Claude just discovered workflows. Charlie started there.
Claude just discovered workflows. Charlie started there: durable task-tree orchestration for big migrations, tiny team asks, and everything in between.
Start with one useful job, review the setup PR, and expand only after the results are clear.
Most software onboarding confuses completion with value. Create an account. Connect every integration. Click “next” six times. Land in an empty dashboard. The product tour is over; the customer is still on their own.
That model works poorly for software that will operate inside an engineering team. Access is necessary, but access alone is not a role. If software will take initiative around repositories, issues, or team workflows, engineers need to understand what job it owns, when it should act, where its work will appear, and what it must not do.
That is why the best onboarding flow for a Daemon looks less like a setup wizard and more like a pull request.
The idea applies beyond Charlie. Agentic software should start with one useful job, make the operating policy easy to inspect, and expand only after the team sees useful results.
For Charlie, the quickest path is to start with a simple, high-value Daemon from the catalog. The catalog covers common under-owned work such as pull request metadata, failing checks, stale docs, dependency updates, and Linear issue hygiene. Pick the narrow role that removes a real maintenance burden for the team.
For a Daemon, the onboarding flow is short:
.agents/daemons/<daemon-id>/DAEMON.md for the repo, and opens a setup pull request.The setup PR gives the team something concrete to inspect, merge, observe, and revise. Trust grows from a role that wakes for the right reasons and leaves reviewable work behind.
Agents create work. Daemons do the rest.
Ask Charlie to recommend one simple catalog Daemon for your project and open the setup PR. If Charlie is not connected to the repository yet, install the GitHub App: https://docs.charlielabs.ai/installation