> ## Documentation Index
> Fetch the complete documentation index at: https://agents.concierca.ch/llms.txt
> Use this file to discover all available pages before exploring further.

# Approvals

> Reviewing and resolving actions that agents need your sign-off for.

Approvals are how Concierca AI keeps humans in control. When an agent wants to do something gated — spend money, send something outbound, delete data, save shared knowledge, or advance a mission past a human checkpoint — it pauses and asks first. Nothing gated executes until a person decides.

## When an approval is created

* **Risky tool calls.** Tool calls are classified automatically (outbound, destructive, escalation). Safe calls run directly; risky ones create an approval request and pause the run.
* **Agent Decision Bounds.** Each agent's guardrails (*"ask me before spending more than \$X"*, *"ask me before doing something irreversible"*) — see [Agents](/guide/agents).
* **Mission human-approval steps.** A mission flow can contain explicit approval gates — see [Missions](/guide/missions).
* **Shared saves and proposals.** Agents proposing to save company knowledge, update a skill, or hire an agent.
* **MCP write tools.** MCP servers with *"Require approval for writes"* enabled route write actions through approval.

## Where you decide

| Surface                           | Who                                   | What                                                                                                                                                                                    |
| --------------------------------- | ------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| **Inbox**                         | The addressed user                    | Pending approvals appear inline with an "On approve" card stating exactly which action will run — **Approve** / **Reject** on the spot. See [Inbox](/guide/inbox).                      |
| **Mission › Approvals tab**       | Step approver, mission owner, or lead | Mission approvals with richer options: Approve, Approve with conditions, Reject, Request changes → step, Delegate. See [Missions](/guide/missions).                                     |
| **Telegram**                      | Users with Telegram linked            | Approval requests arrive as Telegram messages with inline buttons; deciding in the app updates the Telegram message and vice versa.                                                     |
| **Approvals page** (`/approvals`) | Company Admins                        | A plain queue of all pending non-mission approvals (request, requester, expiry, full payload) with Approve/Reject. Reachable by URL; day-to-day decisions normally happen in the Inbox. |

## What happens after you decide

* **Approve** — the system executes *exactly* the approved action (the tool and parameters shown in the "On approve" card), nothing more.
* **Reject** — the agent receives a follow-up with your rejection (and reason, where applicable) so it can adjust course.
* Every request has an **expiry**; overdue requests are marked expired.
* Escalations with high priority also raise a **toast notification** in the app the moment they arrive, with an **Open** action jumping to your Inbox.

## Who may decide

* Company Admins can decide any approval.
* Members can decide approvals from agents they can see.
* Mission approvals follow the mission's rules: the step's designated approver, the owner, or a lead.