Playbooks overview | CloudRaker documentation

A playbook gives an AI agent a job to do. You write down the goal, list the outcomes (tasks) you want, and choose which actions the agent is allowed to run. When someone starts a run inside a space, the agent works through the tasks toward that goal — reading files, searching the knowledge graph, and dispatching actions — and pauses for your approval wherever you said it should.

Playbooks are org-level and reusable. A playbook isn’t tied to one space; instead you make it available to a space type, and every space created from that type can run it.

Playbooks (the definitions) are admin-only. The library lives at Playbooks in the sidebar. If you aren’t an admin you’ll see “You need an admin role to manage playbooks.” Running a playbook, on the other hand, happens inside a space and is open to anyone who can contribute there — see Run a playbook.

Two run types — keep them straight

A space has both a Playbooks tab and an Actions tab, and they are not the same thing.

Surface	What it runs
Playbooks tab	An agentic run — the agent pursues a goal across multiple tasks and actions, pausing for approvals.
Actions tab	A single-action run — you run one action over some files, no agent.

This page and the rest of this section are about playbook runs (the Playbooks tab). If you just want to run one action over some files, see Run an action.

The playbooks library

Open Playbooks to see every playbook in your organization. The list has these columns:

Column	What it shows
Name	The playbook’s name; click it to open the editor.
Status	draft, active, or archived.
Space types	The space types this playbook is bound to, or All space types if it isn’t bound to any.
Actions	How many actions the agent may run.
Updated	When the playbook last changed.

Use New playbook to start one. See Build a playbook for the editor walkthrough.

The lifecycle

Every playbook carries a status, and it moves through three states.

Draft

Being built. You edit the goal, tasks, and actions freely. A draft can’t be run in a space yet.

Active

Runnable. You publish a draft by clicking Activate in the editor. Activation validates the playbook first — only a valid playbook (a name plus a title on every task) can be activated. Only active playbooks appear in a space’s run picker.

Archived

Retired. Kept for history but no longer offered for new runs. Archive a playbook from the editor when a process is replaced or no longer needed.

Runs are always started by a person

There is no trigger or scheduling system. A playbook never runs on its own, on a timer, or in response to an event. Every run is started by someone from a space’s Playbooks tab.

Where to go next

Build a playbook

Set the goal, add tasks, choose actions and approvals, then activate.

Run a playbook

Start a run in a space and follow the live timeline.

Approvals and steering

Approve or reject the agent’s proposals, steer it mid-run, and control the run.

Actions

The installable work a playbook’s agent — or you — can run over files.