---
type: "Evidence Item"
title: "Inside OpenAI’s in-house data agent"
description: "How OpenAI built an in-house AI data agent that uses GPT-5, Codex, and memory to reason over massive datasets and deliver reliable insights in minutes."
resource: "https://openai.com/index/inside-our-in-house-data-agent"
tags: ["appendix-iii", "deployment", "openai"]
timestamp: "2026-01-29"
category: "deployment"
publisher: "OpenAI"
cope_score: 96
confidence: 0.9
---

# Inside OpenAI’s in-house data agent

# Claim

How OpenAI built an in-house AI data agent that uses GPT-5, Codex, and memory to reason over massive datasets and deliver reliable insights in minutes.

# Relevance

Appendix III, section four: enterprise deployment evidence

# Oracle Verdict

OpenAI is describing a frontier or production capability that pushes directly on the thesis. The important signal is not the marketing language; it is the widening set of tasks now being routed through model-driven execution rather than ordinary software or headcount.

# Metadata

* Publisher: OpenAI
* Category: deployment
* Sector: Software engineering
* Capability: Frontier model release and benchmark movement
* Cope score: 96
* Confidence: 0.9

# Related Concepts

* [Live evidence index](index.md)
* [Thesis](../thesis.md)

# Citations

[1] [Inside OpenAI’s in-house data agent](https://openai.com/index/inside-our-in-house-data-agent)