OpenAI's internal data agent takes employees from question to insight in minutes
By OpenAI (Bonnie Xu, Aravind Suresh, Emma Tang)Built and shared by OpenAI (Bonnie Xu, Aravind Suresh, Emma Tang), not by me. Summarised from the public sources below. Check them before you rely on a number.
- Who
- OpenAI (Bonnie Xu, Aravind Suresh, Emma Tang)
- Category
- Data & analytics
- Source
- Web
- Dates
- Published 29 Jan 2026 · Found 17 Oct 2026
OpenAI built an internal data agent that teams in engineering, data science, go-to-market, finance and research use to answer data questions. The agent finds the right tables itself, runs SQL and writes notebooks and reports, so an analysis takes minutes instead of days.
What they built
The agent runs on GPT-5.2 over OpenAI's data platform (more than 600 PB across 70,000 datasets). It draws on several layers of context: table usage, human annotations, Codex-generated descriptions of how each table is built in the code, company context from Slack, Google Docs and Notion, and a memory of earlier learnings. The context is updated daily as embeddings. Quality is checked continuously with the Evals API, which compares the agent's SQL results with expected 'golden' queries.
The result
Analyses go from question to insight in minutes instead of days (self-reported). The data platform behind it serves more than 3,500 internal users. No measured time savings are given.
Sources
Novo Nordisk analyst built a text-to-SQL agent that frees up half a full-time role
By Novo Nordisk (Rare Disease Insights & Analytics)
A senior analyst on Novo Nordisk's Rare Disease Insights & Analytics team built an AI assistant himself that answers business questions in plain language directly on healthcare claims and prescription data.
Vercel removed 80% of its data agent's tools and made it 3.5x faster
By Vercel
Vercel had spent months building an internal text-to-SQL agent, d0, with specialised tools and heavy prompt engineering. When the team replaced most of the tools with a sandbox where the agent can run bash commands over the semantic-layer files, the agent became both more accurate and faster.
Uber's finance team asks its data questions in Slack via the AI agent Finch
By Uber (Eddie Huang, Taya Yusuf, Tim Ross)
Uber's FinTech team built Finch, an AI agent in Slack that lets financial analysts and accountants ask for financial data in plain language. Finch writes and runs the SQL query itself and sends the result back, with a link to Google Sheets.
Want this in
your business?
Tell me which case caught your eye. I will tell you straight whether it fits, and what it would take.
Start a conversation →