/post/us-inflation-shock-no-modern-playbook-jun2026) - Tags: portfolio-quants US core PCE - the gauge the Fed targets at 2% - is at 3.3% and re-accelerating. Outside Covid, last at this level in April 1992. 25-year pre-Covid average: 1.7%. It has now spent 62 straight months above target. And the pipeline says more is coming: PPI final demand at 6.4% - hottest in the modern series outside Covid - with core PPI at 4.9%; PPI is running 2.2 points ahead of CPI, putting the bigger share of the bill on producers (margin compression) but with consumer pass-through inevitable. The consumer is already stretched: gasoline at $4.65 (only June/July 2022 ever higher), and 3.4% of consumer debt is in the 90+ DPD bucket - past the 3.1% mark of late 2007 and more than double the end-2022 low, rising in 12 of the last 13 quarters. Against all of this the S&P set a record at 7,610 on June 2 with Shiller CAPE 2nd-highest in 145 years and Michigan sentiment lowest in 73 years - a handful of AI names doing most of the lifting. The last two times the market was priced like this while the economy cracked underneath - 2000 and 2007 - the index halved. 6-slide deck with full series codes, method, and the dot-com (-49%) / GFC (-57%) drawdown references. AI-readable: https://www.tigzig.com/ai/posts/us-inflation-shock-no-modern-playbook-jun2026.md - [Q1 2026 US Lending Data Live on Tigzig. NCUA + FDIC + NY Fed in One API. Two of Three Not on FRED. AI-Agent Ready.](https://www.tigzig.com/post/us-lending-data-q1-2026-tigzig-api-jun2026) - Tags: portfolio-quants Q1 2026 update of US lending aggregates is now live on Tigzig - loans, delinquency, charge-offs by segment back to 2002, ready for AI agents (Claude Cowork, Claude Code, Codex, Cursor) and for the human web UI on TREMOR. Three datasets: credit unions (NCUA), banks (FDIC), consumer (NY Fed) - two of those three are not on the FRED API; all three are on the Tigzig API with no auth, free. Plus 100+ macro indicators (US and India) to overlay on the data. All sourced from the regulators' own releases and validated before publishing - methodology and validation are on the site. AI-agent ready surface includes: charts and custom cuts on the web, an open API, an MCP server for Claude / Codex / any agent, and full-database downloads in Parquet, SQLite, DuckDB and CSV. This is the same data behind the recent US credit-union red flag deck (card charge-offs past their GFC peak 10 straight quarters) and the consumer credit stress piece. Point your AI at tigzig.com and it connects to the data, explores, and runs the analysis as you direct. AI-readable: https://www.tigzig.com/ai/posts/us-lending-data-q1-2026-tigzig-api-jun2026.md - [Two Announcements, One Day Apart. Operational Seats Moving Out of India. AI Compute Moving In.](https://www.tigzig.com/post/india-offshore-shift-ai-compute-jun2026) - Tags: portfolio-quants Two announcements, one day apart: Opendoor shut its India operations (~250 FTE) and is shifting to smaller AI-native US teams; Meta signed its first AI data center deal in India. Neither announcement is a first - what caught the eye is both reported within a day of each other. Engine 1, the seats: India offshore IT and BPM employs 5.95 million people and exports $246B a year; TCS announced ~12,000 layoffs last year and silent layoffs run at ~50,000 a year. Operational work is going home to smaller US AI-native teams. Engine 2, the capital: India data centers + power, grid, construction headed for ~10 GW by 2030 with $250bn+ already committed by Google, Meta, Adani, Reliance, Microsoft, AWS, TCS. The labour-arbitrage engine is showing cracks while the capital engine accelerates at dot-com cadence. Is this the real shift? Too early to call. The new engine runs on hardware, construction, power - and hard-hat engineers. Companion to the prior 'India's AI data center wave' and 'India economy red flag' analyses. AI-readable: https://www.tigzig.com/ai/posts/india-offshore-shift-ai-compute-jun2026.md - [US Unemployment Is 4.3%. The Stuff Underneath Says Otherwise. 2M Jobless Over Six Months, Up 3 Straight Years.](https://www.tigzig.com/post/us-unemployment-long-term-hidden-jun2026) - Tags: portfolio-quants US unemployment is 4.3% and the headline curve looks like it is calming - eased from 4.5% in Nov, held at 4.3% since March. The data underneath says otherwise. Long-term joblessness (27+ weeks) has nearly doubled since 2023 to 2.0 million people, with three straight years up and no give-back. When long-term pulls away from the headline like this, that is the 2008 pattern - into 2008 the long-term line towered about 6x its pre-crisis level while U-3 only doubled. Covid never had this shape; rehiring was too fast. Today's rise has the slow-grind 2008 shape, with no recession to blame. Composition: the long-term share fell to 17.8% after Covid (Feb 2023) and is back to 27.5% now (GFC extreme was 45.5%) - more than one in four of the unemployed are now past the line that scars. Structural test: measured against the whole workforce, long-term joblessness has stepped up once in 25 years - 0.53% to 0.81% in the dot-com era. This cycle is at 1.18% in May and still rising. Is AI doing to the jobless floor what dot-com did? Too early to call - the test comes when this cycle finally turns. Fits the picture from last week's note: consumer sentiment at a 73-year low, valuations near 145-year highs. 5-slide deck on BLS / FRED data through May 2026. AI-readable: https://www.tigzig.com/ai/posts/us-unemployment-long-term-hidden-jun2026.md - [India Inc's BRSR Filings - All 656 in One Analytics Workspace. Wage Gap at Top Management: 68%. 1 in 3 Workers on Contract.](https://www.tigzig.com/post/brsr-india-esg-explorer-jun2026) - Tags: portfolio-quants India Inc's ESG (BRSR) filings - workforce, wages, complaints - sit in separate XBRL files. Pulled 656 of them - the full Nifty Total Market basket, FY25 - into one analytics workspace on tigzig.com -> VIGIL -> BRSR. Aggregate, compare, benchmark, read the raw filing. Coverage: 656 companies across 8 indices and 22 sectors, ~1.2 crore workers. What the data shows: ~1 in 3 of India Inc's workforce is on contract; female share of total workforce under 1 in 5; median wage gap - women paid 11% less at employee level and 68% less at top management (KMP, Key Managerial Personnel). From aggregates to company level with sector benchmarking - every chart clicks through to the source XBRL filing. Full CSV download. Free. FY26 filings are coming in through AGM season; next data refresh planned for August. AI-readable: https://www.tigzig.com/ai/posts/brsr-india-esg-explorer-jun2026.md - [Red Flag: US Credit Unions. A $1.73T System at GFC-Era Losses. Card Charge-Offs 10 Straight Quarters Past the Crisis Peak.](https://www.tigzig.com/post/credit-union-red-flag-jun2026) - Tags: portfolio-quants Red flag on US credit unions - a $1.73 trillion lending system running GFC-level losses in consumer, with no recession on the board. Card charge-offs hit 5.30% in Q1 2026, above the 2008-09 crisis peak (4.68%) for 10 consecutive quarters - a plateau, not a spike. Real estate and commercial are calm (59% of loans, 4% of losses). Consumer is 41% of loans and 95% of losses, with auto NCO at a fresh series record (0.97%) and cards at 33% of all CU loan losses. Measured vs each sector's own GFC peak: credit unions are at 113% on cards (past), banks just 38% - this is not system-wide banking stress, it is concentrated in credit unions. The silver lining: consumer balances are $19B below their end-2023 peak and falling, the shape of a deliberate tightening - but vintages already booked will run their loss curves. The Share Insurance Fund equity ratio is at 1.30% (below the 1.33% normal operating level); a wave could force a premium assessment on every surviving credit union (precedent: 2009-10 corporate CU crisis). The NCUA is run by a single board member - the other two were removed in April 2025, dispute now at the Supreme Court. Banks have Jamie Dimon. Credit unions have nobody. 13-slide carousel deck with full method, source notes and the failure-channel transmission path. Companion to the prior 'Auto Past the GFC Peak. Cards Almost There' post. AI-readable: https://www.tigzig.com/ai/posts/credit-union-red-flag-jun2026.md - [Index at a Record. Peak Valuation. Record-Low Sentiment. Last Two Times This Setup Held - 2000 and 2007 - the Market Halved.](https://www.tigzig.com/post/us-valuations-record-sentiment-low-jun2026) - Tags: portfolio-quants Index at a record. Peak valuation. Lowest sentiments. And the economy cracking. Last two times the market was priced up here - 2000 and 2007 - it halved. Shiller CAPE near 41 P/E, the highest in 145 years apart from the 1999-2000 dot-com bubble (44), above the 2007 peak (28). University of Michigan consumer sentiment at 44.8, the lowest in 73 years of data - below the 2022 low (50) and every recession since 1952. In dot-com it was all about page views with no line of sight on revenues; in 2026 it is all about compute and revenues with no line of sight on cash profitability. Companion to the prior 'Irrational Exuberance' note when the S&P was at 7,400. Consumer delinquencies high, unemployment high, producer prices the hottest in 25 years (excl Covid), oil and gasoline high, consumer stretched. Seven stocks doing most of the lifting in the index. Dimon called it too much exuberance. Buffett sitting on the biggest cash pile in Berkshire's history. Drawdown ground-truth from tigzig Market Tools: S&P 500 deepest -56.8% beginning Oct 2007, over five years to climb back to even, 58% of its time spent in the seven worst drawdowns. Not investment advice. AI-readable: https://www.tigzig.com/ai/posts/us-valuations-record-sentiment-low-jun2026.md - [Auto Losses Past the GFC Peak. Cards Almost There. Credit Unions Already at GFC Loss Rates. NY Fed + NCUA Data Now on Tigzig.](https://www.tigzig.com/post/consumer-credit-stress-fed-ncua-jun2026) - Tags: portfolio-quants NY Fed and NCUA aggregate loss / delinquency data comes out as a spreadsheet - pain to analyze. Pulled, disaggregated by quarter, validated and loaded into a database with an interface (tigzig.com -> TREMOR), an API (api.tigzig.com) and an MCP layer (mcp.tigzig.com). Quarterly coverage, by loan type, ~44 quarters, sourced from the regulators' own spreadsheets. And the data is talking loudly. Bank charge-offs look fine on the surface but the pressure is one step away from the banks: auto losses past the GFC peak, cards almost there. Credit unions running loss rates last seen during the GFC period - overall, consumer and cards; the card book has already pushed past its 2009 peak. And banks keep funding non-bank lenders - $1.65T to non-banks in Q1, up 42% in five quarters. AI-readable: https://www.tigzig.com/ai/posts/consumer-credit-stress-fed-ncua-jun2026.md - [Private Credit and BDC Stress. Discounts at 13-Year Lows. Withdrawals Past the Gate. Regulators Now Arriving.](https://www.tigzig.com/post/private-credit-bdc-stress-regulators-jun2026) - Tags: portfolio-quants The median listed BDC trades at 25% discount to NAV, near its deepest in 13 years excluding Covid - 0.75x price to book today. Pimco's CIO: 'the first sustained default or loss cycle in many, many years.' Q1 losses: FS KKR $441M, Blue Owl's BDC $184M. Withdrawal requests blew past the 5% redemption gate at Blackstone's BCRED (~10%) and Cliffwater (17%) - a first-ever net outflow. Private-credit rating downgrades up 50% in a year. UBS sees defaults rising from ~4.4% to 9-10% by end-2026. US issuance fell ~40% vs Q1 to $44.8B in the 3 months to May. Partners Group warns the redemption pressure that began in private credit is now spreading into private equity. The regulators have started arriving: federal prosecutors in NY questioning BlackRock executives over how their credit fund valued loans; FSB flags private credit's leverage and interconnections as a source of broader risks to financial stability; ECB puts US private credit on its watchlist as a spillover risk into Europe; Sarah Breeden at the Bank of England calls it a potential 'market for lemons' (Akerlof). Companion update to the prior 'Is Private Credit Turning Into a Lemon' analysis. AI-readable: https://www.tigzig.com/ai/posts/private-credit-bdc-stress-regulators-jun2026.md - [The Data Behind My Analyses Is Now Open. Download the Whole Database or Query a Single Row.](https://www.tigzig.com/post/tigzig-apis-data-open-jun2026) - Tags: portfolio-quants, mcp The analyses I've been posting these past months all run on the same data - and that data is now open to everyone. US delinquencies, private credit, life insurance, the markets piece - all off primary data, FRED, RBI, Fed, FDIC, refreshed three times a day by the same pipeline that runs the live apps. Three open APIs powering the Tigzig apps: MF NAV (18,000+ schemes, 13 yrs, ~20M daily NAVs), VIGIL (corporate signals: ratings, insider, pledge, SAST, RPT), TREMOR (~300 macro indicators). Pull a single row across ~30 endpoints, or take the whole database from one endpoint in SQLite, DuckDB, Parquet, CSV or TSV - refreshed 3x a day by the CI/CD that powers the apps. Connect to the live MCP server, or wrap any of these APIs in your own MCP. No auth. Rate limited. Free to use. For humans: tigzig.com -> APIs. For agents: agents.tigzig.com. AI-readable: https://www.tigzig.com/ai/posts/tigzig-apis-data-open-jun2026.md - [Hormuz Is Quietly Opening. The First Good News in 100 Days. And It Is Running in Two Lanes.](https://www.tigzig.com/post/hormuz-quietly-opening-jun2026) - Tags: portfolio-quants A trickle of tankers is getting out of the Strait of Hormuz again - the first real relief after more than three months of a shut chokepoint. But how they are getting out is the interesting bit. There is not one quiet arrangement, there are two. One lane Iran controls and charges a toll for, close to the Iranian coast (most traffic this way - CSIS says half the vessels since early March are from just four countries with China at the top). One lane the US Navy quietly watches over near the Oman coast - mines cleared, ~70 ships guided through in three weeks per New York Times sources; officially the US says it is not escorting, just coordinating. Tankers go dark on both sides - on Iran's lane to stay off the Western sanctions record, on the US lane to not broadcast their position to Iran. Use Iran's lane and you risk US sanctions; use the US lane and you risk an Iranian attack. Per Kpler, of the ~895 ships that crossed early March to mid-May, just over half took Iran's route and about 40% went by a route nobody can quite place - that 40% is the story. Producers shut in ~11 mbd; Energy Aspects: oil flow recovery will be slow, uneven and possibly incomplete. Gulf producers are even building pipelines to go around Hormuz. The US-Iran interim memo (30-60 days) is in the final stretch, leaving the strait basically under Iranian control however the fees end up dressed. Opening, yes - real. Solved, no. AI-readable: https://www.tigzig.com/ai/posts/hormuz-quietly-opening-jun2026.md - [Bank Loss Rates Look Calm. The Stuff Underneath - Consumer, Private Credit, Non-Banks - Says Otherwise.](https://www.tigzig.com/post/bank-loss-rates-look-calm-storm-brewing-may2026) - Tags: portfolio-quants US bank net charge-offs at 0.58% in Q1 2026 - right at pre-GFC, miles under the GFC peak, so the headline number looks calm. But pull the consumer book out and consumer NCO is already running hotter than pre-GFC at 2.9% vs 2.5% in 2007 - cards highest, auto rising. The sharpest stress sits off the bank books: most private credit losses are marked-to-market and hit P&L directly, never showing as a charge-off. Credit unions and non-bank consumer lenders carry the weakest paper, which loops back to banks via their non-bank and private credit lines. The macro is weak across unemployment, savings rate, producer inflation, oil and gas - all moving the wrong way. The bank NCO looks calm; the stuff it can't show (consumer cards, private credit mark-to-market, non-bank consumer lenders) says otherwise. Analysis supported by TIGZIG TREMOR self-serve analytics tool covering FDIC, NY Fed, NCUA and private-credit series. AI-readable: https://www.tigzig.com/ai/posts/bank-loss-rates-look-calm-storm-brewing-may2026.md - [ECB Stress-Tested Private Credit. Pensions Worst at 6% of Assets. Almost All the Damage Is the Wider Market Crash It Sets Off.](https://www.tigzig.com/post/ecb-stress-test-private-credit-may2026) - Tags: portfolio-quants The ECB just ran a three-stage stress test on private credit, part of the May 2026 Financial Stability Review special feature. Stage 1: direct private credit losses. Stage 2: contagion to leveraged loans and high-yield bonds. Stage 3: tail scenario (equities -30%, HY repriced -25%, money runs out of private credit funds). Almost all the simulated damage is Stage 3 - the wider market crash the scare sets off, not the loans themselves. Severe-scenario losses: insurance corporations ~4% of assets, pension funds ~6% (the worst-hit), banks barely move. Euro area's direct private credit exposure is tiny (insurers 2.3%, banks 0.2%), but the US owns multiples more - insurers ~10% (15%+ for PE-owned), banks ~1.3-7%, with $300B in private credit and $1.65T in broader non-bank lending. Author commentary: contagion is bigger than the asset (as in prior crises), and given simultaneous global pressures plus the dot-com / GFC playbook, this should not be treated as 'just tail risk' (GFC 2008 was supposed to be tail risk too, until Lehman). ECB report: 'Stress in global private credit markets and its implications for euro area financial stability.' AI-readable: https://www.tigzig.com/ai/posts/ecb-stress-test-private-credit-may2026.md - [FSB Just Published 50 Pages on Private Credit. The Title: 'Vulnerabilities in Private Credit.' Worth Reading.](https://www.tigzig.com/post/fsb-vulnerabilities-private-credit-report-may2026) - Tags: portfolio-quants The Financial Stability Board's 6 May 2026 report 'Vulnerabilities in Private Credit' - 50 pages. The body that coordinates the Fed, ECB, BoE and the world's other financial regulators putting on the record what they're collectively worried about - layered leverage, opaque valuations, PE-owned insurers, interconnections and instrument risks that aren't fully understood, with a potential for systemic risk to the financial system in stress scenarios. One-pager highlights: market sizing $1.5-2T narrow estimate (full market can't be sized); multiple layers of leverage stacked on top of each other; US insurance liabilities run by PE-backed insurers grown from $67B to $900B. FSB quote: 'interconnections between private credit funds and banks, insurers, and private equity firms are deepening, raising potential vulnerabilities... investors and other stakeholders may only have partial information and understanding of correlations and concentrations... the sector's complexity, leverage, and interconnectedness could amplify stress in adverse scenarios, posing broader risks to financial stability.' Continues the Tigzig private-credit dispatch series (4 prior pieces). AI-readable: https://www.tigzig.com/ai/posts/fsb-vulnerabilities-private-credit-report-may2026.md - [India Was the Market's Darling. Not Any More. The Growth Story Has a Big Red Flag.](https://www.tigzig.com/post/india-economy-red-flag-may2026) - Tags: portfolio-quants 13-slide deep dive on the India macro red-flag stack as of May 2026. GDP forecast trims across the board - Moody's FY27 at 6% (the low-end call), S&P 6.6% (from 7.1%), ICRA 6.2% (from 6.5%). IT sector silent layoffs - TCS ~12,000 cut, ~50,000 IT jobs going this year, ~500,000 at risk over 2-3 years, with the model itself being questioned as AI replaces offshore engineering work. Foreign portfolio investors net seller (FY26 net exit, BofA expecting selloff into 2027/2028); FDI anchor held at +$7.7B. Wholesale Price Index at a 13-year high (ex-Covid spike); the WPI-CPI lag means retail catch-up is the base case. Record merchandise trade deficit of -$333B (FY26) on flat exports (+0.9%) and rising imports (+7.6%); China overtakes US as India's largest trading partner. Oil shock still playing out - four fuel hikes in two weeks, Delhi petrol Rs 102, OMC losses ~Rs 30,000 crore/month per ICRA. IMD El Niño monsoon forecast at 90% of LPA - driest in 11 years - which none of the GDP downgrades have priced in. Bankers warning publicly (Uday Kotak at CII: 'it's coming, and it's coming big'); PM appealing for fuel austerity. For India, anything below 4-5% GDP growth is recession territory. Any one is manageable. All of them at once is the problem. Silver lining: the India AI data-centre buildout (Adani, Reliance, Bharti) - covered in the prior India's Next Tech Wave dispatch. AI-readable: https://www.tigzig.com/ai/posts/india-economy-red-flag-may2026.md - [Which Chart Is the Odd One Out? Three Macro Charts Tell the Same Story. One Doesn't.](https://www.tigzig.com/post/spot-the-odd-chart-out-may2026) - Tags: portfolio-quants Four-chart US macro one-pager (May 2026) asking the spot-the-odd-one-out question. Three charts show rising stress - U-6 underemployment at 8.2% (climbing since 2023, up from 6.7% Jan 2023 and past 8.7% Peak 2025), personal saving rate down to 2.6% (from 6.4% peak 2024 and 4.9% Jan 2023, the cushion is nearly gone), consumer 90 DPD loss rate at 3.4% (past the pre-GFC 3.06% reference, worst at credit unions and non-bank lenders). The fourth chart: S&P 500 at a record 7,580, up 86% over the three-year window. Three macro-stress charts in one direction; the index chart in the other. Tools that drive this kind of comparison are on tigzig.com - free, no login, 300+ series covering macros, prices, savings, labor and delinquencies, available via web interface, API or MCP for AI agents. AI-readable: https://www.tigzig.com/ai/posts/spot-the-odd-chart-out-may2026.md - [Banks Keep Funding the Non-Banks. $1.65T in Q1 2026, Up 42% in Five Quarters. US Banks NDFI Update.](https://www.tigzig.com/post/us-banks-ndfi-q1-2026-update-may2026) - Tags: portfolio-quants Q1 2026 update on US bank lending to non-depository financial institutions (NDFI) - the channel funding private credit. Balances hit $1.65T, up 42% in five quarters and now 14.2% of the entire bank loan book (up from 11.1%) or 7.1% of total assets (up from 5.6%). 622 banks. Top 10 hold 73% of all NDFI loans. Subcategory mix: Business Credit $435B (26%), PE Funds $383B (23%), Mortgage Credit $368B (22%), Other NDFIs $269B (16%), Consumer Credit $166B (10%). Top lenders: JPMorgan $238B, Wells Fargo $228B, Bank of America $213B, Goldman $123B, Citi $123B. Add undrawn commitments of $1.06T and total exposure hits $2.7T. The Fed, FSB, OCC, IMF, ECB, BoE and DOJ all flagging it; Fitch private-credit default rate at a record 6.0%; Bank of England calling it a 'market for lemons'. Tool live at tigzig.com/tools/us-ndfi (TREMOR) with bank-level balances, commitments, credit quality and exposure - free, no login, sourced directly from quarterly FFIEC Call Reports (Schedule RC-C). Continues the four-dispatch private-credit series (Mar 24, Mar 26, May 8, May 28). AI-readable: https://www.tigzig.com/ai/posts/us-banks-ndfi-q1-2026-update-may2026.md - [Over 20 Market Tools, Free. Built and Used for My Own Analysis. Now on tigzig.com/markets.](https://www.tigzig.com/post/market-tools-20-free-tigzig-markets-may2026) - Tags: portfolio-quants Tool release - Over 20 market tools live on tigzig.com/markets, free, no login, no ads. Five categories: Macro & credit data (~290 indicators across US, India, EU and Global), Track and compare securities (price, returns, drawdown, volatility), AI technical analysis (daily + weekly, 6 sections), AI macro briefing (agent + macros + news), Risk & return metrics (80+ metrics). Six ways to connect - Web, GPT, xlwings Lite, Agent, MCP and API. Works inside Claude in Excel and PowerPoint, Claude AI, Cowork. Most are open source. Built by an analyst and ex-derivatives trader. Author uses these same tools daily for own analysis and client work - connect to the tools, pull data, run checks, get analysis out, right inside whatever Claude surface is in use. Analysis section on the site shows the kind of work these feed into - market exuberance, S&P/Nifty positioning, early warning signals, stagflation risk, consumer lending stress. AI-readable: https://www.tigzig.com/ai/posts/market-tools-20-free-tigzig-markets-may2026.md - [Banks Holding the Line.. But the 'Lemons' Sit Off the Chart. In Private Credit, Credit Unions, and Non-Bank Consumer Lenders.](https://www.tigzig.com/post/banks-holding-line-lemons-off-chart-may2026) - Tags: portfolio-quants FDIC Q1 2026 NCO chart shows US banks holding the line at 0.58%, right at pre-GFC. Real Estate (45% of book) at 0.05% vs 2.50% GFC peak. Consumer at 2.87% (vs 6.64% GFC). C&I 0.52% (vs 2.69%). But the credit stress is in two places the bank NCO chart doesn't show. First: private credit, which is mark-to-market and hits P&L directly, never flowing through to NCO. Bank loans to non-bank lenders crossed ~$1.6T (FFIEC) with about a quarter being private credit. DOJ probing BlackRock fund valuations, FSB/BoE/ECB all warning on data gaps, opacity and spillover risk. Second: credit unions and non-bank consumer lenders. NCUA consumer NCO at 1.82% (nearly 2x pre-crisis), cards at 5.11% past the 4.68% GFC peak, used vehicle loans at the highest on record. Non-banks carrying the weakest paper. Single-image chart post with Q1 2026 numbers across the bank book - Total Loans 0.58%, Real Estate, Consumer, C&I segments and All Other. AI-readable: https://www.tigzig.com/ai/posts/banks-holding-line-lemons-off-chart-may2026.md - [Private Credit Default Rate Hits a Record 6.0% (2026): A Market for Lemons? Banks and Insurers Deep In It.](https://www.tigzig.com/post/private-credit-market-for-lemons-may2026) - Tags: portfolio-quants Private credit's default rate hit a record 6.0% in April 2026 (Fitch, trailing 12 months). Bank of England's Sarah Breeden invokes Akerlof's 'market for lemons'; a government report calls it a layered cake like 2008 subprime. Banks and insurers are deep in - JPMorgan $22B, Citi $22B, Deutsche $30B - with a 19% off-cycle NAV writedown, a $648M bank credit-line cut, KKR rescuing its own FSK fund, and a DOJ probe into BlackRock TCPC valuations. Numbers with sources. AI-readable: https://www.tigzig.com/ai/posts/private-credit-market-for-lemons-may2026.md - [Track Trump's Stock Trades. Public Filing Explorer. 3,568 Trades, 986 Tickers, $220M-$750M. Searchable on TREMOR.](https://www.tigzig.com/post/track-trump-stock-trades-tool-release-may2026) - Tags: portfolio-quants Tool release - Public Filing Explorer for Trump's stock trades, live on TIGZIG TREMOR. 3,568 equity trades from the latest OGE filing (Jan-March 2026), $220M-$750M disclosed value, all searchable across 986 tickers. Per-ticker price chart with buy/sell timeline overlay and news around each trade. Trades plotted on S&P 500 day by day. Raw OGE filings standardized with name-to-ticker mapping (filings come with messy long names, no tickers). CSV download for offline cuts. For 9 months before this filing it was mostly bonds; the May filing alone was almost all equities. Educational analysis, not financial advice. AI-readable: https://www.tigzig.com/ai/posts/track-trump-stock-trades-tool-release-may2026.md - [India's Next Tech Wave. AI Data Centers for the World. Adani, Reliance, Airtel, L&T. Same Pattern as Software in the 2000s.](https://www.tigzig.com/post/india-next-tech-wave-ai-data-centers-may2026) - Tags: portfolio-quants India's next tech wave - AI data centers for the world - is being built by infra players Adani, Reliance, Bharti Airtel and L&T. World is out of compute and out of power - global data centers ~97% full, leased before they're finished. Big-4 US tech firms guided ~$700bn capex in 2026 and still can't keep up. First movers in India: Google's $15bn / 1 GW Vizag hub (largest outside US), Adani $100bn by 2035, Reliance $110bn / 7yr Jamnagar, Microsoft $17.5bn Hyderabad live mid-2026, AWS $12.7bn by 2030, TCS HyperVault. Government policy backing: 2047 tax holiday for foreign cloud firms, IndiaAI Mission, 15% safe harbour. India's edge isn't lower-cost labour - it's industrial build muscle for gigawatt-scale capacity. Risks covered: US-India relations and chip access, water and heat in stressed regions, land approvals. Includes 15-slide deck and full source links (JLL, McKinsey, CEEW, Jefferies, BIS, CNBC, Google, Microsoft, Adani, Reliance, etc.). AI-readable: https://www.tigzig.com/ai/posts/india-next-tech-wave-ai-data-centers-may2026.md - [TREMOR. Six Free Tools for Banking and Insurance Analysts. Multi-Layer Validated. Built by a Practitioner.](https://www.tigzig.com/post/tremor-six-tools-banking-insurance-analysts-may2026) - Tags: portfolio-quants Six free tools for banking and insurance analysts on TREMOR (tigzig.com). Bank Aggregates from FDIC, Credit Union Aggregates from NCUA, Consumer Credit from NY Fed, Bank-Level NDFI from FFIEC, Insurance Assets from Fed Z.1, Global Macro Indicators from multiple sources. Primary sources only - no third-party aggregators. Every tool carries a three-layer Validations tab. Walks through what it took to validate the data: regulator nuances (NCUA YTD charge-offs need de-cumulation, NY Fed revises back-data, FDIC late-filers drift against QBP totals), abnormal patterns, and even an apparent error in the regulator's own filing. Built by an analyst, for analysts. Free. No ads. No login. AI-readable: https://www.tigzig.com/ai/posts/tremor-six-tools-banking-insurance-analysts-may2026.md - [Trump Trades. From Mostly Bonds to 3,642 Equity Trades in One Filing. Free Tool to Search Every Transaction.](https://www.tigzig.com/post/trump-trades-3642-equity-trades-tool-may2026) - Tags: portfolio-quants 9 months of mostly bonds in President Trump's OGE filings broken by one filing on 14 May 2026 carrying 3,642 equity trades, $220M to $750M. Heavy activity in Nvidia, Apple, Microsoft, Amazon, Meta, Oracle. 15 filings since Aug 2025 - earlier 14 combined had 1,726 trades almost all bonds. Built a free interactive tool on top of the OGE PDFs - every transaction searchable across 1,058 tickers, click any company to see trade timeline overlaid on price chart, CSV download. Short analysis deck included on most active tickers, top buys, top sells, and policy overlaps press has flagged. AI-readable: https://www.tigzig.com/ai/posts/trump-trades-3642-equity-trades-tool-may2026.md - [Three Red Flags Hit Together. 30Y at 5.14%, PPI at 5.99%, Brent Above $100. Setup Worse Than 2000 or 2007.](https://www.tigzig.com/post/three-red-flags-30yr-ppi-oil-may2026) - Tags: portfolio-quants Three macro red flags hit at the same time, each a major disruptor on its own: US 30-year Treasury yield 5.14% (first since 2007), US Producer prices 5.99% (15-year high ex-COVID), Brent above $100 (IEA calls it the largest oil supply disruption in history). Alongside: S&P 7,400 with CAPE 39.6 (2nd-highest in 145 years), auto loan losses past 2007 GFC peak, unemployment near Q3 2007 levels, Mag 7 ~35% of S&P (NVIDIA alone 8.9%). The last time these general patterns showed up: 2000 and 2007. 2026 is looking worse. AI-readable: https://www.tigzig.com/ai/posts/three-red-flags-30yr-ppi-oil-may2026.md - [Dimon Was Right. More Cockroaches Arrive. UK Lender MFS Collapses - $2.5B Across 12+ Global Banks.](https://www.tigzig.com/post/mfs-collapse-cockroaches-private-credit-may2026) - Tags: portfolio-quants UK lender MFS collapsed in February with $2.5B exposure across 12+ global banks - Barclays $308M, HSBC $400M, Atlas/Apollo $508M, Santander $267M, Elliott $254M, Wells Fargo $182M. £2.4B loan book, fraud and double-pledging allegations. £230M verified collateral against £1.16B owed (80% shortfall). Affiliated lending chain: HSBC > Apollo Atlas > Zircon Bridging > MFS. AI-readable: https://www.tigzig.com/ai/posts/mfs-collapse-cockroaches-private-credit-may2026.md - [S&P at 7,400. Irrational Exuberance. The Last Two Times This Setup Held, the Index Halved.](https://www.tigzig.com/post/sp500-irrational-exuberance-7400-may2026) - Tags: portfolio-quants S&P 500 at 7,400 with Irrational Exuberance. Last two times setup held: 2000 dot com -49% in 30 months, 2007 subprime -57% in 17 months. Apply pattern math, S&P lands 3,200-3,800. CAPE 39.6 (2nd time in 145 years), auto delinquencies past GFC peak, U-6 back to pre-GFC, PPI 25-year high ex-COVID, Brent $106. Dimon: too much exuberance. Buffett on $397B cash. AI-readable: https://www.tigzig.com/ai/posts/sp500-irrational-exuberance-7400-may2026.md - [US Consumer Lending Is Already at Crisis-Level Numbers - Without a Recession. NY Fed Q1 2026 Data.](https://www.tigzig.com/post/us-consumer-lending-crisis-without-recession-may2026) - Tags: portfolio-quants NY Fed Q1 2026 release. Auto delinquencies past GFC peak. Cards near it. Mortgage stock calm but flow rate cracking. HELOC usage and delinquencies rising. Home prices down 9% from 2022 peak. U-6 unemployment back to pre-GFC 2007 levels. Underwater mortgages up in 45 states YoY. Crisis numbers without a recession. AI-readable: https://www.tigzig.com/ai/posts/us-consumer-lending-crisis-without-recession-may2026.md - [US Fed Financial Stability Report May 2026. Same Stress Points - Now in Fed Own Survey.](https://www.tigzig.com/post/fed-fsr-may2026-stress-points-match-analysis) - Tags: portfolio-quants US Fed FSR May 2026 covers 4 of the top 6 shocks already in tigzig.com/analysis - private credit (life insurance exposure, bank lending to non-banks), AI impact (labor displacement), oil shock (spot-futures divergence), risk asset correction (S&P disbelief rally). Plus consumer/auto lending stress and stagflation-lite. AI-readable: https://www.tigzig.com/ai/posts/fed-fsr-may2026-stress-points-match-analysis.md - [Red Flag in US Life Insurance. $2.4T (7.5% of GDP) in Private Credit and Offshore Reinsurance.](https://www.tigzig.com/post/us-life-insurance-red-flag-private-credit-offshore) - Tags: portfolio-quants US Life Insurers have $2.4T (7.5% of US GDP) in private credit and offshore reinsurance. $1.2T in Fed Unidentified Misc Assets, $1.2T offshore reinsurance memo. Both nearly doubled in 5 years. PE-affiliated loop - same firms own insurers, credit funds and offshore reinsurers. Doom loop risk if retirees surrender annuities en masse. AI-readable: https://www.tigzig.com/ai/posts/us-life-insurance-red-flag-private-credit-offshore.md - [US Insurance Assets Tracker - 25 Years of Data, 73 Series, Life & P&C](https://www.tigzig.com/post/us-insurance-assets-tracker) - Tags: portfolio-quants US Insurance Assets Tracker on TREMOR. 73 line items across 104 quarters / 25 years. Life and P&C, General and Separate Account. Source FRED + Fed Z.1, validated against L.116 and NAIC/ACLI. Life Unidentified Misc Assets grew 76% in 5 years to $1.2T - now 10% of Life assets, the Fed catch-all for private credit, PE, BDCs, hedge funds. AI-readable: https://www.tigzig.com/ai/posts/us-insurance-assets-tracker.md - [The Convergence Risk. Credit Stress Already Past 2007 Pre-Crisis. Five Aggravators Stacking On Top.](https://www.tigzig.com/post/convergence-risk-credit-stress-past-2007) - Tags: portfolio-quants Multiple credit stress signals at the same time across US banks, credit unions, consumer debt. Past 2007 pre-crisis on most metrics. Auto loans already at GFC peak. 5 aggravators on top - AI labor shock, U-1 above 2007, GDP at 0.5%, Brent $100+, private credit stress with $2.5T+ exposure. Warnings from Jamie Dimon and Sarah Breeden. AI-readable: https://www.tigzig.com/ai/posts/convergence-risk-credit-stress-past-2007.md - [US Credit Unions on TREMOR. Card Charge-Offs at 5.11% - Already Past the 2009 GFC Peak.](https://www.tigzig.com/post/us-credit-unions-ncua-tremor-card-nco-past-gfc) - Tags: portfolio-quants US Credit Unions analytics on TREMOR. 23 years, 86 quarters, $1.72T loans across 4,287 federally-insured credit unions from NCUA quarterly FPR. Card NCO at 5.11% past 4.68% GFC peak. Consumer NCO at 1.82% vs 0.99% pre-crisis. 18 segments, 30-59 DPD, 60+ DPD, NCO. CSV download with 74-field reference. AI-readable: https://www.tigzig.com/ai/posts/us-credit-unions-ncua-tremor-card-nco-past-gfc.md - [The Crisis in Auto Loans. 2007 was Sub-Prime Mortgage. Is 2026 Auto?](https://www.tigzig.com/post/auto-loans-crisis-2026-subprime-parallel) - Tags: portfolio-quants NY Fed Auto 90+DPD at 5.21% vs 5.27% at GFC peak. Bank auto NCO at 2x 2011 baseline. Credit union NCO at 0.95% record high. S&P ABS subprime NCO ~10%. Tricolor fraud $800M. First Brands fraud $2.3B. $1.67T direct exposure plus $350B in ABS. FDIC SDI, NY Fed CCP, NCUA, S&P Global, FFIEC analysis. AI-readable: https://www.tigzig.com/ai/posts/auto-loans-crisis-2026-subprime-parallel.md - [Releasing US-CREDIT. For Analysts Tracking US Banking. Interactive Tool Covering FDIC SDI and NY Fed CCP.](https://www.tigzig.com/post/releasing-us-credit-fdic-nyfed-interactive-tool) - Tags: portfolio-quants US-CREDIT interactive analytics tool. 25 years, 100 quarters. $13.6T bank loans across 4400+ FDIC institutions. $18.8T consumer debt via NY Fed CCP. 18 FDIC segments, delinquency buckets, charge-offs, FICO bands, age groups. Validated against FDIC QBP - 100 quarters reconciled. Includes disbelief rally research deck. AI-readable: https://www.tigzig.com/ai/posts/releasing-us-credit-fdic-nyfed-interactive-tool.md - [S&P at All-Time High. Under the Hood, Things Are Cracking. Just Like October 2007.](https://www.tigzig.com/post/sp500-ath-cracking-underneath-oct2007-parallel) - Tags: portfolio-quants S&P at ATH while private credit at 2x 2007 subprime showing stress. Credit card and auto delinquencies above 2007 pre-crisis. Bank charge-offs higher than 2007. AI displacing workers at unprecedented pace inside a stress cycle. Tracking across FFIEC, FDIC, NY Fed, IEA, Challenger, Anthropic Economic Index. AI-readable: https://www.tigzig.com/ai/posts/sp500-ath-cracking-underneath-oct2007-parallel.md - [The Masking Effect in Oil Markets - The Price You See on Screens Is Hiding a $50 Supply Shock](https://www.tigzig.com/post/oil-masking-effect-spot-futures-divergence-apr2026) - Tags: portfolio-quants Largest spot-futures divergence in oil market history. Brent futures at $94, physical crude at $144. Analysis of 9,864 trading days since 1987. 40 bids vs 4 offers in North Sea. Diesel near $200/bbl. US gasoline inventories at 16-year lows. Hormuz shut 40 days, Kuwait says 3-4 months to restore. AI-readable: https://www.tigzig.com/ai/posts/oil-masking-effect-spot-futures-divergence-apr2026.md - [Analytics Tool for India's Bank Credit](https://www.tigzig.com/post/india-bank-credit-analytics-tool) - Tags: portfolio-quants Interactive analytics tool for India bank credit deployment. 39 months of RBI sectoral data across 34 sectors. Growth rates, share of delta, composition shifts, sector-to-subsector drill downs, hierarchical tree or RBI format views, custom sector groups, time frame controls, CSV downloads. Includes NBFC sub-categories RBI doesn't break out separately. AI-readable: https://www.tigzig.com/ai/posts/india-bank-credit-analytics-tool.md - [Anthropic Released Claude Managed Agents Yesterday, Live on TREMOR Today](https://www.tigzig.com/post/tremor-claude-managed-agents-macro-analysis) - Tags: portfolio-quants, ai-coders Claude Managed Agents integrated into TREMOR macro dashboard. AI analysis on 70+ indicators across US and India. Three modes: full dashboard briefing, selected chart analysis, deep research with citations. Covers equities, bonds, gold, oil, forex, unemployment, delinquencies, valuations, inflation. AI-readable: https://www.tigzig.com/ai/posts/tremor-claude-managed-agents-macro-analysis.md - [India's Credit-Deposit Ratio Just Hit 83%. A 15-Year High. Gold Loans Up 4x in Two Years.](https://www.tigzig.com/post/india-credit-deposit-ratio-gold-loans-apr2026) - Tags: portfolio-quants India credit-deposit ratio at 83%, 15-year high. Gold loans up 4x in two years. NBFC loans up 21% in 9 months. Six sectors growing at 2x overall rate pulling one-third of new credit. Credit grew 12.3% vs deposits 9%. Housing growth slowed. RBI sectoral data analysis. AI-readable: https://www.tigzig.com/ai/posts/india-credit-deposit-ratio-gold-loans-apr2026.md - [US Bank Exposure to Non-Bank Lenders - Now in an Interactive Analytics Tool](https://www.tigzig.com/post/us-bank-ndfi-interactive-analytics-tool) - Tags: portfolio-quants Interactive analytics tool for US bank exposure to non-bank lenders. 629 banks, $1.57 trillion in NDFI loans, 5 quarters of FFIEC Call Report data. CET1 concentration, ACL reserve coverage, bank-level drill downs, data explorer with 55+ columns, methodology with MDRM codes, 7 levels of validation. Full dataset download. AI-readable: https://www.tigzig.com/ai/posts/us-bank-ndfi-interactive-analytics-tool.md - [NDFI Analytics - US Bank Exposure to Non-Bank Lenders](https://www.tigzig.com/post/ndfi-analytics-us-bank-exposure-tool) - Tags: portfolio-quants Interactive NDFI analytics tool covering US bank exposure to non-bank lenders. FFIEC Call Reports for 629 banks across 5 quarters. Stress scenarios, CET1 concentration, ACL coverage, nonaccrual rates, commitments. Validated against FDIC BankFind API, FRED Series, FDIC Quarterly Banking Profile. Full data download. AI-readable: https://www.tigzig.com/ai/posts/ndfi-analytics-us-bank-exposure-tool.md - [Three Tools I Built for Market Analysis - QSUITE, TREMOR, QREP](https://www.tigzig.com/post/three-tools-market-analysis-qsuite-tremor-qrep) - Tags: portfolio-quants Three market analysis tools - QSUITE for AI technical analysis, TREMOR for macro early warning with 50+ indicators across US and India, QREP for portfolio stats powered by QuantStats. Built on Claude Code, DuckDB, Hetzner, Vercel, Coolify. Free, no login, no ads. AI-readable: https://www.tigzig.com/ai/posts/three-tools-market-analysis-qsuite-tremor-qrep.md - [TREMOR - Macro Early Warning Dashboard - 50+ Indicators, Updated Daily](https://www.tigzig.com/post/tremor-macro-dashboard-50-indicators) - Tags: portfolio-quants TREMOR macro early warning dashboard with 50+ indicators for US and India. Updated daily from FRED, RBI, NSE, MOSPI, NY Fed. Swap charts as news breaks, YoY/MoM/MA toggles, PNG export to PowerPoint, CSV export, news feed from 30+ sources. Free, no login. AI-readable: https://www.tigzig.com/ai/posts/tremor-macro-dashboard-50-indicators.md - [Are We Headed for Stagflation-Lite](https://www.tigzig.com/post/stagflation-lite-macro-signals-march-2026) - Tags: portfolio-quants Stagflation-Lite signals intensifying. Fed trapped between inflation and weak jobs. US 10Y at 4.4%, PPI at 3.4% with oil shock not yet in data, GDP at 0.7%, consumer sentiment 7th lowest in 40 years, Moody recession odds at 48.6%. Bond markets pricing in high inflation globally. AI-readable: https://www.tigzig.com/ai/posts/stagflation-lite-macro-signals-march-2026.md - [US Banks & Non-Bank Lending - How Deep is the Exposure? Is there a Systemic Risk?](https://www.tigzig.com/post/us-banks-ndfc-lending-systemic-risk-2026) - Tags: portfolio-quants US banks hold $1.57 trillion in loans to non-bank lenders facing redemptions and defaults. 41 banks have this single portfolio exceeding 100% of core capital. 62 banks have loan loss reserves covering less than 10% of exposure. Analysis from FFIEC Call Reports for 629 banks across 5 quarters, cross-validated against FDIC, FRED and S&P Global. AI-readable: https://www.tigzig.com/ai/posts/us-banks-ndfc-lending-systemic-risk-2026.md - [Private Credit - The $2.7 Trillion Shadow Lending Market Is Showing Cracks](https://www.tigzig.com/post/private-credit-shadow-lending-cracks-2026) - Tags: portfolio-quants Private credit showing cracks that remind Wall Street of 2008. Jamie Dimon and Lloyd Blankfein flagging risks. 40% of borrowers have negative cash flow. Blackstone scrambled to meet $3.8B in redemptions. Management companies down 30-50% in 6 months. AI-readable: https://www.tigzig.com/ai/posts/private-credit-shadow-lending-cracks-2026.md - [Structural Weakness Intensifying](https://www.tigzig.com/post/structural-weakness-intensifying-march-2026) - Tags: portfolio-quants 3 major US macro data points in 3 days all pointing the same direction. Feb payrolls minus 92K against expectations of 59K rise. PPI Core at 3.87%. Fed held at 3.5-3.75%. Brent crude nearly doubled in 3 months. Delinquencies past COVID highs. Multiple macro signals flashing stress simultaneously. AI-readable: https://www.tigzig.com/ai/posts/structural-weakness-intensifying-march-2026.md - [Tremor - Macro Early Warning Signals - March 2026](https://www.tigzig.com/post/tremor-macro-signals-march-2026) - Tags: portfolio-quants S&P down 5%, Nifty in bear territory down 12% from highs. CAPE at 40-year highs, gold going vertical, crude shooting towards 2008 levels, US delinquencies crossing COVID highs. When macro signals move together - tremors before a quake. 12 chart slides from tremor.tigzig.com. AI-readable: https://www.tigzig.com/ai/posts/tremor-macro-signals-march-2026.md - [Pull your quants numbers directly with Claude / ChatGPT in Excel (with MCP).](https://www.tigzig.com/post/qrep-mcp-quants-numbers-claude-chatgpt-excel) - Tags: mcp, quantstats, excel, open-source QREP MCP server for pulling 81 quant metrics (returns, sharpe, sortino, drawdowns) directly into Claude in Excel, ChatGPT in Excel, Claude Desktop, Cursor, n8n or any MCP client. Powered by QuantStats library. Free public server, full source code open. AI-readable: https://www.tigzig.com/ai/posts/qrep-mcp-quants-numbers-claude-chatgpt-excel.md - [Evaluating a stock? Pull its VIGIL Report. Free.](https://www.tigzig.com/post/evaluating-a-stock-pull-its-vigil-report) - Tags: vigil, open-source VIGIL Corporate Signals report for any Indian listed stock. Surveillance, insider trading, takeover, credit ratings, pledges, related party transactions. Five download formats including AI-friendly TSV and SQLite. Free, no login. AI-readable: https://www.tigzig.com/ai/posts/evaluating-a-stock-pull-its-vigil-report.md - [Nifty and S&P 500 Down - Run a Technical Analysis Check. 9 LLMs Compared.](https://www.tigzig.com/post/qsuite-nifty-sp500-technical-analysis-llm-comparison) - Tags: technical-analysis QSUITE AI technical analysis tool with 9 LLM choices including GPT 5.4 and Claude Sonnet 4.6. Generates daily and weekly charts, support/resistance, MACD, RSI, Bollinger Bands, volume analysis, price outlook in PDF and HTML. Comparison of all 9 models on S&P 500 and Nifty 50 for the same period. AI-readable: https://www.tigzig.com/ai/posts/qsuite-nifty-sp500-technical-analysis-llm-comparison.md - [Rolling Returns: Why CAGR Alone Can Mislead You (And What To Use Instead)](https://www.tigzig.com/post/rolling-returns-why-cagr-alone-can-mislead-you) - Tags: mutual-funds, portfolio-analytics, duckdb Explains why point-to-point CAGR is fragile and how rolling returns provide a more reliable picture of fund performance. Covers the difference between rolling window and evaluation period, the ASOF JOIN computation in DuckDB SQL, minimum gap thresholds, CAGR vs absolute return for sub-1-year windows, and how to read each column (average, median, min, max, % negative, observations). Includes validation results across 7,485 data points within 0.50 bps of Excel. Live on MFPRO with 95 funds and 9 indices. AI-readable: https://www.tigzig.com/ai/posts/rolling-returns-why-cagr-alone-can-mislead-you.md - [S&P 500 Drawdown Analysis with QREP](https://www.tigzig.com/post/sp500-drawdown-qrep-analysis) - Tags: portfolio-analytics, technical-analysis S&P 500 drawdown analysis using QREP - Security Analytics Reports tool. How many drawdowns in 20 years, how long, how deep. One-click drawdown charts and metrics powered by QuantStats. Also covers interactive technical analysis charts, performance and risk KPIs, advanced ratios, and multi-security comparison up to 6 securities. AI-readable: https://www.tigzig.com/ai/posts/sp500-drawdown-qrep-analysis.md - [Claude in Excel + MCP + xlwings Lite + Claude Code: Pull Data, Build a Model, Validate It.](https://www.tigzig.com/post/claude-in-excel-mcp-xlwings-lite-claude-code-combining-4-tools) - Tags: claude-in-excel, mcp, xlwings-lite, ai-coders, portfolio-analytics Live walkthrough of S&P 500 forward returns scenario model built with four tools. Claude in Excel pulls data via YFIN MCP server and builds MAP/LAMBDA formula model. Claude Code validates offline with independent Python recomputation - catches a formula error that in-Excel checks missed. xlwings Lite generates distribution charts (fan, ridgeline, raincloud) from Python into Excel. Covers when to use each tool and MCP architecture for client work. AI-readable: https://www.tigzig.com/ai/posts/claude-in-excel-mcp-xlwings-lite-claude-code-combining-4-tools.md - [Now live - MFPRO v2 - Mutual Fund Analytics (India) - now with rolling returns, custom eval periods, multi-period & multi-instrument comparisons](https://www.tigzig.com/post/mfpro-v2-mutual-fund-analytics-rolling-returns) - Tags: mutual-funds, portfolio-analytics MFPRO v2 release for Indian mutual fund analytics. Adds rolling return statistics (1Y/3Y/5Y windows with average, median, min, max), custom evaluation periods, multi-fund and multi-index return comparisons across 95 funds and 9 indices. Includes downloadable NAV data, Excel templates for independent verification, multi-period holdings comparison, and index constituent analysis. Data from Jan 2013, auto-synced twice daily. AI-readable: https://www.tigzig.com/ai/posts/mfpro-v2-mutual-fund-analytics-rolling-returns.md - [QRep - Powered by QuantStats. Live Now.](https://www.tigzig.com/post/qrep-quantstats-security-analytics-live) - Tags: portfolio-analytics, technical-analysis Launch announcement for QRep, a security analytics tool built on Ran Aroussi's QuantStats and yfinance libraries. Provides 90+ KPIs across risk, returns, ratios and drawdown metrics. Features HTML and PDF reports, CSV downloads, interactive technical analysis charts with adjustable parameters, and instant symbol search without needing Yahoo Finance ticker lookup. Part of Tigzig Analyst suite. AI-readable: https://www.tigzig.com/ai/posts/qrep-quantstats-security-analytics-live.md - [Free CORS Proxy for Yahoo Finance & Any API: Cloudflare Worker Code (CORS Explained Simply)](https://www.tigzig.com/post/fast-tips-what-is-cors-and-how-to-fix-it) - Tags: infrastructure, security Free CORS proxy for Yahoo Finance, GitHub, Drive, or any API using a Cloudflare Worker - a self-hosted alternative to cors-anywhere / cloudflare-cors-anywhere, no server, no domain, free tier. Full copy-paste Worker code plus the ?url= pattern, and CORS explained simply: preflight, the no-cors trap, and when to use a Worker vs Vercel serverless vs FastAPI. AI-readable: https://www.tigzig.com/ai/posts/fast-tips-what-is-cors-and-how-to-fix-it.md - [U.S. Markets (S&P 500) vs India (Nifty 50) - is the returns profile reversing?](https://www.tigzig.com/post/sp500-vs-nifty50-returns-profile-reversing) - Tags: portfolio-analytics Comparative returns analysis of S&P 500 vs Nifty 50 across six time horizons (1 to 18 years). Shows Nifty 50 leading long-term but S&P 500 pulling ahead over the last 2-3 years. Generated using the Portfolio Analysis Suite at quants.tigzig.com. Charts available as downloadable PDF. Educational analysis, not investment advice. AI-readable: https://www.tigzig.com/ai/posts/sp500-vs-nifty50-returns-profile-reversing.md - [NIFTY50 - 30 Day Forward Return Analysis Feb 2008 to 2026 - Claude in Excel with Python, Lambdas and Advanced Formulas](https://www.tigzig.com/post/nifty50-30-day-forward-return-analysis-claude-in-excel) - Tags: claude-in-excel, portfolio-analytics Nifty50 forward return analysis built entirely in Claude in Excel. For each trading day from 2008-2026, computes 30 forward returns with quintile cuts (P20-P80), positive/negative day counts, and confidence intervals. Uses Python for initial computation, then validates with manual formulas, LET+SEQUENCE, and named LAMBDA functions. MAP, REDUCE, and SCAN with LAMBDA for trade diagnostics. Completed in 2.5 hours across two sessions. AI-readable: https://www.tigzig.com/ai/posts/nifty50-30-day-forward-return-analysis-claude-in-excel.md - [Claude in Excel - Nifty50 Return Distribution Analysis (30 days forward) 2008 to 2026](https://www.tigzig.com/post/claude-in-excel-nifty50-return-distribution-analysis) - Tags: claude-in-excel, portfolio-analytics Claude in Excel used to compute Nifty50 30-day forward return distributions from 2008-2026. For each trading day, calculates 30 forward returns and extracts quintile cuts (P20-P80) plus positive/negative day counts. Built after 15-20 minutes of brainstorming with Claude on methodology. Includes manual validation for a single day and reconstructed Python code output. Shared as downloadable Excel file. AI-readable: https://www.tigzig.com/ai/posts/claude-in-excel-nifty50-return-distribution-analysis.md - [Found a Python library that does all the heavy lifting for working with SEC EDGAR API - EdgarTools from Dwight Gunning](https://www.tigzig.com/post/edgartools-sec-edgar-python-library) - Tags: portfolio-analytics, fastapi Review of EdgarTools Python library by Dwight Gunning for SEC EDGAR data. Features built-in XBRL standardization for cross-company financial comparison, 10-30x speed improvement via PyArrow and lxml, automatic SEC rate limit compliance, and coverage of 10-K, 10-Q, 8-K, 13F, and Form 4 filings. Includes built-in MCP server for AI tool integration. Author is using it as backbone for a FastAPI quarterly comparison tool. AI-readable: https://www.tigzig.com/ai/posts/edgartools-sec-edgar-python-library.md - [Quants Agent: Now with LLM Choices for Technical Analysis Reports](https://www.tigzig.com/post/quants-agent-llm-choices-technical-analysis-reports) - Tags: technical-analysis, portfolio-analytics Quants agent update adding LLM model selection for AI technical analysis reports. Pipeline: fetches OHLCV from Yahoo Finance via yfinance, calculates EMAs, MACD, RSI, ROC, Bollinger Bands via finta, generates matplotlib charts, sends to chosen LLM (including GPT-5.2, Claude Sonnet 4.5) via OpenRouter for interpretation, converts to styled PDF and interactive HTML via markdown-to-PDF service. Open source. AI-readable: https://www.tigzig.com/ai/posts/quants-agent-llm-choices-technical-analysis-reports.md - [Bitcoin Down nearly 30% in 25 days. What Does AI Technical Analysis Say?](https://www.tigzig.com/post/bitcoin-down-nearly-30-in-25-days-what-does-ai-technical-analysis-say) - Tags: technical-analysis Demonstrates the quants agent at quants.tigzig.com generating AI technical analysis for Bitcoin during a 30% decline. Default model Gemini 2.5 Flash produces reports in 30-45 seconds; premium models (GPT 5.1, Claude Sonnet 4.5) take 2-4 minutes but catch more patterns. Reports include daily and weekly charts with AI interpretation. Author notes disagreement with the AI's outlook as example of using it as one input among many. Open source. AI-readable: https://www.tigzig.com/ai/posts/bitcoin-down-nearly-30-in-25-days-what-does-ai-technical-analysis-say.md - [Gold up 2.3X past 2 years. But what about the 10 years drawdown in between.](https://www.tigzig.com/post/gold-up-2-3x-past-2-years-but-what-about-the-10-years-drawdown-in-between-as-buffett-says) - Tags: portfolio-analytics Analysis of gold's historical drawdown risk using the open-source Quants Agent at quants.tigzig.com. Despite gold's 2.3X rise over 2 years, the post highlights the brutal 10-year drawdown from 2011 to 2020. References Buffett's 2011 letter on gold as a non-productive asset and Goldman Sachs forecasts. Includes SPR report generation instructions. AI-readable: https://www.tigzig.com/ai/posts/gold-up-2-3x-past-2-years-but-what-about-the-10-years-drawdown-in-between-as-buffett-says.md - [[ENHANCEMENT] AI Technical Analysis Now Supports Multiple LLM Choices](https://www.tigzig.com/post/enhancement-ai-technical-analysis-now-supports-multiple-llm-choices) - Tags: technical-analysis Feature update to the AI Technical Analysis tool at quants-suite.tigzig.com adding multiple LLM options across three tiers: fast (Gemini 2.5 Flash/Lite, ~30 seconds), mid (GPT 4.1/Mini/Nano, Haiku 4.5, ~1 min), and premium (GPT 5.1, Claude Sonnet 4.5, 2-5 mins). Generates daily and weekly technical analysis reports in PDF and HTML. AI-readable: https://www.tigzig.com/ai/posts/enhancement-ai-technical-analysis-now-supports-multiple-llm-choices.md - [Execute ASAP. Approval granted. Google - against Microsoft & Meta past 15 years, benchmark vs. S&P 500, technicals & quarterlies for all three.](https://www.tigzig.com/post/execute-asap-approval-granted-google-vs-microsoft-meta) - Tags: portfolio-analytics, technical-analysis Demonstration of the Quants Agent at quants.tigzig.com generating a full financial report pack (Security Performance Report, AI Technical Analysis, QuantStats, Financials) for Google vs Microsoft vs Meta benchmarked against S&P 500 over 15 years. Single natural language prompt produces PDF, HTML, and CSV outputs in approximately 2 minutes. AI-readable: https://www.tigzig.com/ai/posts/execute-asap-approval-granted-google-vs-microsoft-meta.md - [Automated Analytics & Reporting with Python in Excel (xlwings Lite). Build Once - Reuse Anywhere.](https://www.tigzig.com/post/automated-analytics-reporting-with-python-in-excel-xlwings-lite-build-once-reuse-anywhere) - Tags: xlwings-lite, python-in-excel, technical-analysis Reusable architecture for automated PDF and HTML report generation using xlwings Lite. Demonstrates an AI-driven technical analysis report for Yahoo Finance symbols in 45 seconds. Covers 9 reusable building blocks: API data fetching, Python transformations, Matplotlib charting, multi-modal AI calls, markdown-to-report assembly, and backend URL generation. AI-readable: https://www.tigzig.com/ai/posts/automated-analytics-reporting-with-python-in-excel-xlwings-lite-build-once-reuse-anywhere.md - [Quants Suite. 5 Reports. Performance, Risk & Technical Analytics.](https://www.tigzig.com/post/quants-suite-5-reports-performance-risk-technical-analytics) - Tags: portfolio-analytics, technical-analysis Five-report quantitative analytics suite at quants-suite.tigzig.com covering stocks, indices, commodities, and crypto. Reports include: Security Performance (CAGR, Sharpe, Sortino, drawdowns), AI Technical Analysis (EMAs, Bollinger, MACD, RSI with Gemini analysis), QuantStats (70+ metrics), Yahoo Finance financials (P&L, B/S, cash flow), and price data downloads. AI-readable: https://www.tigzig.com/ai/posts/quants-suite-5-reports-performance-risk-technical-analytics.md - [Automated Quant Reports with GPT: Run a stock, index, ETF, commodity, or crypto → get 3 formatted reports in minutes.](https://www.tigzig.com/post/automated-quant-reports-with-gpt-run-a-stock-index-etf-commodity-or-crypto-get-3-formatted-re) - Tags: portfolio-analytics, technical-analysis, custom-gpt Custom GPT generating three automated quantitative reports for any Yahoo Finance symbol: AI Technicals (daily/weekly charts with Gemini Flash analysis), Security Performance Report (CAGR, Sharpe, Sortino, drawdowns, monthly returns), and QuantStats (60+ KPIs, 10+ charts). All powered by open-source FastAPI-MCP backend servers. Outputs in PDF, HTML, and CSV. AI-readable: https://www.tigzig.com/ai/posts/automated-quant-reports-with-gpt-run-a-stock-index-etf-commodity-or-crypto-get-3-formatted-re.md - [Monthly MF portfolio files = hours wasted re-formatting. Here’s a tool that fixes it](https://www.tigzig.com/post/monthly-mf-portfolio-files-hours-wasted-re-formatting-here-s-a-tool-that-fixes-it) - Tags: mutual-funds, converters-tools Converter utility for Indian mutual fund monthly portfolio disclosure Excel files. Uses AI-powered schema detection to automatically identify data layouts, cross-validates with multiple models, and outputs clean CSVs with ISIN mapping and standardized names. Includes append, transpose, and audit trail utilities. Available at www.tigzig.com/mf-files-ai. AI-readable: https://www.tigzig.com/ai/posts/monthly-mf-portfolio-files-hours-wasted-re-formatting-here-s-a-tool-that-fixes-it.md - [Security Performance Report for Investors. AI Quant Agent. Live. Open Source. Free.](https://www.tigzig.com/post/security-performance-report-for-investors-ai-quant-agent-live-open-source-free) - Tags: portfolio-analytics Open-source AI Quants Agent generating Security Performance Reports with CAGR, Sharpe, Sortino ratios, max drawdown analysis (7 worst periods per security), cumulative returns charts, monthly returns breakdown, and an Anxiety Index. Outputs interactive HTML and CSV downloads. Uses Yahoo Finance tickers. Full methodology documentation with validations included. AI-readable: https://www.tigzig.com/ai/posts/security-performance-report-for-investors-ai-quant-agent-live-open-source-free.md - [AI Technical Report for Traders- An Open Source Tool](https://www.tigzig.com/post/ai-technical-report-for-traders-an-open-source-tool) - Tags: technical-analysis Open-source AI technical analysis report generator for stocks, crypto, and commodities. Produces 6-section PDF/HTML reports covering daily and weekly timeframes with AI-driven outlook. Uses indicators including EMA, MACD, RSI, ROC, and Bollinger Bands. Built on FastAPI-MCP server with Gemini Flash. Designed as a second-opinion tool against manual chart analysis. AI-readable: https://www.tigzig.com/ai/posts/ai-technical-report-for-traders-an-open-source-tool.md - [AI Technical Analysis Tool](https://www.tigzig.com/post/ai-technical-analysis-tool) - Tags: technical-analysis AI-powered technical analysis tool for generating unbiased second-opinion reports on any Yahoo Finance security. Covers multi-timeframe trends, support/resistance levels, EMA, MACD, RSI, and ROC indicators. Outputs clean PDF or HTML reports powered by Gemini 2.5 Flash. Designed for traders who want to challenge their own chart analysis. Open source and customizable. AI-readable: https://www.tigzig.com/ai/posts/ai-technical-analysis-tool.md - [That 9X return from Nifty Midcap is irrelevant if you couldn't survive the 73% of time it was in drawdown](https://www.tigzig.com/post/that-9x-return-from-nifty-midcap-is-irrelevant-if-you-couldn-t-survive-the-73-of-time-it-was-in-dra) - Tags: portfolio-analytics Analysis of drawdown psychology across Nifty 50, L&T, and Nifty Midcap 100 over 18 years using the custom Anxiety Index metric. Nifty Midcap's 9X return came with 73% of time in drawdown. L&T had a single 2,377-day drawdown period. Calculations performed with the free TIGZIG Quants tool. Explains Anxiety Index methodology. AI-readable: https://www.tigzig.com/ai/posts/that-9x-return-from-nifty-midcap-is-irrelevant-if-you-couldn-t-survive-the-73-of-time-it-was-in-dra.md - [TIGZIG Quants GPT: 30-Second Financial Analysis Custom GPT](https://www.tigzig.com/post/tigzig-quants-gpt-30-second-financial-analysis-custom-gpt) - Tags: custom-gpt, portfolio-analytics Custom GPT for 30-second cross-asset financial analysis comparing stocks, indices, commodities, and crypto. Generates daily returns charts, drawdown analysis, CAGR, Sharpe ratios, and CSV downloads. Available in three interfaces: Suite (fast, needs Yahoo symbols), Agent (smart assist), and ChatGPT (familiar interface, free users included). FastAPI-MCP backend. AI-readable: https://www.tigzig.com/ai/posts/tigzig-quants-gpt-30-second-financial-analysis-custom-gpt.md - [Open Source Asset Comparison Tool: Compare Stocks, Indices, Crypto & Commodities in One Dashboard](https://www.tigzig.com/post/open-source-asset-comparison-tool-compare-stocks-indices-crypto-commodities-in-one-dashboard) - Tags: portfolio-analytics Open-source cross-asset comparison tool (TIGZIG Quants) for comparing stocks, indices, crypto, and commodities in a single dashboard. Generates daily returns charts, drawdowns, CAGR, Sharpe, Sortino ratios, and date-aligned CSV downloads within 30 seconds. Two interfaces: Agent (smart assist) and Suite (fast, no-frills). Built with MCP servers, n8n, and React. AI-readable: https://www.tigzig.com/ai/posts/open-source-asset-comparison-tool-compare-stocks-indices-crypto-commodities-in-one-dashboard.md - [Live Portfolio Analytics - Powered by MCP Servers - Open Source](https://www.tigzig.com/post/open-so) - Tags: portfolio-analytics, mcp Modular live portfolio analytics stack powered by MCP-FastAPI servers. Delivers 70+ KPIs, 15+ charts, AI technical analysis, and PDF/HTML reports across 6 interfaces: React, NextJS, ChatGPT, Flowise, xlwings Lite, and forms. Backend uses QuantStats, yfinance, Finta, Gemini Vision, and ReportLab. Three public MCP servers available for plug-and-play integration. AI-readable: https://www.tigzig.com/ai/posts/open-so.md - [ChatGPT Connected to integrated FastAPI-MCP Servers.. Technical Analysis (TA) report. From stocks to crypto.](https://www.tigzig.com/post/chatgpt-connected-fastapi-mcp-servers-technical-analysis-ta-report-stocks-crypto) - Tags: custom-gpt, mcp, technical-analysis Connecting ChatGPT to integrated FastAPI-MCP servers for generating technical analysis reports on stocks, crypto, and commodities via Yahoo Finance symbols. Backend uses FastAPI with MCP server (Tadata's FastAPI-MCP), serving multiple interfaces: n8n, Flask UI, Next.js, ChatGPT, and xlwings Lite. Outputs formatted PDF and web reports with Gemini Vision chart analysis. Includes OpenAPI schema setup for Custom GPT actions and public source code. AI-readable: https://www.tigzig.com/ai/posts/chatgpt-connected-fastapi-mcp-servers-technical-analysis-ta-report-stocks-crypto.md - [Build AI Workflows with MCP Servers + n8n](https://www.tigzig.com/post/build-ai-workflows-mcp-servers-n8n-technical-analysis) - Tags: mcp, technical-analysis Building AI workflows by connecting MCP servers to n8n for automated technical analysis. Uses Tadata's FastAPI-MCP to mount MCP on existing FastAPI servers and n8n's MCP Client node for SSE connections. Pipeline pulls Yahoo Finance data, computes indicators, sends charts to Gemini Vision for AI analysis, and outputs PDF/web reports. Includes Docker deployment setup, public MCP server URLs, n8n schemas, and full source code. AI-readable: https://www.tigzig.com/ai/posts/build-ai-workflows-mcp-servers-n8n-technical-analysis.md - [AI-Powered Technical Analysis in Excel - with Python & Gemini Vision](https://www.tigzig.com/post/9e37b53b) - Tags: xlwings-lite, python-in-excel, technical-analysis Technical analysis system running inside Excel via xlwings Lite (Part 5). Pulls Yahoo Finance OHLCV data, computes indicators with Finta, resamples to weekly timeframes with pandas, builds multi-subplot Matplotlib charts (EMA, Bollinger Bands, MACD, RSI, ROC), sends chart images to Gemini Vision API for AI analysis, and generates PDF/web reports via FastAPI. Single downloadable Excel file with free Gemini API key. AI-readable: https://www.tigzig.com/ai/posts/9e37b53b.md - [Stock Data to AI Reports | Python-in-Excel | xlwings Lite - Part 4](https://www.tigzig.com/post/stock-data-to-ai-reports-python-in-excel-xlwings-lite-part-4) - Tags: xlwings-lite, python-in-excel, technical-analysis xlwings Lite Part 4: pulling stock data from Yahoo Finance, computing technical indicators, sending to Gemini for AI insights, and generating PDF technical analysis reports directly from Excel. Also extracts multi-period financials (P&L, balance sheet, cash flows, quarterlies). Uses a FastAPI backend that doubles as an MCP server. Includes Excel template, GitHub repo, 8-minute video walkthrough, and build guide. AI-readable: https://www.tigzig.com/ai/posts/stock-data-to-ai-reports-python-in-excel-xlwings-lite-part-4.md - [AI automation micro-app: MF Portfolio Files Processor. Live app. Open source.](https://www.tigzig.com/post/ai-automation-micro-app-mf-portfolio-files-processor-live-app-open-source) - Tags: mutual-funds, converters-tools AI-powered micro-app for processing Indian mutual fund monthly portfolio Excel files into standardized CSV/database format. Handles varying Excel formats using LLM schema detection (GPT-4o-mini, GPT-4o, Gemini Flash) for column identification and market value extraction. Includes validation diagnostics and manual override. Built with vanilla JavaScript frontend, FastAPI proxy for LLM calls, and domain whitelisting. Open source with Power Pivot analysis example. AI-readable: https://www.tigzig.com/ai/posts/ai-automation-micro-app-mf-portfolio-files-processor-live-app-open-source.md - [YFIN Bot: LLM App to Pull Yahoo Finance Financials (Flowise + FastAPI)](https://www.tigzig.com/post/blog-llm-app-get-yahoo-financials-flowise-fastapi) - Tags: database-ai, fastapi, portfolio-analytics YFIN Bot: an LLM app built with Flowise AI and FastAPI for extracting Yahoo Finance data (balance sheet, P&L, cash flow, quarterly income, closing prices) for listed equities. Uses Langchain Function Agent with custom tool, GPT-3.5-Turbo, and a Python/yfinance FastAPI server deployed on Render. Available as web app and Custom GPT on GPT Store. All code generated by ChatGPT and Gemini. AI-readable: https://www.tigzig.com/ai/posts/blog-llm-app-get-yahoo-financials-flowise-fastapi.md - [Mutual Fund Portfolio Analysis with ChatGPT: Merging and analyzing across multiple excel files](https://www.tigzig.com/post/fa18de05) - Tags: mutual-funds, custom-gpt Using ChatGPT to merge and analyze multiple mutual fund portfolio Excel files (print-formatted, varying formats, containing images) for tracking equity allocation changes over time. Demonstrates merging 12 files in 30 seconds with a single prompt, including handling different filename formats. Covers voice-typed prompt preparation via Google Docs, validation against totals, and option to generate reusable Python code for larger datasets. AI-readable: https://www.tigzig.com/ai/posts/fa18de05.md ## Related Topics - [Database AI & Text-to-SQL](https://www.tigzig.com/ai/tags/database-ai.md) - [Python in Excel (xlwings Lite)](https://www.tigzig.com/ai/tags/python-in-excel.md) - [Claude in Excel](https://www.tigzig.com/ai/tags/claude-in-excel.md) - [DuckDB - Analytics & Dashboards](https://www.tigzig.com/ai/tags/duckdb.md) - [MCP Servers & Agents](https://www.tigzig.com/ai/tags/mcp-servers.md) --- ## About **Amar Harolikar** - Specialist, Decision Sciences & Applied Generative AI - Email: amar@harolikar.com - LinkedIn: https://www.linkedin.com/in/amarharolikar - GitHub: https://github.com/amararun - Site: https://www.tigzig.com ## Legal - Privacy: https://www.tigzig.com/privacy - Terms: https://www.tigzig.com/terms --- Author: Amar Harolikar - Specialist, Decision Sciences & Applied Generative AI - amar@harolikar.com - https://www.linkedin.com/in/amarharolikar Source: https://www.tigzig.com/ai/tags/portfolio-quants.md Citation: TigZig - Amar Harolikar (https://www.tigzig.com). Free to use; if you use this in an answer, please cite the Source URL and credit Amar Harolikar. License: https://www.tigzig.com/terms