> For clean Markdown of any page, append .md to the page URL. > For a complete documentation index, see https://docs.cloudraker.com/llms.txt. > For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.cloudraker.com/_mcp/server. # Run a playbook You run a playbook from inside a [space](/spaces/overview). The run page shows what the agent does as it happens — which files it read, which actions it proposed, and where it's waiting on you. Approving, rejecting, steering, and the run controls are covered in [Approvals and steering](/playbooks/approvals-and-steering). This is the space **Playbooks** tab — an agentic run. The space **Actions** tab is different: it runs a single [action](/actions/run-an-action) over some files with no agent. ## Start a run #### Open the space's Playbooks tab and click Run playbook The **Run playbook** picker opens: "Choose a playbook to configure and run in this space." Only playbooks compatible with this space's type appear. If none do, you'll see "No active playbook supports this space type yet." Pick one and click **Continue**. #### Review what the playbook will do The launcher (**Run `{playbook name}`**) previews the run under **What this playbook will do**: a **Tasks** table (Step / Task) and an **Actions and approvals** table. Each action is badged **Approval before running**, **Output review**, or **No approval gate** so you know where it will pause. #### Set file access Under **File access**, choose what the agent can read: **All files in this space**, or **Selected files** (pick them from the list). This bounds the documents the agent works from. #### Start run Click **Start run**. You land on the run detail page, where the agent begins working. The Run playbook launcher for 'Invoice intake' with the Tasks table, the Actions and approvals table, and the File access radio choices ## The run page The run detail page (`/spaces/$spaceId/playbook-runs/$runId`) has four parts: * **Header** — the playbook name and a **status badge**, plus "Started by `{user}` · `{date}` · `{completed}`/`{total}` tasks" and a live activity line. For live runs the run controls live here (see [Approvals and steering](/playbooks/approvals-and-steering#run-controls)). * **Tasks rail** — a **Tasks** progress meter ("`{n}` of `{m}` tasks") and each task with an icon: a **check** for completed, a **lock** for blocked ("Blocked by …"), and a **circle** for ready. Each shows the summary the agent wrote. * **Timeline** — the live activity feed (below). * **Steering composer** — where you add guidance for the agent's next step (covered in [Approvals and steering](/playbooks/approvals-and-steering#steering)). A playbook run detail page for 'Invoice intake' with the header status badge, the timeline of agent events, the Tasks rail on the right, and the steering composer at the bottom ### Statuses The status badge tells you where the run is: | Status | Meaning | | ------------------------ | ----------------------------------------------------------------------- | | **Running** | The agent is working. | | **Waiting for approval** | Paused at an approval gate — a card is waiting for your decision. | | **Waiting for action** | A dispatched action is running. | | **Waiting for you** | A step needs you (for example, a user-triggered browser step). | | **Paused** | You paused the run. | | **Completed** | The run finished. | | **Failed** | The run stopped on an error; a "Run failed" banner shows what happened. | | **Cancelled** | The run was stopped. | The first five are **live** — the page streams updates over a WebSocket. If the connection drops it falls back to polling, and you may see a "Live updates are reconnecting" note. ## The timeline Every event names its **actor** — **Agent** or a person (with their name and avatar) — and what happened. Over a run you'll see: * the run started, completed, failed, or was cancelled; * the agent **reading and searching** files, the knowledge graph, and data (for example "Listed files", "Read a document", "Searched documents", "Searched the knowledge graph", "Queried records"); * an action **proposed**, **dispatched**, **completed**, **failed**, or **skipped**; * approvals requested and decided, and output reviews requested; * **steering** messages you sent; * pause / resume / stop, and browser-session events. A dispatched action shows a **View action run** link into the Actions surface, so you can open that action's own run. A line at the bottom shows what the agent is doing right now ("Agent is working…" or "Waiting for you…"). ## Comments Collaboration on a run happens in **comments** on a run task. You can post a comment, **@mention** teammates, add emoji, use basic formatting, and edit or delete your own comments. This is the place to loop someone in on a run — there is no separate global inbox. ## Browser-control steps A **user-triggered** action (such as a browser-fill step) doesn't get dispatched by the agent — it needs your browser. When the run reaches one, a **browser action card** appears with a **Your step** badge (it becomes **Agent filling** once live): #### Start the browser session Click **Start browser session**. The card shows "Waiting for your browser to connect." Use **Open pairing link** (or **Copy link**) and open it in the Chrome that has the CloudRaker extension installed. #### Let the agent fill the form Once your browser is linked (status **Agent filling**), the agent fills the form in your browser. Review the values it enters. #### Submit it yourself **You submit the form** — the agent doesn't. When it's done the card shows **Done**. If the session expires, use **Start again**. If the step is gated behind tasks, the card shows "Unlocks after: …". You can **Skip this step** until the agent is actively filling. ## When a run finishes There's no single output bundle. A run's results land in their natural homes: approved extraction records go to the space **[Data](/data/records)** tab, files an action generated appear in **[Files](/spaces/files)**, and each dispatched action has its own action run reachable from the timeline's **View action run** links. A failed run shows a "Run failed" banner with the error. ## Where to go next #### [Approvals and steering](/playbooks/approvals-and-steering) Approve or reject the agent's proposals, steer it, and use the run controls. #### [Build a playbook](/playbooks/build-a-playbook) Set the goal, tasks, actions, and approval gates behind a run.