Anthropic engineer's retrospective: Scaling a test impact analysis service under the pressure of agentic coding
Agentic coding is straining CI. Here’s how we scaled test impact analysis at Anthropic
AI BriefingAn Anthropic engineer wrote about scaling a test impact analysis service under the pressure of agentic programming. Claude wrote approximately 80% of the code, the number of tests grew 10x, and CI jobs increased 25x within six months. The article reviews three temporary patches, which lasted only 70 days, 29 days, and less than a day respectively: scaling up, sharding by package, and daily restarts. The team ultimately spent three weeks redesigning the system into a horizontally scalable architecture using statelessness, in-memory storage, and a journal, and recommends capacity planning for 25x the load within two quarters.
Source: Claude: Blog · claude.com