Creating an automation
Open Settings → Automations and click New Automation (or start from a template):- Write the instructions, as you would for a regular task.
- Pick the agent that runs it.
- Set the schedule — a preset, a weekly picker, or a cron expression — and the timezone.
- Leave Fork on to have each run work in its own copy of your cloud environment, or turn it off to run in the main environment, for example to keep dependencies and dev servers up to date for every other task. Changing it later starts a new task on the next run.
Automations require a paid plan — see Pricing.
Templates
The template gallery on the Automations page ships ready-made recurring tasks, maintained as a community catalog that grows over time. A sample of what’s there:- Daily issue triage — scan open GitHub issues every morning: label, prioritize, spawn fixes
- Error monitoring triage — fetch new unresolved Sentry errors and fix the actionable ones
- Cloud log error triage — query GCP or AWS logs for new errors and crashes
- Weekly dependency updates — update dependencies and verify the build still passes
- Sprint automation — pick up ready Linear issues from the current sprint and start coding
- Flaky test detection — mine CI history for flaky tests and verify with targeted reruns
- Stale PR cleanup — nudge, rebase, or close stale pull requests
Managing automations
Each automation can be toggled on/off, force-triggered to run now, edited, or deleted. Runs are recorded in task history, so you can inspect their activity and results.Cron format reference
Cron format reference
Schedules use standard 5-field cron:
minute hour day-of-month month day-of-week.