Run limits: When should an agent stop?
A failed run can still produce useful work. Stripe, Dropbox, and DoorDash use different limits.
Lessons
Short observations for people who build agents.
Each lesson examines a design choice from the agent catalog. Sources describe what teams report. Our observations explain what those reports may mean for other builders.
Human attention: More comments can mean more work
Uber and HubSpot check review comments before engineers see them.
Agent roles: Separate the search from the check
DoorDash changed how its agents divide a code review. Each design exposed a different problem.
Work state: The worker can stop. The work can continue.
A new worker can continue from a saved record.
Tools and context: Two ways to discover tools
Cloudflare and Sentry defer different parts of tool setup until a task needs them.
Workflow control: Some steps do not need a model
Code can control a step that must follow a fixed rule.
Evaluation: Test the agent on your own work
Past tasks and failures can become repeatable checks.
These lessons describe selected cases. They do not establish that one design works best for every team.
Share a resource or public mention, suggest an addition, or correct an existing entry. Pull requests are also welcome.