Meta turned engineers’ judgment into agent skills

Meta engineer Tommy Tran wrote senior performance engineers' reasoning into AI agent skills, cutting diagnosis time from hours to minutes while people still approve production changes.

Meta, the company behind Facebook and Instagram, relied on a few senior engineers to find and fix code that wastes computing power across its servers. Tommy Tran, a software engineer at Meta, built an internal platform of AI agents that investigates these problems and proposes fixes. He described the design to Bill Doerrfeld of LeadDev, a publication for engineering leaders.

• Tran built the agent skills by sitting with senior efficiency engineers and recording the checks they run, the signals they trust and the order they investigate in.
• Stable tools for reading and changing systems are kept separate from the skills, so expertise can change without rebuilding the platform.
• Diagnosis time fell from about 10 hours to about 30 minutes, according to Meta's engineering blog as cited in the article.
• The agents produce a fix ready for review, and a human engineer approves anything that changes production.

An engineering team that wants AI agents to do expert work could start by interviewing its experts and writing their order of investigation into agent instructions. This is an inference and is not the author's claim. The piece rests on one Meta engineer's account of his own project.

Derived by Working Surface from the article; more in the Playbook. Source line: I build skills by sitting with senior efficiency engineers and codifying how they actually reason: the checks they run, the signals they trust, the order they investigate in

6 October 2026: as AI agents take on more of the work, teams are writing down expert judgement for agents, keeping juniors next to reviewers, and building views that let a person check agent output.