@bcherny: A weird experiment I've been trying the last few weeks is having Claude take over day-to-day maintenance of our apps. S…
Summary
An engineer experiments with Claude AI taking over daily app maintenance routines (crash fuzzing, dead-code removal, etc.), resulting in 388 auto-generated PRs with 180 merged after review, showing promising early results for autonomous maintenance workflows.
View Cached Full Text
Cached at: 08/14/26, 01:32 AM
A weird experiment I’ve been trying the last few weeks is having Claude take over day-to-day maintenance of our apps. Seeing early signs of life that this might be possible.
The setup is straightforward: we have a Slack channel called proj-claude-maintains-apps. In it, Claude Tag runs a bunch of daily routines across iOS, Android, Desktop, web, CLI, and Agent SDK:
- Crash fuzzer: open the app in a simulator and tap around to find ways to crash it, then root cause and fix the crashes
- Dup unifier: scans the codebase for similar-yet-slightly-divergent abstractions, and puts up PRs to unify them
- Dead-code remover: removes statically unreachable code, and adds logging to suspected dead code to check if it’s really dead and if so, remove it the next day
- Abstraction police: fixes leaky abstractions
- a bunch more..
Results have been surprisingly positive. Over the last few weeks, these routines have opened 388 PRs across our repos, 180 of which we merged after Claude Code Review + human review. We’re now thinking about how to streamline this to make merging these kinds of mechanical changes easier.
Claude generally gets these PRs right on the first shot, and if it doesn’t, we ask Claude to tune its routines so it’s better the next day. Sometimes it takes a few days of tuning.
To try a similar workflow, ask Claude Code or Tag, or create some routines directly at https://claude.ai/code/routines. A few of the actual prompts I used below.
Has anyone experimented with similar workflows?
Similar Articles
@hanakoxbt: Anthropic Claude Code engineer: "If you're watching Claude write code, you're the QA tester. That's not what you're pai…
An Anthropic engineer explains how to use Claude Code in a loop to autonomously write code and manage PRs, allowing developers to step away from the keyboard entirely.
The $110/month self-improving pipeline (5 minute read)
A developer shares their $110/month automated pipeline that uses Claude AI to triage, decompose, implement, and test GitHub issues, resulting in 27 merges over 2 weeks with minimal failures.
@bcherny: Claude Code showed that AI could do real work, not just answer questions. Developers hand Claude a feature, come back t…
Anthropic is merging the chat and Cowork features of Claude into a single unified AI product that can maintain context across tasks and work autonomously, rolling out to Pro and Max users over the coming weeks.
@bcherny: Something I have been thinking about: in the past, the best engineers I knew spent a lot of time automating their work …
A thought-provoking thread arguing that automating engineering tasks, especially with AI agents like Claude, is more important than ever. It advocates encoding domain knowledge as infrastructure to accelerate development and enable contributions from non-engineers.
Boris Cherny on Trying to Get Claude Code to Rewrite the Claude App
Boris Cherny, head of Claude Code at Anthropic, discusses an experiment where he directed Claude Tag to rewrite the Claude desktop app in Swift using a Mac VM and pixel-by-pixel comparison, with the task still running after two weeks. John Gruber critiques the approach as fixing technical issues but not the app's fundamental design problems.