Skip to main content
Original: Simon Willison · 22/02/2026

​
Summary

Simon Willison discusses the concept of Codex, explaining its components and how it functions as OpenAI’s software engineering agent.

​
Key Insights

“Codex is OpenAI’s software engineering agent, available through multiple interfaces.” — Introduction to Codex and its role in the OpenAI ecosystem.
“The harness, in turn, is shaped around how the model plans, invokes tools, and recovers from failure.” — Explanation of the relationship between the Codex model and its harness.
“Codex models are trained in the presence of the harness.” — Insight into the training process of Codex models.

​
Topics

​
Full Article

22nd February 2026 - Link Blog How I think about Codex. Gabriel Chua (Developer Experience Engineer for APAC at OpenAI) provides his take on the confusing terminology behind the term “Codex”, which can refer to a bunch of of different things within the OpenAI ecosystem: In plain terms, Codex is OpenAI’s software engineering agent, available through multiple interfaces, and an agent is a model plus instructions and tools, wrapped in a runtime that can execute tasks on your behalf. […] At a high level, I see Codex as three parts working together: Codex = Model + Harness + Surfaces […] Model + Harness = the Agent Surfaces = how you interact with the Agent He defines the harness as “the collection of instructions and tools”, which is notably open source and lives in the openai/codex repository. Gabriel also provides the first acknowledgment I’ve seen from an OpenAI insider that the Codex model family are directly trained for the Codex harness: Codex models are trained in the presence of the harness. Tool use, execution loops, compaction, and iterative verification aren’t bolted on behaviors — they’re part of how the model learns to operate. The harness, in turn, is shaped around how the model plans, invokes tools, and recovers from failure.

Introducing the Codex app

Simon Willison · explanation · 72% similar

Use subagents and custom agents in Codex

Simon Willison · how-to · 71% similar

[AINews] Is Harness Engineering real?

Swyx · explanation · 69% similar
Originally published at https://simonwillison.net/2026/Feb/22/how-i-think-about-codex/#atom-everything.