---
type: "Evidence Item"
title: "Unrolling the Codex agent loop"
description: "A technical deep dive into the Codex agent loop, explaining how Codex CLI orchestrates models, tools, prompts, and performance using the Responses API."
resource: "https://openai.com/index/unrolling-the-codex-agent-loop"
tags: ["appendix-iii", "vendor", "openai"]
timestamp: "2026-01-23"
category: "vendor"
publisher: "OpenAI"
cope_score: 74
confidence: 0.9
---

# Unrolling the Codex agent loop

# Claim

A technical deep dive into the Codex agent loop, explaining how Codex CLI orchestrates models, tools, prompts, and performance using the Responses API.

# Relevance

Appendix III, section two: vendor threshold and platform capability evidence

# Oracle Verdict

This is a lower-to-mid strength vendor signal for the capability register. It does not prove displacement on its own, but it records another platform step that can later show up as workflow automation, procurement change, or organisational dependency.

# Metadata

* Publisher: OpenAI
* Category: vendor
* Sector: Software engineering
* Capability: Autonomous software engineering and computer-use agents
* Cope score: 74
* Confidence: 0.9

# Related Concepts

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

# Citations

[1] [Unrolling the Codex agent loop](https://openai.com/index/unrolling-the-codex-agent-loop)
