Inside OpenAI’s in-house data agent
📰 OpenAI News
OpenAI built an in-house AI data agent to quickly answer high-impact data questions using natural language and contextual understanding
Action Steps
- Identify high-impact data questions that require quick and accurate answers
- Develop a custom AI data agent using tools like Codex, GPT-5, Evals API, and Embeddings API
- Integrate the agent with existing data and workflows to provide contextual understanding
- Train the agent to continuously learn and improve with every interaction
- Use the agent to answer data questions and provide insights across various functions, including engineering, data science, and finance
Who Needs to Know This
Data scientists, engineers, and product managers at OpenAI benefit from the agent's ability to provide fast and accurate insights, enabling them to make informed decisions and drive business growth
Key Insight
💡 A custom AI data agent can be a powerful tool for surfacing insights and driving business growth by providing fast and accurate answers to high-impact data questions
Share This
🤖 OpenAI's in-house AI data agent helps teams answer high-impact data questions in minutes, not days! 💡
Key Takeaways
OpenAI built an in-house AI data agent to quickly answer high-impact data questions using natural language and contextual understanding
Full Article
# Inside OpenAI’s in-house data agent | OpenAI
[Skip to main content](https://openai.com/index/inside-our-in-house-data-agent#main)
[](https://openai.com/)
* [Research](https://openai.com/research/index/)
* Products
* [Business](https://openai.com/business/)
* [Developers](https://openai.com/api/)
* [Company](https://openai.com/about/)
* [Foundation(opens in a new window)](https://openaifoundation.org/)
Log in[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
* Research
* Products
* Business
* Developers
* Company
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)Login
OpenAI
Table of contents
* [Why we needed a custom tool](https://openai.com/index/inside-our-in-house-data-agent#why-we-needed-a-custom-tool)
* [How it works](https://openai.com/index/inside-our-in-house-data-agent#how-it-works)
* [Context is everything](https://openai.com/index/inside-our-in-house-data-agent#context-is-everything)
* [Built to think and work like a teammate](https://openai.com/index/inside-our-in-house-data-agent#built-to-think-and-work-like-a-teammate)
* [Moving fast without breaking trust](https://openai.com/index/inside-our-in-house-data-agent#moving-fast-without-breaking-trust)
* [Agent security](https://openai.com/index/inside-our-in-house-data-agent#agent-security)
* [Lessons learned](https://openai.com/index/inside-our-in-house-data-agent#lessons-learned)
* [Same vision, new tools](https://openai.com/index/inside-our-in-house-data-agent#same-vision-new-tools)
January 29, 2026
[Engineering](https://openai.com/news/engineering/)
# Inside OpenAI’s in-house data agent
By Bonnie Xu, Aravind Suresh, and Emma Tang
Loading…
Share
Data powers how systems learn, products evolve, and how companies make choices. But getting answers quickly, correctly, and with the right context is often harder than it should be. To make this easier as OpenAI scales, we built **our own bespoke in-house AI data agent** that explores and reasons over our own platform**.**
Our agent is a custom internal-only tool (not an external offering), built specifically around OpenAI’s data, permissions, and workflows. We’re showing how we built and use it to help surface examples of the real, impactful ways AI can support day-to-day work across our teams. The OpenAI tools we used to build and run it ([Codex](https://openai.com/index/introducing-codex/), [our GPT‑5 flagship model](https://openai.com/index/introducing-gpt-5-2/), the [Evals API(opens in a new window)](https://platform.openai.com/docs/guides/evals), and the [Embeddings API(opens in a new window)](https://platform.openai.com/docs/guides/embeddings)) are the same tools we make available to developers everywhere.
Our data agent lets employees go from question to insight in minutes, not days. This lowers the bar to pulling data and nuanced analysis across all functions, not just by our data team. Today, teams across Engineering, Data Science, Go-To-Market, Finance, and Research at OpenAI lean on the agent to answer **high-impact data questions.** For example, it can help answer how to evaluate launches and understand business health, all through the intuitive format of natural language. The agent combines Codex-powered table-level knowledge with product and organizational context. Its continuously learning memory system means it also improves with every turn.
In this post, we’ll break down why we needed a bespoke AI data agent, what makes its code-enriched data context and self-learning so useful, an
[Skip to main content](https://openai.com/index/inside-our-in-house-data-agent#main)
[](https://openai.com/)
* [Research](https://openai.com/research/index/)
* Products
* [Business](https://openai.com/business/)
* [Developers](https://openai.com/api/)
* [Company](https://openai.com/about/)
* [Foundation(opens in a new window)](https://openaifoundation.org/)
Log in[Try ChatGPT(opens in a new window)](https://chatgpt.com/)
* Research
* Products
* Business
* Developers
* Company
* [Foundation(opens in a new window)](https://openaifoundation.org/)
[Try ChatGPT(opens in a new window)](https://chatgpt.com/)Login
OpenAI
Table of contents
* [Why we needed a custom tool](https://openai.com/index/inside-our-in-house-data-agent#why-we-needed-a-custom-tool)
* [How it works](https://openai.com/index/inside-our-in-house-data-agent#how-it-works)
* [Context is everything](https://openai.com/index/inside-our-in-house-data-agent#context-is-everything)
* [Built to think and work like a teammate](https://openai.com/index/inside-our-in-house-data-agent#built-to-think-and-work-like-a-teammate)
* [Moving fast without breaking trust](https://openai.com/index/inside-our-in-house-data-agent#moving-fast-without-breaking-trust)
* [Agent security](https://openai.com/index/inside-our-in-house-data-agent#agent-security)
* [Lessons learned](https://openai.com/index/inside-our-in-house-data-agent#lessons-learned)
* [Same vision, new tools](https://openai.com/index/inside-our-in-house-data-agent#same-vision-new-tools)
January 29, 2026
[Engineering](https://openai.com/news/engineering/)
# Inside OpenAI’s in-house data agent
By Bonnie Xu, Aravind Suresh, and Emma Tang
Loading…
Share
Data powers how systems learn, products evolve, and how companies make choices. But getting answers quickly, correctly, and with the right context is often harder than it should be. To make this easier as OpenAI scales, we built **our own bespoke in-house AI data agent** that explores and reasons over our own platform**.**
Our agent is a custom internal-only tool (not an external offering), built specifically around OpenAI’s data, permissions, and workflows. We’re showing how we built and use it to help surface examples of the real, impactful ways AI can support day-to-day work across our teams. The OpenAI tools we used to build and run it ([Codex](https://openai.com/index/introducing-codex/), [our GPT‑5 flagship model](https://openai.com/index/introducing-gpt-5-2/), the [Evals API(opens in a new window)](https://platform.openai.com/docs/guides/evals), and the [Embeddings API(opens in a new window)](https://platform.openai.com/docs/guides/embeddings)) are the same tools we make available to developers everywhere.
Our data agent lets employees go from question to insight in minutes, not days. This lowers the bar to pulling data and nuanced analysis across all functions, not just by our data team. Today, teams across Engineering, Data Science, Go-To-Market, Finance, and Research at OpenAI lean on the agent to answer **high-impact data questions.** For example, it can help answer how to evaluate launches and understand business health, all through the intuitive format of natural language. The agent combines Codex-powered table-level knowledge with product and organizational context. Its continuously learning memory system means it also improves with every turn.
In this post, we’ll break down why we needed a bespoke AI data agent, what makes its code-enriched data context and self-learning so useful, an
DeepCamp AI