Devin adds recurring scheduled tasks for release notes, QA, and cleanup jobs
Cognition now lets Devin turn a one-off task into a recurring workflow on a schedule. It pushes Devin further from ad hoc sessions toward unattended maintenance jobs, which is useful for teams already trusting it with repetitive repo work.
TL;DR
- Cognition says Devin can now turn a successful one-off task into a recurring job, so teams can schedule work like feature flag cleanup, release notes, and QA instead of rerunning the same prompt manually launch post.
- The company’s product page says scheduled runs are available to all users and are meant for “routine, non-urgent tasks” that can be described once and then repeated on a cadence.
- This pushes Devin beyond ad hoc sessions: Scott Wu said 30% of Devins already start automatically via API or managed flows, and argued scheduled launches move teams closer to “agent-native” dev workflows usage split.
What shipped
Cognition’s launch post frames the feature simply: “run any task once,” then tell Devin to make it recurring. The examples are practical engineering chores rather than greenfield coding: feature flag cleanup, release note generation, and QA runs.
The linked product page adds the missing implementation detail. Users describe the task once, set a cadence such as weekly or every Monday morning, and Devin handles repeat execution and follow-up. Cognition also says scheduled Devins can maintain state between runs, which matters for jobs that build up over time, like summarizing newly merged pull requests or checking for stale flags that were not present last week product page.
Why it matters for agent workflows
The bigger change is operational. Scheduled tasks make Devin less like a chat session and more like background automation for repo and team hygiene. Cognition’s product page also ties the feature to Managed Devins, which run parallel agents in isolated environments, suggesting recurring jobs can fan out into multi-step workflows such as QA sweeps and report generation.
Scott Wu’s usage split gives a snapshot of the transition: this week, he said 70% of Devins were still started by humans through the web app, Slack, or Linear, while 30% were started automatically through the API and managed or scheduled Devins. His examples of where this goes next are concrete: agents kicking off on Sentry or Datadog alerts, continuously running integration tests, and acting as “first-line incident-response.” The launch does not prove Devin can handle all of that yet, but it does add the scheduling primitive needed for unattended maintenance work.