OpenAI details Codex-powered ChatGPT performance workflow
OpenAI says its cloud-based Performance Factory uses Codex agents to investigate ChatGPT performance regressions, propose fixes for engineer review, and check after deployment whether performance returned to baseline. A separate review step tries to disprove proposed diagnoses. OpenAI reports that, in just over three months, its Regression Workflow tracked more than 1,700 investigations and identified more than 600 root causes; in a manual review of 100 root-cause suggestions, 70% were graded as accurate. A secondary Chinese report said about 50 production fixes adopted or referenced an agent’s proposal, while only around 15 pull requests written by Codex were merged with little or no human modification.
The reports describe a production use of coding agents across performance-regression investigation, diagnosis, remediation and verification. The gap between the reported volume of investigations and fixes merged with little modification also shows that engineer review and judgment remained important parts of the workflow.
November 19, 2026
How OpenAI’s Performance Factory keeps ChatGPT fast
Our Codex-powered system automates finding and fixing performance issues.
By Okay Zed and Cyrus Forbes, Members of Technical Staff
The staggering pace of agentic development has made traditional approaches to performance engineering unsustainable. To keep up, we built the Performance Factory, an autonomous system that uses the full capabilities of Codex and our models to find and fix regressions at an unprecedented speed. The Performance Factory, which runs in the cloud and automates investigating and resolving performance problems, enables us to keep pace with the ambition of our roadmap.
#OpenAI#ChatGPT#Codex#Performance Factory#Regression Workflow#perf-forensics