> ## Documentation Index
> Fetch the complete documentation index at: https://help.get-ryze.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Approvals

> The agent finds improvements in your accounts on its own and brings them to you for sign-off — you approve, it applies the change.

Approvals flip the direction of work. Instead of you checking dashboards for problems, the agent continuously researches your connected accounts — SEO and paid — and when it finds something worth fixing, it files a proposal. You review the exact change, approve or reject, and on approval the agent applies it.

Find them under **Approvals** in the sidebar.

<Frame>
  <img src="https://mintcdn.com/ryzeai-5f9aafd5/D5UqALOsthei8CQz/images/approvals-list.png?fit=max&auto=format&n=D5UqALOsthei8CQz&q=85&s=3b9c8183dcdedf79a038e91b11e4ef2a" alt="The Approvals page with a pending proposal and Approve and Reject buttons" width="3110" height="1700" data-path="images/approvals-list.png" />
</Frame>

## What a proposal looks like

Every proposal is specific and grounded in your data — never "consider improving X". Open one to see:

* **Summary** — what's wrong, what it costs you, and why it matters, with real numbers from your accounts.
* **Entity** — the exact account and campaigns the change touches.
* **Proposed changes** — a before/after table of every change the agent wants to make.
* **Evidence** — the data the agent pulled to reach its conclusion.

<Frame>
  <img src="https://mintcdn.com/ryzeai-5f9aafd5/D5UqALOsthei8CQz/images/approvals-detail.png?fit=max&auto=format&n=D5UqALOsthei8CQz&q=85&s=5787619f7d57756809ce4271b240d20c" alt="A proposal with entity, proposed changes as a before and after table, and evidence" width="3110" height="1700" data-path="images/approvals-detail.png" />
</Frame>

## Approve or reject

* **Approve** — the agent applies the change to your account and verifies it landed. The proposal moves to **History**.
* **Reject** — nothing is touched. The agent takes the hint and won't re-file the same proposal.

Use the product filter to see proposals for SEO, paid ads, or everything at once.

## Blocked proposals

Sometimes the agent finds a real problem but can't fix it from its side — a tag that must be installed on your website, a pixel that needs verifying, a platform it has no access to. Those proposals arrive as **Blocked**: the same evidence and proposed changes, plus a blocker note that tells you exactly what to do and where.

<Frame>
  <img src="https://mintcdn.com/ryzeai-5f9aafd5/D5UqALOsthei8CQz/images/approvals-blocked-list.png?fit=max&auto=format&n=D5UqALOsthei8CQz&q=85&s=7f8fa611398d327e37f69e22c4d566cc" alt="A blocked proposal in the list with Acknowledge and Remove blocker actions" width="3110" height="1700" data-path="images/approvals-blocked-list.png" />
</Frame>

<Frame>
  <img src="https://mintcdn.com/ryzeai-5f9aafd5/D5UqALOsthei8CQz/images/approvals-blocked-detail.png?fit=max&auto=format&n=D5UqALOsthei8CQz&q=85&s=c195a6bb06d017fcde88b928b5b88421" alt="A blocked proposal with the blocker note explaining what needs to be fixed and where" width="3110" height="1700" data-path="images/approvals-blocked-detail.png" />
</Frame>

* **Remove blocker** — tell the agent you've resolved the blocker. It re-checks reality before proceeding — if the fix is actually live, the proposal moves forward; if not, it stays blocked and tells you what's still missing.
* **Acknowledge** — you've seen it and will handle it later.

## How proposals are found

The agent runs research on a regular cadence per product, in the background — no setup needed. It only files a proposal when it finds something concrete and worth your attention; quiet accounts produce no noise. Research runs are free — you only spend credits when you approve a fix and the agent applies it (see [Credits & Usage](/agent/credits)).

## Related

<CardGroup cols={2}>
  <Card title="Scheduled Tasks" icon="clock" href="/agent/schedules">
    Point the agent at your own recurring checks.
  </Card>

  <Card title="Credits & Usage" icon="coins" href="/agent/credits">
    How agent runs are billed.
  </Card>
</CardGroup>
