Asana completed a years-long code migration in 2 weeks with Codex
Codex — Its platform uses AI agents and automations to help customers manage, track, and execute that work. For this project, [Codex helped Asana’s engineers remove Enzyme(opens in a new window)](https://asana.com/inside-asana/migrating-off-enzyme-2-weeks), an outdated testing system that had made the company’s code harder to upgrade. Model and infrastructure costs came to about $12,000. > “Not every years-long project will collapse into weeks.
- Agent or tool
- OpenAI
- Topic
- Software Development
- Reported on
- Case study (OpenAI)
- Added
- 2026-11-11
Why it matters
Coding agents are moving from autocomplete to doing whole tasks: reading a codebase, making a plan and changing many files. This case is a concrete example of where that works in practice. It is one of 221 sightings filed under Software Development on Agent Sightings (number 57 by interest), and one of 25 involving OpenAI.
How you could try it
Here is a reusable prompt, written by us in our own words, that captures the task. Paste it into OpenAI or any similar agent and adjust the details to your situation.
I want a coding agent to plan first, work on a branch, and show me the diff before anything is merged. The tool in the source case was OpenAI.
Tip: Work on a fresh branch, ask for a plan before edits, and review the diff and test results before merging.
Source
Read the original first-hand account on Case study (OpenAI): https://openai.com/index/asana. Our summary is a paraphrase; details are in the source.
Featured in these guides
Built an AI agent? Feature your agent on Agent Sightings, free submission or a featured spot.
Browse more like this
Related sightings
- Warp’s big bet on building open source with GPT-5.5
- A contractor's personal Claude Code agent allegedly ran inside a secure Pentagon system for two months
- Claude Code's 3-word status line reportedly burns 15 to 20% of tokens
- Rocket Money on building agents that fix their own code
- Unify engineers growth by using the right model for every task
- Terminal X matches senior investor judgment 88.6% with GPT-6.1