Software & DevOpsDone with custom-built or unnamed agent Sep 11, 2026
Run an AI software factory that opens, reviews, and merges PRs
A guide to building agents that open, review, and merge pull requests.
- What They Did
- The guide breaks a software factory into five stages: intake, isolation, tools, verification and a merge gate. It draws on published setups from Stripe, Spotify, Shopify and Ramp. It gives configs for each stage, including an issue filter, git worktrees per agent, a shared MCP tool block, a screenshot-verification skill and tiered merge rules. A human reviews at the end.
- How It Went
- Microsoft's dotnet/runtime data shows agent PRs merging 67.9% of the time against 87.1% for engineers, and 55.1% when fully autonomous. Review capacity becomes the bottleneck, and proven results are mostly mechanical migrations.
- Worth Knowing
- Build the gates before the fleet, and start with one gate where agents cause the most rework. Worktrees start empty, with no .env, dependencies or free port, and non-interactive runs don't clean up after themselves.
Try it yourself with custom-built or unnamed agent
Set up a workflow for the repository [repo name] where an agent picks up issues labeled [label], opens a pull request with a fix and tests, and a second agent reviews it. Write the configuration and a short guide for how it runs. Do not enable automatic merging yet; show me the merge rules you propose and wait for my approval.