Cricket (ODI/T20) & Tour de France stats from a Custom GPT connected to 3 live databases.
- Amar Harolikar
- Sep 17
- 2 min read
Ask it a natural-language question. It queries the right DB and gives you the answer. It's a live connection to three separately hosted Postgres databases - Supabase, Neon & Aiven.
The GPT dynamically shifts connections to analyze 340 MB of data spanning 2.5 million rows in six tables across the 3 databases - 122-year history for Tour de France, and 22 years for Cricket across 7,596 matches.
𝗧𝗵𝗲 𝗗𝗮𝘁𝗮𝗯𝗮𝘀𝗲𝘀 (𝗟𝗶𝘃𝗲 𝗗𝗮𝘁𝗮)
• 𝘀𝘂𝗽𝗮𝗯𝗮𝘀𝗲_𝗽𝗼𝘀𝘁𝗴𝗿𝗲𝘀 → ODI ball-by-ball (2003→2025) / 1.5M rows
• 𝗻𝗲𝗼𝗻_𝗽𝗼𝘀𝘁𝗴𝗿𝗲𝘀 → T20 ball-by-ball (2005→2025) / 1M rows
• 𝗮𝗶𝘃𝗲𝗻_𝗽𝗼𝘀𝘁𝗴𝗿𝗲s → Tour de France riders + stages (men 1903→2025; women 2022→2025)
𝗪𝗵𝗮𝘁 𝗶𝘁 𝗗𝗼𝗲𝘀
▪️ Computes player stats (runs, strike rate, averages)
▪️ Builds rankings (top scorers, best bowlers, most wins)
▪️ Summarizes Tour history (winners, distance, avg speed)
▪️ Produces charts & run statistical analysis with python
𝗧𝗿𝘆 𝗶𝘁 𝘆𝗼𝘂𝗿𝘀𝗲𝗹𝗳 - 𝘀𝗮𝗺𝗽𝗹𝗲 𝗾𝘂𝗲𝘀𝘁𝗶𝗼𝗻𝘀
The GPT has starter prompts. Ask things like:
▪️ Cricket: 'Top 10 ODI strikers by total runs off the bat, with matches, overs, and run rates per match/over. Add two charts for run rates.'
▪️ Tour de France: 'Show Tour de France winners from 2015–2025 with distance, time, and average speed. Also, chart the riders with 3+ wins in history.'
𝗖𝘂𝘀𝘁𝗼𝗺 𝗚𝗣𝗧 = 𝗽𝗿𝗮𝗰𝘁𝗶𝗰𝗮𝗹 𝗮𝗻𝗮𝗹𝘆𝘁𝗶𝗰𝘀 𝘁𝗼𝗼𝗹
▪️ UI + agent + Python sandbox out of the box. Efficient + cost effective
▪️ Use for automations, report generators, and database applications
▪️ Live examples: app.tigzig.com → GPT section (top menu)
𝗖𝘂𝘀𝘁𝗼𝗺𝗶𝘇𝗲 & 𝗗𝗲𝗽𝗹𝗼𝘆
▪️ 𝗙𝗮𝘀𝘁𝗔𝗣𝗜 𝗯𝗮𝗰𝗸𝗲𝗻𝗱 powers any custom front end, BI tool, or internal app.
▪️ 𝗢𝗽𝗲𝗻-𝘀𝗼𝘂𝗿𝗰𝗲 - repo and docs include architecture, action schema, and deployment steps.
▪️ 𝗘𝘅𝗮𝗺𝗽𝗹𝗲: Custom build - DATS-4 AI suite - app.tigzig.com/analyzer
▪️ 𝗔𝘂𝘁𝗵: Bearer API key in this GPT. OAuth supported for role-based access and RLS (row level security)
𝗟𝗶𝗻𝗸𝘀
• SQL AI Apps: app.tigzig.com-> Database AI & SQL Apps
• Database providers: neon.com, aiven.io, supabase.com
• Cricket data source: cricsheet.org
• Cricksheet data processor : app.tigzig.com/csv-processor
• Tour de France data source: https://github.com/thomascamminady/LeTourDataSet

