Asana cleared 5 years of engineering work in 2 weeks with Codex
Asana successfully replaced an outdated testing system in two weeks using OpenAI's Codex, a task previously estimated to take five years and $6 million. The project cost only $12,000 and demonstrated the potential for AI agents to handle large-scale codebase migrations.
Why it matters
This case study highlights a massive shift in software engineering productivity, suggesting that AI can make previously impractical or prohibitively expensive technical debt projects viable.
Using OpenAI Codex, Asana replaced an outdated testing system in two weeks for about $12K.
Calendar weeks to finish work expected to take 5 years
Model and infrastructure cost versus Asana’s ~$6M staffing estimate
Loading… Share In about two weeks, Asana completed work it expected to take five years.
Asana helps teams coordinate work. Its platform uses AI agents and automations to help customers manage, track, and execute that work. Asana brings the same approach to its engineering organization, where people use OpenAI Codex, powered by frontier models, to tackle large codebase changes, then review and approve each proposed change.
For this project, Codex helped Asana’s engineers remove Enzyme, an outdated testing system that had made the company’s code harder to upgrade. Model and infrastructure costs came to about $12,000, compared with Asana’s roughly $6 million estimate for the previous staffing plan.
Get smarter about the news
Sign up free for a feed built around what you actually care about, Dive Deeper research on any story, and the full text of every article.
Create free accountAlready have an account? Sign in