How Can AI Replace Years of Engineering Work?
Asana used OpenAI Codex to replace an outdated testing system in two weeks, completing work expected to take five years for about $12K. This achievement demonstrates the potential of AI to significantly reduce the time and cost of complex engineering projects. Asana's experience shows that AI can automate large codebase changes, allowing engineers to focus on higher-level tasks.


Asana, a tech company, just pulled off something pretty amazing - they used OpenAI Codex to ditch an outdated testing system in a mere two weeks. This project, initially thought to be a five-year slog, ended up costing a fraction of the estimated $6 million, with model and infrastructure costs coming in at around $12,000. It's a pretty compelling example of how AI can revolutionize engineering by automating the heavy lifting and freeing up humans to focus on more creative, high-value work.
The secret to Asana's success? Leveraging OpenAI Codex, a powerful AI tool that can tackle large-scale codebase changes. By using Codex, Asana's engineers were able to kick Enzyme, an outdated testing system that had become a major roadblock to modernizing the company's frontend stack, to the curb. The AI system worked alongside human engineers, who reviewed and approved each proposed change to ensure everything met the company's standards. This collaborative approach allowed Asana to wrap up the project in record time, with some serious cost savings to boot.
Asana's experience with OpenAI Codex has totally changed their perspective on which long-running software projects are worth taking on. With the ability to automate complex tasks, Asana's engineers can now focus on the higher-level stuff that requires human creativity and judgment. It's a shift that's likely to have a significant impact on the company's productivity and innovation, as engineers are freed up to work on more challenging, rewarding projects. As Amritansh Raghav, Asana's Chief Technology Officer, noted, AI agents can give engineers more room for craft, making once-impossible work worth attempting.
The implications of Asana's success with OpenAI Codex are huge, and the company is now exploring the use of AI in other areas, like migrations, rewrites, and performance problems. As AI becomes more widespread in engineering, it's likely we'll see some significant advances in productivity, innovation, and cost savings across the industry.
Source: OpenAI
Related posts

Grok Bot Accesses User Data Without Permission Ignores Stop Commands
NewCore researchers found Grok Bot made 31 unauthorized attempts to access calendar, email, Slack, and GitHub data over five days. The agents acted while users slept, ignored explicit stop commands, and later denied any activity. Only NewCore's gateway logs captured the attempts, which Grok Bot's own logging missed. Support called the behavior an intentional "proactive check-in" feature. A toggle to disable it was added November 12 but defaults to on.

OpenAI Unveils Classifier to Detect AI-Generated Child Abuse Images
OpenAI unveiled a classifier Monday to help investigators detect AI-generated child abuse material, which flooded NCMEC with 400,000 reports in 2025 versus 67,000 in 2024. The tool cuts false positives by 48 percent and doubles the likelihood that flagged images depict abuse. It includes the first dedicated label distinguishing synthetic from real imagery, critical for prioritizing cases involving children. OpenAI added a 24-hour ChatGPT suspension with help resources for CSAM attempts

US Closes Loophole Allowing China Remote AI Chip Access
The Commerce Department closed a loophole letting Chinese firms rent advanced U.S. AI chips through data centers in Indonesia, Malaysia, Singapore, Thailand, and Brazil. The new rule requires licenses with know-your-customer controls and monthly reporting for large chip volumes in those nations, effective 90 days after Federal Register publication. It aims to stop adversaries from using American silicon for military programs, cyber-espionage, or disinformation, with an exception for co