Inside OpenAI’s in-house data agent

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, built specifically around OpenAI’s data, permissions, and workflows. The OpenAI tools we used to build and run it (Codex, our GPT‑5.2 flagship model, the Evals API, and the Embeddings API) are the same tools we make available to developers everywhere. OpenAI’s data platform serves more than 3.5k internal users working across Engineering, Product, and Research, spanning over 600 petabytes of data across 70k datasets. At that size, simply finding the right table can be one of the most time-consuming parts of doing analysis. Our data agent lets employees go from question to insight in minutes, not days. It handles the analysis end-to-end, from understanding the question to exploring the data, running queries, and synthesizing findings. One of the agent’s superpowers is how it reasons through problems. Rather than following a fixed script, the agent evaluates its own progress. If an intermediate result looks wrong, the agent investigates what went wrong, adjusts its approach, and tries again. High-quality answers depend on rich, accurate context. To avoid failure modes, the agent is built around multiple layers of context: metadata grounding, code-level definitions from Spark/Python, and internal knowledge from Slack, Google Docs, and Notion. Furthermore, the agent features a memory system that allows it to save corrections and nuances, ensuring it constantly improves with its users.