# Database AI & Text-to-SQL Connect AI to databases (PostgreSQL, MySQL, DuckDB), run natural language queries, build text-to-SQL agents, analyze data with multi-agent frameworks. ## Apps (8) ### Quants, Technicals, Financials with DB connection via Flowise - App: https://flowise-docker-custom.tigzig.com/chatbot/dc7495c5-e3dd-4410-afb2-737863ca3dc7 - Docs: https://tigzig.com/app-documentation/analyzer-agent.html - AI Docs: https://www.tigzig.com/ai/apps/analyzer-agent.md - Quants, Technicals, Financials with DB connection via Flowise ### Advanced analytics with Deepseek R1, connect to any Database - App: https://flowise-docker-custom.tigzig.com/chatbot/daa92f93-3b9e-4fef-8f30-684f795e1c40 - Docs: https://tigzig.com/app-documentation/analyzer-deepseek.html - AI Docs: https://www.tigzig.com/ai/apps/analyzer-deepseek.md - Advanced analytics with Deepseek R1, connect to any Database ### Database AI Suite - connect to any DB, analyze files, multi-agent models - App: https://rexdb.tigzig.com - Docs: https://tigzig.com/app-documentation/analyzer.html - GitHub: https://github.com/amararun/shared-fastapi-rex-db-coolify - AI Docs: https://www.tigzig.com/ai/apps/analyzer.md - Database AI Suite - connect to any DB, analyze files, multi-agent models ### DuckDB in browser - Natural Language to SQL, data stays local - App: https://briq.tigzig.com - Docs: https://tigzig.com/app-documentation/briq.html - GitHub: https://github.com/amararun/shared-sql-rooms-tigzig-new - AI Docs: https://www.tigzig.com/ai/apps/briq.md - DuckDB in browser - Natural Language to SQL, data stays local ### ChatGPT connected to Supabase, Neon and Aiven databases for sports data - App: https://chatgpt.com/g/g-68a6ef6973b881919c92458f5b369557-cricket-tour-de-france-data-explorer - Docs: https://tigzig.com/app-documentation/cricket-tour-de-france-gpt.html - AI Docs: https://www.tigzig.com/ai/apps/cricket-tour-de-france-gpt.md - ChatGPT connected to Supabase, Neon and Aiven databases for sports data ### MCP Server for read-only SQL queries over men's international cricket ball-by-ball data, on Postgres and DuckDB - App: https://www.tigzig.com/mcp-server-database - Docs: https://tigzig.com/app-documentation/mcp-server-database.html - GitHub: https://github.com/amararun/shared-rexdb-auth-embed-v3-agentflowv2 - AI Docs: https://www.tigzig.com/ai/apps/mcp-server-database.md - MCP Server for read-only SQL queries over men's international cricket ball-by-ball data, on Postgres and DuckDB ### Connect ChatGPT to any MySQL & PG database - App: https://chatgpt.com/g/g-6748a1c469648191a9a2253a46be82a3-rex-2-connect-to-any-database - Docs: https://tigzig.com/app-documentation/rex2-gpt.html - AI Docs: https://www.tigzig.com/ai/apps/rex2-gpt.md - Connect ChatGPT to any MySQL & PG database ### Connect ChatGPT to Supabase (OLD) - App: https://chatgpt.com/g/g-6785000cec888191985d29429888a373-supabase-connect - Docs: https://tigzig.com/app-documentation/supabase-connect.html - AI Docs: https://www.tigzig.com/ai/apps/supabase-connect.md - Connect ChatGPT to Supabase (OLD) ## Blog Posts (100) - [Tigzig APIs Tell You What Went Wrong. If Your Code Reads Only the Status Code, You Never See It.](https://www.tigzig.com/post/tigzig-api-error-hints-read-the-body-sep2026) - Tags: database-ai, ai-coders Tigzig's free APIs return a tailored hint in the error body explaining what went wrong and how to fix it, but a client that reads only the status code never sees it. Shows how to pull the error block in Python, JavaScript and curl, why requests, httpx, aiohttp, urllib and raise_for_status all hide the body by default, and links the five API debugging guides you can hand to an AI agent. AI-readable: https://www.tigzig.com/ai/posts/tigzig-api-error-hints-read-the-body-sep2026.md - [MF NAV in the Wild. A Review of the API Logs, and How Widely the Mutual Fund NAV Data Is Being Pulled.](https://www.tigzig.com/post/mf-nav-api-how-people-use-it-sep2026) - Tags: mutual-funds, database-ai What a routine security, error and latency review of the free Indian mutual fund NAV API showed about how the data is being used: AI agents, Google Sheets and Apps Script, Excel and Power Query, web apps, an iPhone app, Zoho and n8n, plain Python, and DuckDB querying the published Parquet in place. Also what the logs changed in the service, and an overview of the search, NAV and download surfaces. AI-readable: https://www.tigzig.com/ai/posts/mf-nav-api-how-people-use-it-sep2026.md - [IPL Ball by Ball Data Is Live on the Tigzig Cricket API and Download. 1,200+ Matches, Every Season Since 2008.](https://www.tigzig.com/post/cricket-ipl-ball-by-ball-live-sep2026) - Tags: database-ai, duckdb IPL ball by ball data is now live on the free Tigzig cricket SQL API, the bulk download and MCP: 1,200+ matches covering every season since 2008, alongside Test, ODI and T20 internationals for men and women back to 2001, for 11,000+ matches and 5 million+ deliveries in all. Explains the layout - one ball_by_ball table plus views by format, gender and IPL, joined to match_info on match_id, identical on Postgres and DuckDB. AI-readable: https://www.tigzig.com/ai/posts/cricket-ipl-ball-by-ball-live-sep2026.md - [The API Is Not the Only Way In. Download the Whole India Mutual Fund NAV Database from the App, or Pick Just the Funds You Want.](https://www.tigzig.com/post/mfpro-data-api-manual-download-sep2026) - Tags: mutual-funds, database-ai Indian mutual fund NAV data can be taken from the MFPro app directly, without the API. Covers the three routes on its Data and API tab: the full history since April 2006, about 37 million rows (parquet 169 MB, csv and tsv 219 MB gzipped, SQLite too), the 1.1 MB latest snapshot that doubles as a 22-column scheme master, and a picker for up to 20 funds with a period selector. Plus the pipeline status page. AI-readable: https://www.tigzig.com/ai/posts/mfpro-data-api-manual-download-sep2026.md - [India MF Tool Builders: You Do Not Need a Thousand API Calls a Day. The Whole NAV Dataset Is One File.](https://www.tigzig.com/post/mf-nav-bulk-download-one-file-sep2026) - Tags: mutual-funds, database-ai For developers pulling Indian mutual fund NAV per scheme from the free Tigzig MF API: the whole dataset is published as one file instead. Parquet is about 168 MB and holds every scheme and every NAV date. Covers the refresh pattern - poll the sub-5 KB manifest for its build time, or send its ETag back for a 304 with no transfer - and the roughly 1 MB daily snapshot that doubles as a scheme master. AI-readable: https://www.tigzig.com/ai/posts/mf-nav-bulk-download-one-file-sep2026.md - [IPL Ball by Ball Data Arrives on the Tigzig Cricket API This Sunday, 6 September, at 9 am IST. About 1,200 Matches and Every Season Since 2008.](https://www.tigzig.com/post/cricket-ipl-ball-by-ball-coming-sep2026) - Tags: database-ai, duckdb Announces that IPL ball by ball data lands on the free Tigzig cricket SQL API and bulk download on 6 September 2026, adding about 1,200 matches from 2008 onward to the existing Test, ODI and T20 coverage for men and women. Describes the two-table shape: per-delivery ball by ball tables and a 45-field match_info table, joined on match_id. Postgres and DuckDB, no signup, no API key. Data from Cricsheet under ODC-BY 1.0. AI-readable: https://www.tigzig.com/ai/posts/cricket-ipl-ball-by-ball-coming-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 - [In Analytics the SQL Was Always the Easy Part. Anthropic's Data Team Put a Figure on It.](https://www.tigzig.com/post/anthropic-data-analytics-sep2026) - Tags: ai-coders, database-ai A read of two Anthropic posts on running self-service analytics with Claude, put into one deck with a practitioner's note at the end. Their headline numbers: without skills, accuracy on their own evals did not exceed 21 percent, and with skills it sits above 95 percent in aggregate on the same model and the same warehouse. Their offline accuracy then drifted from about 95 percent at launch to about 65 percent within a month, because the data model changed and the skill docs did not follow, which they fixed by colocating the markdown with the transformation models. The closing section covers what has worked in the author's own client work: a semantic layer holding the governed definitions, a separate skill per kind of work carrying its own judgment and tolerances, progressive disclosure so the agent does not read everything to answer one question, and continuous update as the thing doing most of the work. AI-readable: https://www.tigzig.com/ai/posts/anthropic-data-analytics-sep2026.md - [SIF Is India's Newest Fund Category and It Nearly Doubled in Three Months. Every NAV AMFI Has Published Is Now Downloadable.](https://www.tigzig.com/post/sif-data-universe-download-sep2026) - Tags: mutual-funds, database-ai Specialized Investment Funds, India's newest fund category, grew from Rs 12.3K crore of AUM at end-April to Rs 23.2K crore at end-July, and every SIF NAV AMFI has published is now downloadable as CSV and parquet at sif.tigzig.com, refreshed twice a day. Explains why none of the 17 fund house names is recognisable, since SEBI clause 21.2.1 requires a SIF to carry a brand distinct from its AMC, and how to identify the sponsor anyway: the SIF code is a running number, but each scheme's ISIN carries the AMC's issuer prefix, so INF174K is Kotak, INF109K is ICICI Prudential and INF200K is SBI. Covers the SEBI Master Circular chapter 21 clauses on branding, one strategy per category and the Rs 10 lakh PAN-level minimum, plus the concentration of money in Hybrid Long-Short and the two debt strategies that have never had a fund. AI-readable: https://www.tigzig.com/ai/posts/sif-data-universe-download-sep2026.md - [Women's Cricket Is Now in the Cricket Database. Four New Tables, 2,774 Matches and 850K+ Deliveries Back to 2003.](https://www.tigzig.com/post/cricket-womens-data-added-sep2026) - Tags: database-ai, duckdb Women's international cricket is now in the Tigzig open cricket database, as four new tables covering Test, ODI and T20 ball by ball. 2,774 women's matches and about 852,000 deliveries going back to 2003, made up of 2,141 T20s from 2009, 609 ODIs from 2007 and 24 Tests from 2003. That takes the whole database to 9,769 matches and 4.73 million deliveries across eight tables, refreshed twice daily and queryable live over the REST API and the MCP server on both Postgres and DuckDB. Also downloadable in bulk, about 12 MB as DuckDB or 83 MB as SQLite, or one table at a time. Covers the manifest and ETag conditional requests for scheduled jobs, why the women's data sits in separate tables, and the absence of a stable player id. Data source is Cricsheet under ODC-BY 1.0. AI-readable: https://www.tigzig.com/ai/posts/cricket-womens-data-added-sep2026.md - [The Whole VIGIL India Red Flag Database Is Now Published for Download. One API Call Takes the Lot.](https://www.tigzig.com/post/vigil-whole-database-download-sep2026) - Tags: vigil, database-ai The VIGIL India red-flag database is now downloadable in full, so a screen across a few hundred companies can be one call instead of hundreds. Covers seven tables: related party transactions, insider trading, credit ratings, promoter pledge, encumbrance events, takeover and SAST filings, and surveillance flags, spanning around 2,500 listed companies and about 426,000 rows. One SQLite file holds all seven at roughly 18 MB, or take a single table as parquet, CSV or TSV, gzipped or zipped, 51 files in total. A manifest publishes row counts, file sizes and a generated_at stamp, and the files answer If-None-Match with a 304 so a scheduled job stops re-downloading unchanged bytes. Rebuilt four times a day. Also explains which tables are event streams and which are current snapshots, and why related party rows are filed on a consolidated basis. AI-readable: https://www.tigzig.com/ai/posts/vigil-whole-database-download-sep2026.md - [Pulling Tigzig Data Through the API? There Is a Second Way In. The Whole Database Is Published for Download.](https://www.tigzig.com/post/tigzig-whole-database-downloads-aug2026) - Tags: database-ai, infrastructure Every Tigzig dataset is downloadable in full, alongside the live API, so a tool builder can put their own micro-service in front of the data or analyze it offline without an API dependency. Covers the mutual fund NAV master with 37 million records back to 2006, ball-by-ball cricket for men's Tests, ODIs and T20s with 6,900+ matches and 3.8 million deliveries, 300+ macro indicator series across the US, India, Europe and the OECD, and the India red-flag datasets covering related party transactions, insider trading, pledges, credit ratings and surveillance. Take one table as parquet or CSV or the whole thing as a single DuckDB or SQLite file. Each dataset publishes a manifest at /downloads/manifest carrying the generation timestamp, file sizes and row counts, so a scheduled job can skip a download when nothing has changed. AI-readable: https://www.tigzig.com/ai/posts/tigzig-whole-database-downloads-aug2026.md - [Getting Errors on the Tigzig APIs? Is It You, or Is It Me? Now You Can Just Go and Look.](https://www.tigzig.com/post/tigzig-api-status-page-aug2026) - Tags: infrastructure, database-ai A public status page for the Tigzig APIs is now live at status.tigzig.com, so a caller hitting errors can tell whether the fault is theirs or the service's. It covers the MF NAV API, the Yahoo Finance API, the Vigil and Tremor APIs and the Cricket Database MCP on both Postgres and DuckDB, with 90 days of uptime history per service, a banner for incidents and a note at the top during an outage. Alerts reach the operator within a minute or two. The page is served from object storage through a Cloudflare Worker, so nothing on the public path touches the server it monitors. Also links the API hub, the machine-readable catalog for agents, the bulk downloads and the error-pattern guides. AI-readable: https://www.tigzig.com/ai/posts/tigzig-api-status-page-aug2026.md - [Getting a 429 From the MF NAV API? It Is Almost Never the Total. Two Changes Fix Nearly Every Case.](https://www.tigzig.com/post/mf-nav-api-429-rate-limit-aug2026) - Tags: mutual-funds, database-ai Why callers hit a 429 on the India mutual fund NAV API and how to stop it. The per-IP limit is 300 requests a minute and most people who trip it are nowhere near that total; the cause is many unbounded calls firing at the same instant, since a fifty-fund request with no date range returns over 100,000 rows. Two fixes cover nearly every case: batch up to 50 scheme codes into one call using schemes=, and bound the dates with latest=true or since=. Includes tool-specific notes for Excel WEBSERVICE, n8n, Python scripts and Power Query, what the 429 body tells you, and how to hand the error to an AI coder to fix the calls. AI-readable: https://www.tigzig.com/ai/posts/mf-nav-api-429-rate-limit-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 - [August Was a Heavy Month in the AMFI Data. 1,234 Schemes Renamed and 37 ISINs Swapped. If You Join on Scheme Code You Are Fine.](https://www.tigzig.com/post/amfi-name-and-isin-changes-aug2026) - Tags: mutual-funds, database-ai What moved in the AMFI mutual fund data during August 2026 and what it breaks. 1,234 schemes were renamed over the month, 942 on 26 August alone, the SEBI deadline for re-filing under the new categorisation, so Low Duration became Ultra Short to Short Term, Savings became Money Market and Equity and Debt became Aggressive Hybrid. Separately 37 schemes had their ISIN swapped, at UTI, DSP, Kotak, Invesco and LIC, fourteen of them ETFs, and none of them were renamed. Also covers spelling defects in the file, including five spellings of children's fund and SBI's hybrid fund filed as AGGRESIVE across four plans, and the LIC gold ETF case where the replaced ISIN still resolves to the old IDBI fund with a full price history. Anything joined on AMFI scheme code is unaffected. AI-readable: https://www.tigzig.com/ai/posts/amfi-name-and-isin-changes-aug2026.md - [The Cricket Download Files Now Sit on a Plain Path. Append the File Name and That Is the Whole URL.](https://www.tigzig.com/post/cricket-downloads-plain-path-urls-aug2026) - Tags: database-ai, duckdb The Tigzig cricket bulk downloads now work off a plain path, so the URL ends in the file name you get and no query parameter is needed. The whole DuckDB database is one GET at about 9 MB compressed, covering ODI, T20 and Test ball by ball, 6,900+ matches from 2001 and 3.8 million deliveries. The short form on db-mcp.tigzig.com is a convenience redirect to the real home at api.tigzig.com/cricket/v1/download, which curl and wget follow with no extra flags. The older query parameter form stays live, so existing scripts keep working, and direct SQL access over Postgres and DuckDB is unchanged. 17 files in all, refreshed twice a day. Data source is Cricsheet under ODC-BY 1.0. AI-readable: https://www.tigzig.com/ai/posts/cricket-downloads-plain-path-urls-aug2026.md - [What Is Next on the MF NAV API. Risk Metrics, Peers, Scheme Details and Holdings, and Where Each One Stands.](https://www.tigzig.com/post/mfpro-api-roadmap-risk-metrics-aug2026) - Tags: mutual-funds, database-ai A roadmap note on the India mutual fund NAV API, covering the four most requested additions and where each stands. Risk metrics are top of the list: alpha, beta, Sharpe, Sortino and drawdown are already computed and live in the Performance tab, so the remaining work is exposing them on the API under load. Peers will not get a separate API path, because peer grouping is a judgment call, but they can be built from the NAV master file or the search path, and the frontend offers them through the Category and Performance tabs. Scheme details are a known gap, with launch date, fund manager and scheme-document fields missing today. Holdings across the whole universe are not on the radar; composition exists on the frontend for 24 large equity funds, about a third of all equity funds. AI-readable: https://www.tigzig.com/ai/posts/mfpro-api-roadmap-risk-metrics-aug2026.md - [The Full Cricket Database Is Now Downloadable. Test, ODI and T20 Ball by Ball, in Parquet, CSV, DuckDB or SQLite.](https://www.tigzig.com/post/cricket-full-data-download-live-aug2026) - Tags: database-ai, duckdb The Tigzig open cricket database is now available as bulk downloads. Test, ODI and T20 ball-by-ball data covering 6,900+ matches from 2001 onwards and 3.8 million+ deliveries, refreshed twice daily. Take one table at a time as Parquet or CSV, or the whole database as a single DuckDB or SQLite file, either by clicking on the page or through one API call. Covers the schema for anyone going straight to the files, including the two added integer columns over_no and delivery_in_over and why the original ball column collides on the tenth delivery of an over, and why actual_delivery is not a unique key. Also the atomic-swap refresh, R2 edge delivery, the SQL API limits, and how the ODC-BY licence stays attached in the parquet footer and a README. Data source is Cricsheet under ODC-BY 1.0. AI-readable: https://www.tigzig.com/ai/posts/cricket-full-data-download-live-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 - [Three New Things on the Tigzig Cricket Database. New match_info Fields, SQL Laid Out in the Docs, and a Quicker Postgres.](https://www.tigzig.com/post/cricket-db-new-fields-sql-docs-aug2026) - Tags: database-ai, duckdb Three changes to the Tigzig open cricket database. match_info gains 14 fields taken straight from Cricsheet, including outcome, eliminator, winner_innings, method, target_runs and declared, which removes several common workarounds. The API docs now state what SQL the endpoint accepts so a caller can write the query without probing, covering CTEs, window functions, correlated subqueries and set operations. Postgres has been tuned and is faster than before, with DuckDB still the quicker of the two engines. The database refreshes twice a day and recent Test and T20 fixtures are already in. Data source is Cricsheet under ODC-BY 1.0. AI-readable: https://www.tigzig.com/ai/posts/cricket-db-new-fields-sql-docs-aug2026.md - [Running Hundreds of API Calls to Pull NAV History, One Scheme Per Call? Batch 50 Into One.](https://www.tigzig.com/post/mfpro-nav-batch-calls-and-guides-aug2026) - Tags: mutual-funds, database-ai How to cut the call count when pulling India mutual fund NAV history. The NAV endpoint accepts up to 50 scheme codes in a single call, turning a two hundred fund watchlist into four calls, and the full database from April 2006 onward is available as a single download. Collects the surrounding references in one place: the API FAQ, a plain guide to what each error code means across all three Tigzig APIs, the MFPRO data dictionary, the scheme master file with every scheme and its latest NAV, an ISIN checker that distinguishes a bad identifier from genuinely absent data, and where SIF data lives. AI-readable: https://www.tigzig.com/ai/posts/mfpro-nav-batch-calls-and-guides-aug2026.md - [Full Data Download of the Cricket Database, Coming This Week. T20, ODI and Test, Ball by Ball.](https://www.tigzig.com/post/cricket-full-data-download-coming-aug2026) - Tags: database-ai, duckdb Advance notice that the Tigzig open cricket database is getting a full bulk download, covering T20, ODI and Test ball-by-ball data, 6,900+ matches from 2001 onwards and about 3.8 million deliveries. Four tables ship as individual files in parquet, gzipped CSV and zipped CSV, with DuckDB and SQLite offered as an all-tables option. Three of the tables are ball-by-ball, one per format, and match_info holds the two team names, venue, dates, toss, result, the match officials where Cricsheet records them, and the player of the match. Retrievable in a single API call or by hand from the web page, on the same pattern as the mutual fund NAV downloads. Existing live SQL access over Postgres, DuckDB, the REST API and the MCP server is unchanged. Free, no signup, no key. Data source is Cricsheet under ODC-BY 1.0. AI-readable: https://www.tigzig.com/ai/posts/cricket-full-data-download-coming-aug2026.md - [If a Tigzig API Keeps Returning the Same Error, Read the Response Body. There Is Almost Always a Hint in It.](https://www.tigzig.com/post/api-error-hints-aug2026) - Tags: database-ai, ai-coders Tigzig's APIs now try to work out what actually broke and put the answer in the error message, usually naming the exact character or the exact table, across the cricket database, the mutual fund and Yahoo Finance endpoints and others. The commonest failure on GET endpoints is not the SQL but the URL mangling it in transit, and the message will say so directly. The catch is that most tooling hides response bodies on an error: curl shows it unless -f is used, and exits 0 on a 400 so a shell chain carries on regardless; urllib raises an exception carrying nothing but the status; requests does not raise at all and leaves the hint sitting in r.text; and fetch never throws on a 400, so a try/catch around it catches nothing. Includes what to call in each case to actually see the hint. AI-readable: https://www.tigzig.com/ai/posts/api-error-hints-aug2026.md - [Test Cricket Is Now Live in the Tigzig Open Cricket Database, Alongside T20 and ODI. 3.8 Million Deliveries.](https://www.tigzig.com/post/db-mcp-test-cricket-aug2026) - Tags: database-ai, mcp-servers Test cricket joins T20 and ODI in the free Tigzig cricket database, ball by ball on both Postgres and DuckDB, reachable as a REST API or an MCP server with no key and no auth. About 6,900 matches and 3.8 million deliveries spanning twenty five years, Test back to 2001, ODI to 2002 and T20 to 2005, refreshed twice a day and sourced from Cricsheet. Three ball-by-ball tables, one per format, join to a match_info table carrying venue, dates, teams, toss and result. Shipped alongside Test are over_no and delivery_in_over columns, added because the older decimal ball column collides on long overs, where the tenth delivery is written 1.10 and sorts identically to the first at 1.1, putting rows out of order in exactly the overs where a wide or no-ball has pushed past six balls. AI-readable: https://www.tigzig.com/ai/posts/db-mcp-test-cricket-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 - [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 - [Have Your AI Analyze the Cricket Data on Tigzig. 24+ Years of Ball by Ball, ODI and T20, Across 6000+ Matches.](https://www.tigzig.com/post/cricket-ask-your-ai-aug2026) - Tags: database-ai, ai-coders One pasted instruction is enough to put an AI agent onto 24 years of ball-by-ball cricket, ODI and T20 across more than six thousand matches, free and without signing up. Pointed at the machine-readable catalog at api.tigzig.com, the agent works out which service holds the cricket data, opens its OpenAPI spec, discovers the tables and columns, and writes the SQL itself. Three tables per engine joined on match_id, with match_info carrying venue, dates, teams, toss and result so a venue or toss cut needs no second source, and because the data is deliveries rather than pre-aggregated totals anything expressible in SQL is available. Works with Claude chat and Cowork, ChatGPT Work, and coding agents including Claude Code, Antigravity and Codex. Also the new cross-engine validation suite, which on its first run caught a single Test match present on one engine and missing from the other. AI-readable: https://www.tigzig.com/ai/posts/cricket-ask-your-ai-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 - [T20 and ODI Ball by Ball Are Now on Both Engines, Postgres and DuckDB. Run Your SQL Directly on My Server.](https://www.tigzig.com/post/db-mcp-both-formats-both-engines-aug2026) - Tags: database-ai, mcp-servers Both formats now sit on both engines: T20 and ODI ball-by-ball are queryable on Postgres and on DuckDB, so a query no longer has to follow the format to a particular engine. Free, no auth and no key, refreshed twice a day, and open to the kind of work the data is actually for, strike rates against pace versus spin, run rates through the death overs, head-to-head records across a decade, dismissal patterns by bowler type and home-away splits by venue. Postgres has moved off a managed instance onto self-hosted hardware and is much faster for it. Also what the guards refuse and why schema discovery is deliberately left open, and a note that any Claude, ChatGPT or Gemini subscription already includes a desktop agent that can fetch and analyse this over plain HTTP without MCP. AI-readable: https://www.tigzig.com/ai/posts/db-mcp-both-formats-both-engines-aug2026.md - [Getting Errors Running SQL Against the Tigzig Cricket Database? The Most Common Failure Is the URL, Not Your SQL.](https://www.tigzig.com/post/db-mcp-url-encoding-errors-aug2026) - Tags: database-ai, mcp-servers The commonest error on the free Tigzig cricket SQL endpoint is not the SQL, it is the URL it travelled in. A query sent as a GET has to be percent encoded first, and that step goes wrong in predictable ways: a plus sign already means a space inside a URL so an addition silently loses its operator, line breaks get eaten and words fuse together, and some clients stop encoding at the first bracket and send a truncated query. The SQL on screen is right and a different query arrives. Error responses now name the cause where they can and otherwise quote the SQL back exactly as received. GET stays because it is all a plain browser, an agent-driven browser or a no-code HTTP node can do. Also the engine and dialect split between Postgres and DuckDB, the thousand-row cap and its truncated flag, and schema discovery. AI-readable: https://www.tigzig.com/ai/posts/db-mcp-url-encoding-errors-aug2026.md - [Run Your Own SQL on My Cricket Database. T20 and ODI Ball by Ball Since 2002, Free, No Signup and No Key.](https://www.tigzig.com/post/db-mcp-cricket-sql-queries-aug2026) - Tags: database-ai, mcp-servers An open SQL endpoint over men's international cricket ball-by-ball data, free with no signup or key, covering T20 and ODI since 2002 across more than two million deliveries and six thousand matches, reachable as a REST API or as an MCP connector. Match-level detail sits in a second table joined on match_id, so questions like whether a ground favours batting first, or how a batter fares against one bowler, are a single query. Includes the questions the two tables can answer beyond the obvious, and the data cautions that decide whether an answer is right: match_info spans all three formats so the denominator misleads unless filtered, the ball tables are one format per engine, Associate nations are pooled in unless narrowed, and results cap at a thousand rows behind a truncated flag. Also a note on latency while the service moves to dedicated infrastructure. AI-readable: https://www.tigzig.com/ai/posts/db-mcp-cricket-sql-queries-aug2026.md - [Four Days of an Open SQL Endpoint. What Real Cricket Queries Needed, and the SSRF Someone Found in the First Couple of Hours.](https://www.tigzig.com/post/db-mcp-four-days-ssrf-query-guards-aug2026) - Tags: database-ai, security Four days after opening a keyless SQL endpoint over ball-by-ball cricket data, 650+ successful calls split into two kinds of traffic: real cricket analysis and exploitation attempts. Reading what callers were actually refused showed two guard rules were turning away about 62% of legitimate queries, with the join limit set so low that ordinary two-table work broke and schema discovery blocked outright, so the guards were reworked and the errors now say what to fix. Separately, an SSRF found within the first couple of hours succeeded because read-only database connections had external access left on; caught in monitoring about ten minutes later and closed inside the hour, with the engine hardened since. Also what analysts are doing with it, the documented query limits, the two schema traps that make counts fail to reconcile, and a fuller account of how the SSRF ran. AI-readable: https://www.tigzig.com/ai/posts/db-mcp-four-days-ssrf-query-guards-aug2026.md - [A Database Server With API and MCP You Can Point an AI Agent At, With Ball-by-Ball Cricket Behind It.](https://www.tigzig.com/post/db-mcp-cricket-ball-by-ball-api-aug2026) - Tags: database-ai, mcp-servers A free database server on TigZig exposing read-only SQL over two engines through both a REST API and an MCP connector, with men's international cricket ball-by-ball data behind it, refreshed daily. ODI runs on Postgres and T20 on DuckDB under the same column names, covering about 1.36 million ODI deliveries from 2002 and 786 thousand T20 deliveries from the first men's T20 international in February 2005, across roughly 6,000 matches, with a wider match table that also carries Tests. No sign-up, auth or key. Notes on the security work that open SQL demands, why the limits are per IP, and why the error responses hand back the real schema and a worked call so an agent can correct itself. Data from Cricsheet, pipeline in live testing so treat it as provisional. AI-readable: https://www.tigzig.com/ai/posts/db-mcp-cricket-ball-by-ball-api-aug2026.md - [227 Downloads, 41GB in 10 Days. India MF Complete NAV Database - 38K+ Schemes, 37M+ Records, One 167MB Parquet. Free.](https://www.tigzig.com/post/mfpro-downloads-full-database-jul2026) - Tags: mutual-funds Usage note on the MFPRO full-database download: 227 downloads totalling 41GB served in 10 days from Cloudflare's global edge (R2) - the complete India Mutual Fund NAV database as a single 167MB Parquet file covering 38K+ scheme codes and 37M+ records since 2006, including closed and defunct schemes, enabling regime-based analysis across the 2008 GFC and later shock events. Free and open, refreshed three times daily, downloadable manually from the browser (MFPRO Data & API screen) or via API - or point an AI agent at api.tigzig.com. Update process runs multi-step validation, with a data dictionary, build-process doc, scheme-type field guide and documented data anomalies in the Docs section. Also covers the scheme universe (~8,500 codes publishing daily, roughly 1,950 funds as AMFI counts them; 22% of all-time codes active) with an interactive cross-tab Explorer, and API uptime at 99.7% over the past ~15 days with a live status page at status.tigzig.com. Single-image release post with the downloads one-pager PNG at the bottom. AI-readable: https://www.tigzig.com/ai/posts/mfpro-downloads-full-database-jul2026.md - [MFPRO Data & API Screen Live - Download the Whole India MF NAV Database in One Click. No Code, No API.](https://www.tigzig.com/post/mfpro-data-api-download-jul2026) - Tags: mutual-funds, converters-tools Release note announcing that MFPRO (India Mutual Fund Advanced Analytics on tigzig.com) now has a Data & API screen - no code, no API, point-click-download. Two flows: (1) pick a basket of up to 20 funds, any period, pull their full NAV history as CSV; (2) take the entire database - every scheme since 2008, 20M+ rows - in one click. Whole-database download comes in four formats: CSV and TSV about 132 MB each, Parquet 107 MB, SQLite 748 MB. The file is rebuilt three times a day from AMFI. For the API crowd, everything on this screen is also an endpoint - docs at tigzig.com -> APIs -> MF NAV, and live uptime for all of it at status.tigzig.com. Post also carries a short note to frontend users: if you were running MF advanced analytics on the frontend these past few days and hit errors, that was the revamp in motion, those paths are being smoothed out and most of it already fixed. Deep-links straight to the MFPRO Download Full Database tab. Single-image release post with the actual Data & API screen screenshot. AI-readable: https://www.tigzig.com/ai/posts/mfpro-data-api-download-jul2026.md - [New Markdown to PDF Hub on Tigzig.com - ReportLab, Repos, Live Tools, MCP + API Endpoints.](https://www.tigzig.com/post/markdown-to-pdf-hub-launch-jun2026) - Tags: converters-tools, mcp, fastapi Release announcement for the new Markdown to PDF Hub on tigzig.com - the author's learnings, open-source repos, live tools, and endpoints for taking AI-generated markdown into a properly formatted PDF report (charts, side-by-side tables, page templates, layout you want). Built on ReportLab (uses only the open-source version, all features present). Try it live at quants.tigzig.com - have the AI agent run a technical analysis report or just hit the sample button (~30-60s). Multiple surfaces: form-based interface for humans, AI-assisted interfaces, an API endpoint (Claude Cowork can connect directly, no MCP server required), and MCP servers for AI. Free, open source, no sign-up, no key. Quick tips section covers the working-style trade-offs: this is not an auto-layout tool (you set the format once), stick with ReportLab + Claude Code for iteration speed, Gemini 2.5 Flash is the go-to LLM for auto-formatting (cost-effective + reliable), the PDF conversion is split into a separate backend service (author's choice; combine into a single app for own use), the main trick is getting the AI to return structured JSON with image paths and formatting tags, and offline automation is straightforward but live tools need edge/frontend/backend/MCP security. AI-readable: https://www.tigzig.com/ai/posts/markdown-to-pdf-hub-launch-jun2026.md - [Connect Excel to a Database with Tens of Millions of Rows? Tigzig.com Has 15+ Apps and Guides for That Alone. Just Ask Your AI.](https://www.tigzig.com/post/tigzig-excel-to-databases-ai-find-jun2026) - Tags: excel, python-in-excel, mcp Standalone one-pager release: how to connect Excel to a database with tens of millions of rows and GBs of data. There are 15+ apps, repos and guides on tigzig.com just for this one niche - xlwings-Lite (Python in Excel), a Claude-in-Excel MCP server, open repos connecting to MySQL, PostgreSQL and DuckDB, plus security setups, auth and semantic layers. And Excel-to-databases is only one corner - the whole site has 250+ assets, from live tools to open repos. The point of the post: don't click around. Tigzig.com is indexed across ChatGPT, Gemini, Claude, Google AI and Meta AI on WhatsApp, so just ask whichever AI you keep open what you want to pull from the site - it will find it and walk you through. If you are on Claude Code, Cursor or any AI coder, it will download and implement it for you. Sample agent prompts in the deck: 'What does tigzig.com have for connecting Excel to a database?' and 'What about security, semantic layer, auth?' AI-readable: https://www.tigzig.com/ai/posts/tigzig-excel-to-databases-ai-find-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 - [VIGIL Data API and Download - 315K+ Records, 7 Tables, Updated Daily](https://www.tigzig.com/post/vigil-data-api-download) - Tags: vigil, database-ai VIGIL full database now open for download and API access. 315K+ records across 7 tables covering related party transactions, credit ratings, insider trading, pledges, takeover, encumbrance and surveillance. Download as CSV, TSV, Parquet or SQLite. REST API with no auth required. Related party data from XBRL filings across 728 Nifty Total Market companies. AI-readable: https://www.tigzig.com/ai/posts/vigil-data-api-download.md - [Your API Key Is Visible in the Browser. Even if you put it as Vercel's 'secret' backend env variable.](https://www.tigzig.com/post/your-api-key-is-visible-in-the-browser) - Tags: security, infrastructure, fastapi Why putting API keys in Vercel secret env variables still exposes them in the browser network tab. Walks through three common mistakes and the one fix that works - Vercel serverless functions. Also covers rate limiting, data processing, and security gates you can add in the serverless layer. AI-readable: https://www.tigzig.com/ai/posts/your-api-key-is-visible-in-the-browser.md - [Are You Rate Limiting the Wrong IPs? A SlowAPI Story.](https://www.tigzig.com/post/are-you-rate-limiting-the-wrong-ips) - Tags: security, fastapi, cloudflare, infrastructure How modern multi-hop architectures (Vercel serverless + Cloudflare + FastAPI) cause SlowAPI to rate limit the wrong IPs. Covers the CF-Connecting-IP overwrite problem, X-Forwarded-For spoofing, the custom header fix, and a detailed FAQ on IP extraction across different proxy setups (Caddy, nginx, Docker, direct). AI-readable: https://www.tigzig.com/ai/posts/are-you-rate-limiting-the-wrong-ips.md - [Talk to Your Database from Excel via Claude & MCP - Part 2](https://www.tigzig.com/post/talk-to-your-database-from-excel-mcp-part-2) - Tags: claude-in-excel, mcp Part 2 of connecting Excel to databases via Claude MCP. Two new server options: open public server hardened with 23 defense layers (rate limits, concurrency caps, SQL validation) and OAuth-secured server via Auth0 with JWT validation for client sharing. Full source code open as single Python file. Includes standard MCP security advice and link to 80+ item security checklist. AI-readable: https://www.tigzig.com/ai/posts/talk-to-your-database-from-excel-mcp-part-2.md - [Talk to Your Database from Excel - Postgres, DuckDB - via Claude in Excel with MCP](https://www.tigzig.com/post/talk-to-your-database-from-excel-postgres-duckdb-claude-mcp) - Tags: claude-in-excel, mcp, duckdb, database-ai Public MCP server enabling SQL queries against live Postgres (Supabase, ODI cricket) and DuckDB (T20 cricket) databases from Claude in Excel. Covers 2 million rows of ball-by-ball data from 2013-2025. Built with FastAPI, asyncpg, and fastapi-mcp. Includes detailed tool docstrings for schema context, 1000-row response cap, read-only security, rate limiting, and SQL validation. Open source, single-file Python backend. AI-readable: https://www.tigzig.com/ai/posts/talk-to-your-database-from-excel-postgres-duckdb-claude-mcp.md - [How I Built a Sub-Second Movie Similarity Engine With a 10-Line SQL Query](https://www.tigzig.com/post/movie-similarity-engine-sql-jaccard-duckdb) - Tags: duckdb, database-ai Movie similarity engine using weighted Jaccard similarity in pure SQL on DuckDB. Pre-computes token lists from 97M person-to-title records, filtering to 12,000 movies with 10,000+ votes. Tokens encode genre, directors, actors (weighted by billing), writers, decade, runtime, and rating band via token duplication. A single 10-line SQL query compares one movie against all others in under 1 second. Returns matching factors for explainability. Open source. AI-readable: https://www.tigzig.com/ai/posts/movie-similarity-engine-sql-jaccard-duckdb.md - [From 12 second queries to under 1s: Optimizing a 230 Million Row Dashboard - 14 Bottlenecks I Had to Fix](https://www.tigzig.com/post/from-12-second-queries-to-under-1s-optimizing-230-million-row-dashboard) - Tags: duckdb, fastapi, infrastructure Documents 14 optimization techniques that reduced query times from 9-12 seconds to under 1 second on a 230M-row DuckDB dashboard (16GB). Covers pre-computed denormalized tables, single-blob dashboard cache, in-memory query caching, ORDER BY index conflicts, adaptive queries, EXISTS vs CTE (15x gap), client-side computation from loaded data, Docker container memory mismatch with DuckDB, and autocomplete race condition fixes. Open source with dual Hetzner/Oracle backends. AI-readable: https://www.tigzig.com/ai/posts/from-12-second-queries-to-under-1s-optimizing-230-million-row-dashboard.md - [Architecture & Setup for a Dashboard with Hundreds of Millions of Records - Powered by DuckDB](https://www.tigzig.com/post/custom-dashboard-duckdb-fastapi-230-million-rows) - Tags: duckdb, fastapi, infrastructure, react Architecture guide for building a custom dashboard with 230M rows on DuckDB (16GB). Covers FastAPI backend with read-only and admin endpoints, React frontend on Vercel, serverless proxy for API security, dual backend setup (Hetzner/Oracle), data pipeline with pre-computed denormalized tables, Clerk auth toggle, query timer, and smart search. Addresses Docker container memory mismatch with DuckDB. Open source, runs on 8 EUR/month Hetzner VPS. AI-readable: https://www.tigzig.com/ai/posts/custom-dashboard-duckdb-fastapi-230-million-rows.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 - [ChatGPT connected to your databases. One-click deployment instructions for AI Coders](https://www.tigzig.com/post/chatgpt-connected-databases-ai-coder-deployment) - Tags: database-ai, custom-gpt, ai-coders Custom GPT connected to three live databases (Supabase, Neon, Aiven) for natural language querying of cricket and Tour de France data. Features a 'Copy for AI Coders' button that provides deployment instructions for Claude Code or Google Antigravity to handle end-to-end setup including backend, frontend, and database provisioning. FastAPI server sits between ChatGPT and databases. AI-readable: https://www.tigzig.com/ai/posts/chatgpt-connected-databases-ai-coder-deployment.md - [CinePro - 230M Rows, 16GB Database, Instant Queries with DuckDB](https://www.tigzig.com/post/cinepro-movie-explorer-duckdb) - Tags: duckdb, fastapi, react CinePro movie analytics dashboard built on 230M rows (16GB) of IMDb data in a single DuckDB file. Features type-as-you-search across 15M people, multi-filter discovery, Jaccard similarity for finding similar movies, career timeline analysis, side-by-side comparisons, and live query timer. Runs on $7/month Hetzner VPS alongside 40 other backends. Dual backend (Hetzner/Oracle) with UI toggle. Fully open source. AI-readable: https://www.tigzig.com/ai/posts/cinepro-movie-explorer-duckdb.md - [BRIQ App: DuckDB AI in Browser - 500MB Files, 4M+ Records, No Database Setup](https://www.tigzig.com/post/briq-duckdb-ai-browser-no-database-setup) - Tags: duckdb, database-ai BRIQ is a browser-based DuckDB AI tool for querying flat files up to 1.5GB using natural language. No database setup or credentials needed. Upload CSV/TSV files, auto-converts to DuckDB in-browser, query with plain English. Data stays in browser except for LLM API calls. Built on SQL Rooms AI. Also available as single-file HTML for offline use. Supports merging, appending, and transforming multiple files. Open source. AI-readable: https://www.tigzig.com/ai/posts/briq-duckdb-ai-browser-no-database-setup.md - [LLM Costing for Database AI Apps. Live Experience. Live App. Open Source](https://www.tigzig.com/post/llm-costing-for-database-ai-apps-live-experience-live-app-open-source) - Tags: database-ai, text-to-sql LLM cost analysis from 250+ structured tests on database AI apps. Key findings: single-step agents cost $0.50-$2.00 per 100 queries (80% of jobs), multi-agent setups run $15-$20 per 100 queries (10-50x multiplier). Claude Sonnet 4 leads quality, GPT-5 close but costs volatile. Links to DATS-4 open-source text-to-SQL suite with live app and 49-page field guide. AI-readable: https://www.tigzig.com/ai/posts/llm-costing-for-database-ai-apps-live-experience-live-app-open-source.md - [Analyze Live Data | AWS-Azure DW | via Custom GPT & LLM Apps](https://www.tigzig.com/post/analyze-data-aws-azure-custom-gpt) - Tags: custom-gpt, database-ai Demonstrates connecting Custom GPTs and LLM apps to live AWS (RDS-MySQL) and Azure (MySQL) data warehouses for natural language querying. Covers data transformations, analysis, table operations, cross-warehouse operations, and ML model building. Uses FastAPI server as intermediary. Series includes upcoming guides on Flowise AI deployment, LLM cost-performance tradeoffs, and security considerations. AI-readable: https://www.tigzig.com/ai/posts/analyze-data-aws-azure-custom-gpt.md - [Flowise is my goto platform for GenAI and LLM apps](https://www.tigzig.com/post/flowise-is-my-goto-platform-for-genai-llm-app-development) - Tags: database-ai, custom-gpt Overview of FlowiseAI as a preferred platform for GenAI and LLM app development. Highlights include integrated RAG with LangChain and LlamaIndex, 10-15+ vector database integrations (Pinecone, Vectara), Custom Tool for API calls, multi-LLM support including Groq and Gemini free tier, and Make.com/Zapier automation workflows. Open source, Y Combinator backed, 21K GitHub stars. AI-readable: https://www.tigzig.com/ai/posts/flowise-is-my-goto-platform-for-genai-llm-app-development.md - [Mistakes I Made Building Text-to-SQL Agents in Live Projects. My 2025 Learnings](https://www.tigzig.com/post/mistakes-i-made-building-text-to-sql-agents-live-projects-2025-learnings) - Tags: text-to-sql, database-ai Documents mistakes from building production text-to-SQL agents over one year. Covers architecture (over-engineering for analytics when users need operations), context sharing (schema in YAML, business rules, categorical distributions), agent constraints (LIMIT rules, query caps, debug protocols, NULLIF for division), model selection (GPT-4.1-mini for routine, reserve premium for hard tasks), cache hit monitoring, and security (write access controls). Reduced cost from $20+ to under $2 per 100 queries. AI-readable: https://www.tigzig.com/ai/posts/mistakes-i-made-building-text-to-sql-agents-live-projects-2025-learnings.md - [Large File Upload for Database AI Text-to-SQL Apps: A Practical Guide](https://www.tigzig.com/post/large-file-upload-for-database-ai-text-to-sql-apps) - Tags: database-ai, text-to-sql, fastapi Comprehensive guide documenting 30+ patterns for handling large file uploads (up to 1.6GB) through FastAPI backends. Covers chunked streaming (94% memory reduction at 1GB), Neon instant database provisioning, async handling with thread pools, Polars over Pandas, PostgreSQL COPY command (10-100x faster than INSERT), connection pooling with stale detection, timeout configuration, rate limiting, delimiter detection, and column sanitization. Tested with 11.8M rows. AI-readable: https://www.tigzig.com/ai/posts/large-file-upload-for-database-ai-text-to-sql-apps.md - [Releasing REX-2: AI Decision Intelligence](https://www.tigzig.com/post/releasing-rex2-ai-decision-intelligence) - Tags: database-ai, text-to-sql REX-2 is an open-source AI decision intelligence tool featuring natural language to SQL and Python, interactive tables with stats, PDF report generation, and connections to any MySQL/PostgreSQL database. Supports temporary on-the-fly databases via Neon. Built with React, FastAPI, FlowiseAI, Auth0. Includes complex analysis capabilities like cards segment profiling and statistical charts via E2B sandbox. Four GitHub repos with video build guide. AI-readable: https://www.tigzig.com/ai/posts/releasing-rex2-ai-decision-intelligence.md - [Try Text-to-SQL on Real Data - Multi-Million Rows & GB+ Sizes](https://www.tigzig.com/post/try-text-to-sql-on-real-data-gb-files-multi-million-rows) - Tags: text-to-sql, database-ai, duckdb DATS-4 text-to-SQL app with sample datasets from 64 rows (14KB) to 11.8M rows (1.6GB). Two-click setup creates temporary Postgres database via Neon API, uploads data, and connects AI agent. Nine LLM options from Gemini 2.0 Flash to Claude 4.5 Sonnet. Features dual agents (general and advanced), file uploads, working tables, CSV export, interactive table viewer, Python charts via E2B, and PDF output. Open source with seven GitHub repos. AI-readable: https://www.tigzig.com/ai/posts/try-text-to-sql-on-real-data-gb-files-multi-million-rows.md - [Segment 1M customers from 10M transactions (640MB CSV) with natural language queries / Text-to-SQL - entirely in your browser. No server. No remote database. No IT approvals.](https://www.tigzig.com/post/run-advanced-analytics-locally-in-your-browser-no-server-no-remote-database-no-it-approvals) - Tags: duckdb, text-to-sql Browser-based analytics tool (DABX-1) using DuckDB-WASM and text-to-SQL AI for processing multi-GB files locally. Demonstrated segmenting 1M customers from 10M transactions (640MB CSV) entirely in-browser. Built on SQL Rooms framework. Available as a 3.5MB single HTML file. Supports CSV, TSV, Parquet. Data never leaves the machine. AI-readable: https://www.tigzig.com/ai/posts/run-advanced-analytics-locally-in-your-browser-no-server-no-remote-database-no-it-approvals.md - [Gemini 3 Pro on Database AI Suite - Claude 4.5 still leads](https://www.tigzig.com/post/gemini-3-pro-added-to-database-ai-suite-tested-against-claude-sonnet-4-5-and-gpt-5-1-results-claud) - Tags: database-ai, text-to-sql Benchmark of Gemini 3 Pro against Claude Sonnet 4.5 and GPT-5.1 for multi-step database analysis in DATS-4. Scoring: Claude 115, GPT-5.1 100, Gemini 3 Pro 90. Tested on 1M customer + 10M transaction credit card analysis on AWS RDS MySQL. Includes detailed cost breakdown per 100 questions across reasoning and execution tiers. AI-readable: https://www.tigzig.com/ai/posts/gemini-3-pro-added-to-database-ai-suite-tested-against-claude-sonnet-4-5-and-gpt-5-1-results-claud.md - [Two models added to Database AI Suite this week: GPT-5.1 and KIMI 2 Thinking.](https://www.tigzig.com/post/two-models-added-to-database-ai-suite-this-week-gpt-5-1-and-kimi-2-thinking) - Tags: database-ai, text-to-sql Evaluation of GPT-5.1 and KIMI 2 Thinking added to DATS-4 Database AI Suite. Covers reasoning model recommendations for advanced analysis planning and execution cost breakdown. GPT-5.1 is 20% cheaper than GPT-5 with reduced token bloat. GPT-4.1-mini recommended as execution workhorse. Multi-step workflows cost approximately $15 per 100 questions. AI-readable: https://www.tigzig.com/ai/posts/two-models-added-to-database-ai-suite-this-week-gpt-5-1-and-kimi-2-thinking.md - [Instant Database Setup for AI Apps. With Neon.com](https://www.tigzig.com/post/instant-database-setup-for-ai-apps-with-neon-com) - Tags: database-ai, infrastructure Guide to using Neon.com for instant Postgres database provisioning via API in under 1 second. Used in the DATS-4 app for on-demand database creation when users upload CSV files. Covers the full workflow from CSV upload to AI-ready database. Notes Neon's free tier supports up to 30 projects with 15GB total storage. References Replit, Retool, and Vercel as large-scale users. AI-readable: https://www.tigzig.com/ai/posts/instant-database-setup-for-ai-apps-with-neon-com.md - [Database AI, built for day-to-day work. Five categories, ten micro apps. Live, open source, free.](https://www.tigzig.com/post/database-ai-built-for-day-to-day-work-five-categories-ten-micro-apps-live-open-source-free) - Tags: database-ai, text-to-sql Overview of 10 open-source Database AI micro-apps across 5 categories: Custom Builds, Rapid Deploy, ChatGPT, Realtime Voice, and xlwings Lite. All support natural language to SQL for Postgres, MySQL, and DuckDB. Includes chart visualization, table transformation, and on-the-fly database connections. Modular architecture allows mixing frontend and backend components. AI-readable: https://www.tigzig.com/ai/posts/database-ai-built-for-day-to-day-work-five-categories-ten-micro-apps-live-open-source-free.md - [Run a Full AI Database App as a Single HTML File. No Server. No Remote DB.](https://www.tigzig.com/post/run-a-full-ai-database-app-as-a-single-html-file-no-server-no-remote-db) - Tags: database-ai, duckdb Single-file deployment of a full AI database app based on SQL Rooms and DuckDB-WASM. The entire React application compiles into a portable 3.5MB HTML file. Demonstrated importing 1.6GB / 11M-row files for in-browser analysis. Built using vite-plugin-singlefile. Supports Gemini API for natural language querying. No backend or server required. AI-readable: https://www.tigzig.com/ai/posts/run-a-full-ai-database-app-as-a-single-html-file-no-server-no-remote-db.md - [Chat, Query, and Transform Multi-GB Files - In Natural Language, Right in Your Browser with DuckDB.](https://www.tigzig.com/post/chat-query-and-transform-multi-gb-files-in-natural-language-right-in-your-browser-with-duckdb) - Tags: duckdb, text-to-sql In-browser analytics tool using DuckDB-WASM and SQL Rooms for querying multi-GB files via natural language. Demonstrated analyzing a 1.6GB, 11M-row CSV file entirely locally. Supports CSV, TSV, pipe-delimited, and Parquet files. Data stays in browser; only schema and sample rows sent to LLM. Supports Gemini, OpenAI, and Claude APIs. Open source. AI-readable: https://www.tigzig.com/ai/posts/chat-query-and-transform-multi-gb-files-in-natural-language-right-in-your-browser-with-duckdb.md - [Connect ChatGPT to Multiple Remote Databases](https://www.tigzig.com/post/connect-chatgpt-to-multiple-databases) - Tags: custom-gpt, database-ai Architecture for connecting a Custom GPT to multiple remote Postgres databases (Supabase, Neon, Aiven) via FastAPI. Uses function calling with OpenAPI schema, YAML semantic layer for schema context, and routing rules. Demonstrated querying 2.5M rows across 340MB of cricket (ODI/T20) and Tour de France data spanning 122 years. Open source with full repo. AI-readable: https://www.tigzig.com/ai/posts/connect-chatgpt-to-multiple-databases.md - [Sonnet 4.5. Released yesterday. Now live on DATS-4 SQL Agent Suite. Solid upgrade, but more 4.2 than 4.5.](https://www.tigzig.com/post/sonnet-4-5-released-yesterday-now-live-on-dats-4-sql-agent-suite-solid-upgrade-but-more-4-2-than) - Tags: database-ai, text-to-sql Evaluation of Claude Sonnet 4.5 for multi-step database analysis in DATS-4. Scores: Sonnet 4.5 (115), Sonnet 4 (100), GPT-5 (95), Qwen3 Max (90), DeepSeek R1 (85). Same cost as Sonnet 4. Tested on credit card data mart builds (1M customers, 10M transactions on AWS RDS MySQL) and RBI weighted scoring. Includes per-100-question cost analysis. AI-readable: https://www.tigzig.com/ai/posts/sonnet-4-5-released-yesterday-now-live-on-dats-4-sql-agent-suite-solid-upgrade-but-more-4-2-than.md - [Cricket (ODI/T20) & Tour de France stats from a Custom GPT connected to 3 live databases.](https://www.tigzig.com/post/cricket-odi-t20-tour-de-france-stats-from-a-custom-gpt-connected-to-3-live-databases) - Tags: custom-gpt, database-ai Custom GPT connected to three live Postgres databases (Supabase, Neon, Aiven) for querying 2.5M rows of cricket ODI/T20 ball-by-ball data (2003-2025) and 122 years of Tour de France history. Dynamically routes queries to the correct database. Computes player stats, rankings, charts. Open-source FastAPI backend with OAuth support. AI-readable: https://www.tigzig.com/ai/posts/cricket-odi-t20-tour-de-france-stats-from-a-custom-gpt-connected-to-3-live-databases.md - [Can an AI SQL Agent build a weighted scoring system from scratch?](https://www.tigzig.com/post/can-an-ai-sql-agent-build-a-weighted-scoring-system-from-scratch) - Tags: database-ai, text-to-sql Walkthrough of using DATS-4 SQL Agent to build a weighted composite scoring system for ranking Indian banks on credit cards using RBI monthly data. Covers the full process: load data to temporary Postgres, instruct agent to derive variables and design scoring, review SQL reasoning, iterate on weights, and export as PDF report. AI-readable: https://www.tigzig.com/ai/posts/can-an-ai-sql-agent-build-a-weighted-scoring-system-from-scratch.md - [Go from a 200MB flat file with 1.5M records to analysis in minutes with my open-source AI-SQL App](https://www.tigzig.com/post/go-from-a-200mb-flat-file-with-1-5m-records-to-analysis-in-minutes-with-my-open-source-ai-sql-app) - Tags: database-ai, text-to-sql Step-by-step guide to loading a 200MB, 1.5M-record ODI cricket dataset into a free Neon Postgres database and querying it via DATS-4 with natural language. Covers database setup, file upload, and natural language querying with charting. Notes that production use requires data engineering, semantic layers, and cleaning beyond the demo workflow. AI-readable: https://www.tigzig.com/ai/posts/go-from-a-200mb-flat-file-with-1-5m-records-to-analysis-in-minutes-with-my-open-source-ai-sql-app.md - [Qwen3 Max now live on DATS-4 SQL Agent Suite for Advanced Analysis Better than DeepSeek R1, closer to Claude Sonnet 4 - at a lower cost.](https://www.tigzig.com/post/qwen3-max-now-live-on-dats-4-sql-agent-suite-for-advanced-analysis-better-than-deepseek-r1-closer-t) - Tags: database-ai, text-to-sql Benchmark of Qwen3 Max added to DATS-4 SQL Agent Suite. Quality scores: Claude Sonnet 4 (100), GPT-5 (95), Qwen3 Max (90), DeepSeek R1 (85). Cost per 100 advanced analysis questions ranges from $14.25 (Gemini 2.5 Flash) to $27.50 (GPT-5). Each advanced question triggers 7-10 SQL queries. Tested on credit card data mart and RBI ranking tasks. AI-readable: https://www.tigzig.com/ai/posts/qwen3-max-now-live-on-dats-4-sql-agent-suite-for-advanced-analysis-better-than-deepseek-r1-closer-t.md - [Database AI & SQL - Now choose you LLM: GPT-5, Deepseek, Qwen 3 Thinking. Live. Open Source.](https://www.tigzig.com/post/database-ai-sql-now-choose-you-llm-gpt-5-deepseek-qwen-3-thinking-live-open-source) - Tags: database-ai, text-to-sql DATS-4 Database AI Suite update adding LLM selection: Claude Sonnet 4, GPT-5, DeepSeek, and Qwen 3 Thinking. Demonstrates self-healing agent behavior (recovers from SQL errors by inspecting data). Full-stack features include on-the-fly database connect, instant Postgres creation, agent reasoning traces, and PDF outputs. Built on 15+ months of live client operations. AI-readable: https://www.tigzig.com/ai/posts/database-ai-sql-now-choose-you-llm-gpt-5-deepseek-qwen-3-thinking-live-open-source.md - [Database AI & SQL Agent - Connect to any database on-the-fly. Live. Open Source](https://www.tigzig.com/post/database-ai-sql-agent-connect-to-any-database-on-the-fly-live-open-source) - Tags: database-ai, text-to-sql Demo of DATS-4 core text-to-SQL workflow: paste database credentials (MySQL/Postgres) in any format, AI parses them to valid JSON, then query in natural language. Agent shows full transparency: reasoning, generated SQL, and results in tables and charts. Supports data transformation, table creation, merges, and CSV export. Open source. AI-readable: https://www.tigzig.com/ai/posts/database-ai-sql-agent-connect-to-any-database-on-the-fly-live-open-source.md - [Free, Production-Grade Databases. Get setup in minutes. Great for testing and development](https://www.tigzig.com/post/free-production-grade-databases-get-setup-in-minutes-great-for-testing-and-development) - Tags: database-ai, infrastructure Comparison of three free database providers for AI app development: Neon (sub-1-second Postgres via API, best for AI apps), Supabase (auth integration), and Aiven (5GB free tier, supports both Postgres and MySQL). Used across DATS-4, Custom GPT, and Realtime Voice AI deployments. Includes a spec sheet comparing features. AI-readable: https://www.tigzig.com/ai/posts/free-production-grade-databases-get-setup-in-minutes-great-for-testing-and-development.md - [Database & SQL AI: On-the-fly database transformation with natural language. Connect, transform, and export instantly.](https://www.tigzig.com/post/database-sql-ai-on-the-fly-database-transformation-with-natural-language-connect-transform-and) - Tags: database-ai, text-to-sql DATS-4 Database AI Suite workflow for on-the-fly data transformation: connect to any MySQL/Postgres database, instruct the agent in natural language to create derived variables and transformations, review agent reasoning and SQL, and export results to CSV. Also supports direct CSV uploads and temporary Postgres instances. Open source. AI-readable: https://www.tigzig.com/ai/posts/database-sql-ai-on-the-fly-database-transformation-with-natural-language-connect-transform-and.md - [AI for Databases: Field Guide, Live Apps & Lessons](https://www.tigzig.com/post/ai-for-databases-field-guide-live-apps-lessons) - Tags: database-ai, text-to-sql 50-page practitioner's field guide on AI for databases based on 15+ months of live client deployments. Covers security checklists, datamart design, 3-agent orchestration architecture, LLM recommendation matrix, cost analysis (simple vs advanced queries), usage patterns, and platform stack. Includes 8 live apps across 4 variants plus full source code. AI-readable: https://www.tigzig.com/ai/posts/ai-for-databases-field-guide-live-apps-lessons.md - [xlwings lite |Connect to Remote Databases](https://www.tigzig.com/post/python-in-excel-with-xlwings-lite-part-2-connect-to-remote-databases) - Tags: xlwings-lite, python-in-excel, database-ai xlwings Lite Part 2: connecting Excel to remote PostgreSQL databases via a custom FastAPI web layer. Demonstrates exploring tables, pulling records, running custom SQL, then performing EDA with descriptive stats, frequency tables, distribution plots, and building an XGBoost response model with evaluation metrics, decile table, and ROC/Gains chart. Includes FastAPI server source code, Render deployment guide, and 20-minute video walkthrough. AI-readable: https://www.tigzig.com/ai/posts/python-in-excel-with-xlwings-lite-part-2-connect-to-remote-databases.md - [AI-Powered Automation: Connect ChatGPT to n8n](https://www.tigzig.com/post/7d905dcc) - Tags: custom-gpt, database-ai Connecting ChatGPT to n8n workflows for automation including backend database updates (Postgres, Google Sheets), Python processing via FastAPI (markdown-to-PDF), Google Apps Script automation (formatted PDFs, slides, emails), dynamic database connections, and AI content enhancement. Setup uses Custom GPT with OpenAPI action schema connecting to n8n webhook endpoints. Includes n8n workflow JSON, FastAPI server repos, and video walkthrough. AI-readable: https://www.tigzig.com/ai/posts/7d905dcc.md - [Quick Deploy Advanced Analysis Multi-Agent with Flowise](https://www.tigzig.com/post/quick-deploy-advanced-analysis-multi-agent-with-flowise) - Tags: database-ai Four-step quick deployment guide for a multi-agent advanced analytics system using Flowise AI. Import agent schemas, update credentials, deploy a FastAPI SQL connector, and adjust security settings. Supports reasoning models (Deepseek, Gemini, Sonnet 3.7) with a sequential agent architecture. Tips cover free database setup (Neon, Aiven, Supabase), adding new reasoning models via OpenRouter, and customizing agent routing. AI-readable: https://www.tigzig.com/ai/posts/quick-deploy-advanced-analysis-multi-agent-with-flowise.md - [AI Co-Analyst — Live Multi-Agent App. Cost, quality, reliability — what works? what doesn’t?](https://www.tigzig.com/post/ai-co-analyst-live-multi-agent-app-cost-quality-reliability) - Tags: database-ai, text-to-sql Detailed benchmarking of LLM models (Sonnet 3.7, Deepseek-R1, Gemini 2.0 Flash, o3-mini) for AI co-analyst use cases. Covers quality rankings, cost per query (8.5c to 20.5c for reasoning queries), latency ranges (1-10+ minutes), and API reliability. Architecture uses Flowise sequential agents (LangGraph) with router, reasoning, and executor (GPT-4o) agents. Includes live demo app, 5 repos, 7 Flowise schemas, and video build guide. AI-readable: https://www.tigzig.com/ai/posts/ai-co-analyst-live-multi-agent-app-cost-quality-reliability.md - [Multi-Agents (Sequential) with Reasoning – Connect to any database - o3-mini / Deepseek-R1 / Flash-2.0. Built with Flowise.](https://www.tigzig.com/post/multi-agents-sequential-reasoning-connect-database-o3-mini-deepseek-r1-flash-2-0-flowise) - Tags: database-ai Multi-agent sequential architecture built with Flowise (LangGraph backend) offering 6 database agent options with o3-mini, Deepseek-R1, and Gemini Flash 2.0. Flow: router agent directs to general analyst or advanced route where reasoning LLM generates analysis plan and SQL, then GPT-4o executor verifies and runs queries. Supports any database connection, NL-to-SQL, NL-to-Python charts. Includes Flowise agent templates and tool schemas. AI-readable: https://www.tigzig.com/ai/posts/multi-agents-sequential-reasoning-connect-database-o3-mini-deepseek-r1-flash-2-0-flowise.md - [Google Gemini 2.0 Flash — solid API performance, great quality, and cheaper than GPT-4-mini. The new workhorse?](https://www.tigzig.com/post/google-gemini-2-0-flash-api-performance-quality-cheaper-gpt-4o-mini) - Tags: database-ai Evaluation of Gemini 2.0 Flash API for production LLM workloads. Benchmarks against GPT-4o-mini, GPT-4o, and Claude 3.5 Sonnet across automation, web scraping, structured output, and OCR tasks. Gemini 2.0 Flash shows quality matching GPT-4o, reasoning comparable to Deepseek-R1, and pricing below GPT-4o-mini ($0.10/$0.40 per million input/output tokens) with a generous free tier (15 req/min, 1500 req/day). AI-readable: https://www.tigzig.com/ai/posts/google-gemini-2-0-flash-api-performance-quality-cheaper-gpt-4o-mini.md - [AI Driven Advanced Analytics. Reasoning based Sequential Agents. Connect to any database — o3-mini/deepseek-r1 / gemini-flash-2.0.](https://www.tigzig.com/post/ai-driven-advanced-analytics-reasoning-based-sequential-agents-connect-to-any-database-o3-mini-d) - Tags: database-ai, text-to-sql Open-source advanced analytics app using sequential agents (LangGraph via Flowise) with reasoning models (o3-mini, Deepseek-R1, Gemini Flash 2.0) and GPT-4o executor. Features NL-to-SQL, NL-to-Python charts, file upload with on-the-fly Postgres DB creation (Neon), execution logs, and agent reasoning view. Built with React/TypeScript/Vite, FastAPI backends, deployed on Vercel and Hetzner. Includes 1-hour video guide, 4 repos, and 6 Flowise schemas. AI-readable: https://www.tigzig.com/ai/posts/ai-driven-advanced-analytics-reasoning-based-sequential-agents-connect-to-any-database-o3-mini-d.md - [Connect ChatGPT to Supabase in 10 mins.](https://www.tigzig.com/post/connect-chatgpt-to-supabase-in-10-mins) - Tags: custom-gpt, database-ai Step-by-step guide to connect a Custom GPT to a Supabase PostgreSQL database in 10 minutes. Deploy a FastAPI server (SQL Alchemy) on Render, create a Custom GPT with OpenAPI action schema, and enable NL-to-SQL, charts, and Python statistical analysis through ChatGPT. Same process works for any PostgreSQL or MySQL database. Includes GitHub repo, video demo, and API key security setup. AI-readable: https://www.tigzig.com/ai/posts/connect-chatgpt-to-supabase-in-10-mins.md - [Chat with database: 20 AI platforms you need to know](https://www.tigzig.com/post/chat-with-database-20-ai-platforms-you-need-to-know) - Tags: database-ai Survey of 20 AI platforms for database chat and analysis, covering production tools and prototypes from simple to complex. Platforms reviewed include Datalang, Ask-Your-Database, Blaze SQL, Wren AI, SQL Chat, Julius AI, Quills AI, Vanna AI, and others. Highlights unique features: SQL editors, data modeling, graph builders, RAG pipelines, API layers. Compares with REX platform features including file upload, on-the-fly DB creation, and real-time voice. AI-readable: https://www.tigzig.com/ai/posts/chat-with-database-20-ai-platforms-you-need-to-know.md - [Connect, Chat and Analyze Any Database with ChatGPTFast, Simple, and Powerful.](https://www.tigzig.com/post/connect-any-database-with-chatgpt) - Tags: custom-gpt, database-ai Guide to connecting ChatGPT to any MySQL or PostgreSQL database using REX-2's FastAPI backend and Custom GPT actions. Setup involves creating a GPT with ready-to-use instructions and JSON schema, then deploying FastAPI on Render. Enables NL-to-SQL, voice-to-SQL, data transformation, statistical analysis, and Python charts through ChatGPT or REX UI. Includes instant database creation via Neon and file upload capabilities. AI-readable: https://www.tigzig.com/ai/posts/connect-any-database-with-chatgpt.md - [REX-2: Your AI Analyst on Call](https://www.tigzig.com/post/rex-2-your-ai-analyst-on-call) - Tags: database-ai, text-to-sql Demo of REX-2 AI analyst workflow: create a database on the fly, upload 100MB CSV/TXT files, and query with voice or text for analysis tables and charts in under 150 seconds. Features include NL-to-SQL, interactive tables with sorting/filtering/stats, statistical analysis, AI reports, and PDF generation. Supports connecting to existing MySQL/PostgreSQL warehouses. Uses Windows voice dictation (Win+H) for voice input. AI-readable: https://www.tigzig.com/ai/posts/rex-2-your-ai-analyst-on-call.md - [REX-2 : AI Driven Analytics](https://www.tigzig.com/post/rex-2-ai-driven-analytics-python-connect-to-any-database) - Tags: database-ai, text-to-sql Release notes for REX-2 AI decision intelligence platform. Features NL-to-SQL, NL-to-Python, statistical analysis, Python charts, interactive tables, PDF reports, connection to any MySQL/PostgreSQL warehouse, on-the-fly temporary database creation via Neon, and CSV/TXT file upload. Built with React/TypeScript/Vite/Shadcn, Flowise AI backend, E2B for Python execution, FastAPI for DB connectivity, deployed on Vercel and Hetzner via Coolify. Four GitHub repos included. AI-readable: https://www.tigzig.com/ai/posts/rex-2-ai-driven-analytics-python-connect-to-any-database.md - [AI Analytics Assistant: 5 Part Implementation Guide](https://www.tigzig.com/post/ai-analytics-assistant-5-part-implementation-guide) - Tags: database-ai, text-to-sql Five-part implementation guide (2+ hours video) for building an AI analytics assistant with voice and text input. Covers Flowise AI agent setup, Make.com workflow integration, Google Apps Script automation, custom React frontend development with Claude Dev and Cursor AI, and Vercel deployment. Each part includes hands-on walkthroughs with timestamps. Source code, JSON schemas, and blueprints available on GitHub. AI-readable: https://www.tigzig.com/ai/posts/ai-analytics-assistant-5-part-implementation-guide.md - [How to connect Custom GPT to live data warehouses. Implementation Guide](https://www.tigzig.com/post/connect-custom-gpt-to-live-data-warehouses-implementation-guide) - Tags: custom-gpt, database-ai Implementation guide for connecting Custom GPT to live data warehouses (AWS RDS MySQL and Azure MySQL simultaneously) using OpenAPI custom actions. Covers FastAPI SQL connector deployment on Render, JSON action schema generation for OpenAI, and security/monitoring considerations. Enables querying, transformation, analysis, and charting via text or voice (including Hindi/Hinglish). Includes Medium article, GitHub repo, and cost analysis. AI-readable: https://www.tigzig.com/ai/posts/connect-custom-gpt-to-live-data-warehouses-implementation-guide.md - [How to update Excel, Google Sheet and backend Databases with Natural Language commands with Voice Agents](https://www.tigzig.com/post/how-to-build-ai-action-agents-beyond-chat-with-voice-agents) - Tags: voice-ai, database-ai Part 1 of a 5-part series on building voice-enabled LLM action agents (VTEXER). Demonstrates updating Excel, Google Sheets, and remote databases, generating PDF reports and slides, querying MySQL, and emailing results via natural language voice commands. Uses Flowise AI ReAct agents with function calling, Make.com automation workflows, Google Apps Script, and FastAPI backend. Built with React.js frontend, all code generated by AI tools. AI-readable: https://www.tigzig.com/ai/posts/how-to-build-ai-action-agents-beyond-chat-with-voice-agents.md - [How to update Excel, Google Sheet and backend Databases with Natural Language commands with Voice Agents](https://www.tigzig.com/post/how-to-update-excel-google-sheets-and-databases-with-ai-voice-agents) - Tags: voice-ai, database-ai Part 2 implementation guide for AI voice action agents. Hands-on 45-minute video showing how to set up Flowise ReAct agents and Make.com webhooks to update Excel, Google Sheets, and databases via voice commands. Covers two go-live scenarios: Flowise native UI and full custom voice bot UI. Deployable source code on GitHub produces a functional voice bot. Integrates with 1000+ platforms via Make.com connectors. AI-readable: https://www.tigzig.com/ai/posts/how-to-update-excel-google-sheets-and-databases-with-ai-voice-agents.md - [How to use AI Assisted Coding Tools like Claude Dev and Cursor AI to develop LLM Apps with natural language commands. And deploy to open internet.](https://www.tigzig.com/post/build-ai-voice-action-agent-app-in-react-js-in-natural-language) - Tags: voice-ai, ai-coders Part 4: using AI-assisted coding tools (Claude Dev VS Code extension and Cursor AI) to build LLM voice agent apps with natural language instructions. Demonstrates building a React.js voice bot with voice-to-text, chat completion, and text-to-speech components, then deploying to Vercel. Covers GitHub-to-Vercel deployment pipeline, multilingual support, and API endpoint routing to Flowise LLM agents. AI-readable: https://www.tigzig.com/ai/posts/build-ai-voice-action-agent-app-in-react-js-in-natural-language.md - [Meet REX-1: Your Realtime AI Analytics Agent System (Web Version)](https://www.tigzig.com/post/rex1-your-realtime-ai-analytics-agent-system-web-version) - Tags: database-ai, text-to-sql REX-1 real-time AI analytics agent built on OpenAI's Realtime API (~$1/min). Connects to data warehouses (AWS, Azure, MySQL) for voice-driven text-to-SQL, statistical analysis, Python charts, web scraping, stock technical charts, and reporting automation. Backend uses Flowise AI agents, Make.com workflows, and custom FastAPI servers. Includes 90-minute build guide video, non-realtime free tier with voice input, and detailed architecture walkthrough. AI-readable: https://www.tigzig.com/ai/posts/rex1-your-realtime-ai-analytics-agent-system-web-version.md - [GenAI App | LLM Analytics Assistant: Simplifying Data Transformation & Insights. AWS & Azure MySQL DW Example](https://www.tigzig.com/post/genai-llm-app-analytics-assistant-aws-azure-mysql) - Tags: database-ai, text-to-sql LLM analytics assistant app demonstrating data transformation and analysis on AWS MySQL with million-to-10M-row datasets. Covers creating customer profiles, summary tables, merging data via natural language instructions through Flowise AI platform. Details architecture with modular FastAPI processing server, model selection trade-offs (GPT-3.5 at ~$1 for 478 queries over 10 hours), cost optimization strategies, and split workflow approaches to minimize LLM token ingestion costs. AI-readable: https://www.tigzig.com/ai/posts/genai-llm-app-analytics-assistant-aws-azure-mysql.md - [VOICE MODE - Querying & Analyzing Data with Custom GPT AWS - Azure Data Warehouse](https://www.tigzig.com/post/voice-mode-query-analyze-database-aws-azure-custom-gpt) - Tags: voice-ai, custom-gpt, database-ai Demonstration of ChatGPT voice mode for querying and analyzing an Azure MySQL data warehouse via Custom GPT. Shows inserting conditional fields, creating distributions from calculated fields, generating charts, creating summary tables, merging datasets, and table operations via voice commands. Applications include senior leadership voice dashboards, ad-hoc query support, and rapid data transformations. Part 2 of the AWS/Azure data warehouse series. AI-readable: https://www.tigzig.com/ai/posts/voice-mode-query-analyze-database-aws-azure-custom-gpt.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 - [Building Machine Learning Models with ChatGPT - Part 2: Modeling Process Listing & EDA](https://www.tigzig.com/post/build-machine-learning-model-with-chatgpt-exploratory-data-analysis-eda) - Tags: custom-gpt, database-ai Part 2 of building ML models with ChatGPT: getting detailed modeling process documentation and exploratory data analysis (EDA). Shows how prompting ChatGPT to share process steps, results, plots, and distributions before model building produces comprehensive EDA output. Demonstrates that specific instructions yield specific outputs, with video walkthrough of the iterative prompt refinement process. AI-readable: https://www.tigzig.com/ai/posts/build-machine-learning-model-with-chatgpt-exploratory-data-analysis-eda.md - [Build Machine Learning Model with ChatGPT prompts: Random Forest example.](https://www.tigzig.com/post/build-machine-learning-model-chatgpt) - Tags: custom-gpt, database-ai Building a Random Forest propensity model entirely through ChatGPT prompts: data preprocessing, model building, validation, decile tables, feature importance, and scoring code generation. Covers tips for managing GPT limits (start with low complexity: 30 trees, depth 3), avoiding overfitting, using Google Colab T4 GPU for intensive tasks, and data security (anonymize PI data, use scrambled data). Includes five sequential base prompts for replication. AI-readable: https://www.tigzig.com/ai/posts/build-machine-learning-model-chatgpt.md ## Related Topics - [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) - [Portfolio & Quantitative Analysis](https://www.tigzig.com/ai/tags/portfolio-quants.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/database-ai.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