How an OpenAI team built a product with Codex writing all of the code
A small OpenAI team built an internal beta product starting from an empty repository, with Codex writing the code and humans steering. The post covers how they set up the repository and process for agents.
The problem
The team wanted to find out how far a codebase could go if humans only wrote prompts and reviewed work and never wrote code themselves. That required a repo, docs and checks the agents could navigate reliably.
How they did it
- Started from an empty repo and had Codex CLI generate the scaffold, structure and CI configuration.
- Gave high-level task prompts; Codex opened PRs and ran agent reviews both locally and in the cloud.
- Kept a short AGENTS.md as an entry point and treated a structured docs directory as the system of record.
- Enforced architecture rules with custom linters and ran recurring cleanup to manage technical debt.
- Escalated to humans only when judgment was needed.
Results as reported by OpenAI
- As reported by OpenAI: 'roughly 1,500 pull requests have been opened and merged with a small team of just three engineers'.
- That averaged '3.5 PRs per engineer per day', and the repository grew to 'on the order of a million lines of code'.
- The team estimates it built the product in 'about 1/10th the time' of writing the code by hand.
These figures are as reported by OpenAI in OpenAI engineering blog ↗ (Feb 11, 2026). OpenAI sells the product used here. AgentGid did not measure or independently verify them.
This suits a small team of experienced engineers who can build the scaffolding agents depend on: a structured docs directory, custom linters and CI checks. Expect review and cleanup to take real effort, and the 1,500 PRs and 1/10th-time figures are OpenAI's own reports. Pi (Free, OSS) is a cheaper terminal alternative, though you'd pay your model provider directly.
The agent used here
Similar use cases
Mod almost any PC game with Claude Code and the universal-modder plugin
An open-source GitHub project packages skills, a command-line tool, a shared knowledge base and the fal MCP server so AI coding agents such as Claude Code can mod PC games the use…
The repository ships three worked examples: a Terraria tModLoader weapon and boss pack with sprites made through fal, an Age of Empires II DE civiliz… (as reported by the project's author)
Auto-fix failing CI with the Codex GitHub Action
When your CI workflow fails, a second GitHub Actions workflow runs Codex on the failing commit, asks it to reproduce the failure and make the smallest fix, and opens a pull reques…
Every failed CI run triggers a Codex attempt on the exact failing commit, and any fix is saved as a patch artifact. (as reported by OpenAI)
Porting JustHTML from Python to JavaScript with Codex CLI in an afternoon
Simon Willison gave Codex CLI a handful of high-level prompts to port JustHTML to a dependency-free JavaScript library. He published the repo and a playground.
The library passes 9,200 tests from the html5lib-tests suite. (as reported by Simon Willison)
Guides
JEV for Claude Code: A Second Opinion on Every Command
A viral post says jev-axi screens every command your Claude Code agent runs for a fraction of a cent. We read the repo, TypeSafe's docs and privacy policy: what runs locally, what is sent, how it fails, and how it compares with auto mode.
VoiceStudio: The Free, Local ElevenLabs Alternative
A viral post calls VoiceStudio a 100% free ElevenLabs replacement with 19.4K stars. We checked it against GitHub and the project's own pages: what it does, what is really free, the license catch in the default voice model, and how to plug it into Claude Code or Codex.
Best Claude Code Alternatives in 2026: Open-Source, Cheaper and Multi-Model
The strongest alternatives to Claude Code, grouped by why you are switching: price, model choice, open source or a different workflow. Live usage and prices for each.
AI Coding Agent Pricing Explained: Claude Code, Cursor, Codex and Copilot (2026)
What Claude Code, Cursor, OpenAI Codex, GitHub Copilot and other coding agents really cost: plan prices, usage limits, subscription vs API billing, and how to estimate your monthly bill.