@santtiagom_: Very good article from OpenAI about Harness Engineering and Codex. They explain how they used agents to build an intern…
Summary
This tweet summarizes an OpenAI article on Harness Engineering and Codex, discussing challenges and insights from building a 1M-line internal product using AI agents.
View Cached Full Text
Cached at: 05/17/26, 03:28 AM
Very good article from OpenAI about Harness Engineering and Codex.
They explain how they used agents to build an internal product with ~1M lines of code and what problems arose in the process.
Some interesting ideas: • preventing code generated by agents from degrading over time • using tests and CI as more reliable constraints than prompts • keeping code and documentation readable for agents • how engineers’ work changes when agents start to program
Much of the challenge lies in the system around the model.
Similar Articles
Harness engineering: leveraging Codex in an agent-first world
OpenAI describes an internal experiment building a production software product with zero manually-written code using Codex agents, achieving approximately 10x faster development with 1.5M lines of code written by AI in five months. The team learned that effective agent-driven development requires engineers to focus on systems design, scaffolding, and feedback loops rather than writing code directly.
@bibryam: This OpenAI article is an absolute gold mine for harness engineers. The insight isn’t “AI writes code.” It’s: → how to …
OpenAI shares how its team built a full software product with zero manually-written code using Codex agents, focusing on designing environments and feedback loops for reliable agent operation.
@Av1dlive: 2 OpenAI engineers just gave a masterclass on how to build and ship apps using Codex they spent 16 mins on how Codex tu…
OpenAI engineers showcase Codex as an agent harness for software engineering, capable of reviewing code, splitting work across sub-agents, and running workflows autonomously, effectively turning one person into a full engineering team.
@Potatoloogs: https://x.com/Potatoloogs/status/2057391224592667051
This article deeply analyzes the concept of Agent Harness, which is the engineering infrastructure wrapped around an LLM, including 12 components such as orchestration loops, tool calling, memory systems, context management, etc. The article cites practices from companies like Anthropic, OpenAI, and LangChain, arguing for the critical role of the harness in production-grade AI agents.
How is Codex as a harness for local models?
An article exploring the use of OpenAI's Codex as a harness or tool for running local AI models, discussing its effectiveness and potential.