Anthropic is testing whether its AI model, Claude Code, can handle daily maintenance of the company's own software. In a few weeks, the AI created 388 pull requests, and 180 were merged after human review. According to Boris Cherny, the Anthropic engineer who created Claude Code, the AI has been running daily maintenance on the company's in-house apps for "the last few weeks." Instead of tying up developers with repetitive maintenance work, Claude handles it on its own. Cherny calls the results "surprisingly positive."
Claude runs a battery of specialized maintenance routines, according to Cherny. A "Crash Fuzzer" opens apps in a simulator, taps around randomly to trigger crashes, analyzes the root cause, and creates a fix. A "Dup Unifier" scans the codebase for similar but slightly different abstractions and proposes merging them. The "Dead-Code Remover" strips out statically unreachable code and, for suspicious code, first adds logging so it can check the next day whether the code is actually unused.
Cherny shared some of his prompts in Slack, and there's no elaborate prompt engineering going on. He tells Claude in plain language to start daily routines for crash fuzzing on iOS, Android, and desktop, to use real apps without mocks, to trigger crashes, and to create pull requests with fixes. A Slack screenshot shows how Boris Cherny delegates AI maintenance routines for crash fuzzing, logic bugfixes, dead-code removal, and other tasks using plain-language Slack messages.
Source: thedecoder
