AutomationsScheduled tasks

Run tasks on autopilot

Automations run coding tasks on a schedule. Daily cleanups, weekly dependency updates, nightly test suites. Set it once and let agents handle the rest.

What to automate

What to automate

Put recurring work on autopilot, from maintenance to monitoring.

Daily lint fix

Daily lint fix

Run your linter with auto-fix every morning. Wake up to a clean codebase with no more style nits piling up in PRs.

Weekly dependency updates

Weekly dependency updates

Check for outdated packages, update patch and minor versions, run tests, and get a summary of what changed. Stay current without the busywork.

Nightly test suite

Nightly test suite

Run the full test suite every night. If anything fails, the agent investigates and fixes it before your team starts the next day.

Security reviews

Security reviews

Scan authentication flows, API endpoints, and database queries for vulnerabilities on a recurring schedule. Report findings as GitHub issues.

Code quality sweeps

Code quality sweeps

Identify dead code, unused imports, and redundant logic across your codebase. Keep things lean without manual audits.

Changelog generation

Changelog generation

Generate a changelog from recent commits and merged PRs every week. Formatted, organized, and ready to ship with your release notes.

How it works

How it works

Three steps. No infrastructure. No cron servers to manage.

CreateStep 1

Create

Give your automation a name and a prompt, the same way you'd describe any task. Tell the agent exactly what to do.

ScheduleStep 2

Schedule

Pick a preset like daily, weekly, or weekdays, or write a custom cron expression. Set the timezone and choose your model.

ReviewStep 3

Review

Each run creates a normal task. Review the diff, create a PR, or send feedback, just like any other Capy task.

Powerful scheduling

Powerful scheduling

Flexible scheduling with full control over how and when agents run.

  • Daily, weekly, weekday, and custom cron schedules
  • Build agents for coding or Captain for planning
  • Any AI model available on Capy
  • Full timezone support across all schedules
  • Enable or disable without deleting
  • Complete run history with status tracking
  • Each run is a reviewable task with diffs and PRs
  • Configure base branch per automation
Peeking Capy
FAQ

FAQ

Common questions about Capy automations.

How is an automation different from a regular task?+
An automation is a task that runs on a schedule. Each time it triggers, Capy creates a new task with your prompt, on the branch you configured. You review the output exactly like any other task: check the diff, create a PR, send feedback.
What schedule options are available?+
You can choose from presets (every day, every weekday, every week on a specific day, every N hours, every N minutes) or write a custom cron expression for full control. All schedules respect the timezone you set.
Can I use Captain for automations?+
Yes. You can choose between Build (for direct coding tasks) and Captain (for planning and delegation). Captain is great for recurring analysis, architecture reviews, or multi-step workflows.
What happens if an automation run fails?+
Failed runs appear in the run history with their status. You can review what went wrong, adjust the prompt, and the next scheduled run will try again with your updated instructions.
Can I pause an automation temporarily?+
Yes, just toggle the automation off without deleting it. All configuration is preserved. Toggle it back on whenever you're ready.

Set it and ship it

Put your recurring work on autopilot. Create your first automation in under a minute.

Capy Portal