> 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.

# Approvals, steering, and run controls

The assistant drafts and proposes; **you decide what to approve**. This page
covers the approval cards, steering the agent between steps, and the run
controls. For the run page layout and timeline, see
[Run a playbook](/playbooks/run-a-playbook).

## Approval gates

When a run reaches a gate you set on an action (see
[Build a playbook](/playbooks/build-a-playbook)), its status becomes **Waiting
for approval** and an **approval card** appears inline above the timeline,
badged **Approval needed**. There are two kinds.

### Before action (pre-approval)

Labelled **Before action**. Shown before the agent dispatches the action:

* the agent's **rationale** for what it's about to do;
* **Documents to include** — checkboxes; you can drop files the agent shouldn't
  use;
* **Proposed parameters** — the action's payload, which you can edit.

Choose **Approve** to let it run, or **Reject** to send it back.

### Output review (post-approval)

Labelled **Output review**. Shown after the action produces a result, so you can
check it before it's committed. It lists the source documents and any
**artifacts**. An embeddable artifact opens a fullscreen review surface (for
example, an extraction table) where you inspect or edit before approving —
saving changes there only saves your table edits; the agent resumes when you
approve. The approve button reads **Approve & resume agent**.

Approving an extraction output "adds the extracted records to Data, with every
extracted field marked approved." The records land in the space
[Data](/data/records) tab.

<img src="https://fdr-prod-docs-files-public.s3.us-east-1.amazonaws.com/cloudraker.docs.buildwithfern.com/9db189e8419bc395fd382e14a60e6ccb0f3fe2fab8f6af08565c90377c839d09/docs/assets/images/guide/playbooks/approval-card.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=AKIA6KXJSKKNFOCF7G4B%2F20260726%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260726T051844Z&X-Amz-Expires=604800&X-Amz-Signature=8bf5a869379664c257515bf74b96d6562f33dcee4690fbebe0dccf2e88641522&X-Amz-SignedHeaders=host&x-amz-checksum-mode=ENABLED&x-id=GetObject" alt="An 'Approval needed' card for the Invoice extraction action labelled Output review, showing the agent rationale, the source documents, and the Reject and 'Approve & resume agent' buttons" />

### Rejecting

To reject, add a note — **"Add a note so the agent can adjust."** — and confirm.
The agent uses your note to retry or adjust its approach.

**Who approves:** anyone with enough access to the space who's looking at the
run. An approval is a single decision on the card, not a request routed to a
named person. (Contributing to a space is what grants the ability to decide;
see [Members and roles](/admin/members-and-roles).)

<a id="steering" />

## Steering the agent

At the bottom of a live run is the **steering composer**: **"Add guidance for
the next agent step."** Type your guidance and click **Steer**. It applies
**between** the agent's steps — helper text reads "Guidance applies between agent
steps." — and your message appears in the timeline as your event. Once the run
finishes the composer is disabled ("This run has finished and no longer accepts
guidance.").

<a id="run-controls" />

## Run controls

For a live run, the controls sit in the header.

* **Pause** / **Resume** — pause the agent and pick it back up. A paused run
  shows **Resume**.
* **Stop** — opens a confirm dialog ("Stop this run?" — "The agent will stop
  after the current operation. A downstream action may continue running.").
  Confirming marks the run **cancelled**.
* **More run controls** (the **⋯** menu) — **Skip current action** when Waiting
  for approval, or **Skip running actions** when Waiting for action. Skipping
  cancels the in-flight action(s) so the run can move on.

<img src="https://fdr-prod-docs-files-public.s3.us-east-1.amazonaws.com/cloudraker.docs.buildwithfern.com/0539a4df4539abdba484e46ff886d9f8f0238353f012040c565075b6e72ce331/docs/assets/images/guide/playbooks/run-controls-menu.png?X-Amz-Algorithm=AWS4-HMAC-SHA256&X-Amz-Content-Sha256=UNSIGNED-PAYLOAD&X-Amz-Credential=AKIA6KXJSKKNFOCF7G4B%2F20260726%2Fus-east-1%2Fs3%2Faws4_request&X-Amz-Date=20260726T051844Z&X-Amz-Expires=604800&X-Amz-Signature=f64e62c4e8ceb83bb6f55d1f7c49455bf882e06dd69f1a68357ca3f2f1046bcd&X-Amz-SignedHeaders=host&x-amz-checksum-mode=ENABLED&x-id=GetObject" alt="The run header with the Pause and Stop buttons and the More run controls menu open showing 'Skip running actions'" />

## Where to go next

#### [Run a playbook](/playbooks/run-a-playbook)

The run page, statuses, timeline, and comments.

#### [Build a playbook](/playbooks/build-a-playbook)

Set which actions pause for approval and behind which tasks.