Start an agent as a suggestion and put it on autopilot once it has proven reliable
Teams ask the agent for suggestions, observe its performance, add guidance, and automate it after it has proven reliable.
How Linear used this technique
Read what Linear changed and follow the original sources.
Start an agent as a suggestion and put it on autopilot once it has proven reliable
Linear's teams introduce autonomy gradually: they ask the agent for suggestions, observe its performance, and add guidance, and they put it on autopilot once it has proven reliable. Engineers also get better results by breaking work into small, focused steps for the agent. For an agent check on pull requests, that is a check that comments first and becomes a required check after its record has been read.
- Use it when
- A new agent check, or an agent that opens its own pull requests, is about to become a required gate.
- Before applying it
- Set the promotion bar before the trial starts, such as the share of its findings that people acted on, and keep a person's approval on the merge.
Company Playbooks
- Read Anthropic’s playbookRun only affected tests
- Read DoorDash’s playbookRun build and test in parallel, sharded across CI agents
- Read Linear’s playbookBenchmark the same job on faster hardware
- Read Mastra’s playbookStarSling runners for the slowest test workflow
- Read OpenAI’s playbookRank CI fixes by the minutes they save
- Read Ramp’s playbookMove a CPU-bound test suite to a faster CPU
- Read Shopify’s playbookLet an agent iterate against one CI metric
- Read Spotify’s playbookBuild arm64 on native arm64 runners
- Read Stripe’s playbookRun only the tests a change can reach
- Read Uber’s playbookBuild the merge-queue speculations most likely to be needed