Actions
The Actions tab is where your team approves or rejects the specific capability calls Lira's AI agent could not — or should not — run on its own. It is the human-in-the-loop edge of the Agent Runtime.
Navigate to Support → Actions.
When something lands here
Not every capability call needs your team's attention. Most reads and low-risk writes auto-execute, and many high-stakes operations are confirmed by the customer directly in chat. A run only enters this queue when the policy engine returns mode: "human" for one of two reasons:
- The capability's risk tier is
admin_approve— e.g. an integration write that you have explicitly chosen to require teammate approval for. - An admin override raised an existing capability into a tier that requires human approval.
If a call is blocked outright (insufficient auth, end-to-end-blocked tier), it never reaches this queue — it is refused and the agent escalates differently. You can still see those records under Audit with status blocked.
Approval queue
The Approval Queue tab shows runs in the pending_approval state. A red badge on the tab indicates how many are waiting.
Each card shows:
- Capability — the resource or action the agent wants to call, e.g.
stripe_cancel_subscription,create_linear_issue. - Status badge — pending (amber), approved (blue), running (blue), succeeded (green), failed (red), cancelled (gray).
- Risk tier — why this needed approval in the first place.
- Conversation ID — link back to the chat that triggered the run.
- Timestamp — when the agent requested it.
- Input summary — redacted snapshot of the arguments the agent would pass.
Approving a run
Click Approve. The runtime moves the run to approved, executes the capability, and the status transitions to succeeded or failed depending on the outcome. The result is summarised back in the chat for the customer.
Rejecting a run
Click Reject. The run moves to cancelled and is never executed. The agent receives a signal that it should pursue a different path — typically by escalating the conversation to a teammate.
History
The History tab is a quick view of recent runs, including ones that auto-executed. For the full audit trail across every status and filter, use the Audit tab — it has time-range and capability filters, pagination, and the same redacted input / output summaries.
Action statuses explained
| Status | Meaning |
|---|---|
requested | The agent asked, the engine has not finished evaluating. Rarely visible here. |
pending_approval | Waiting for your team to approve or reject. |
approved | Your team approved; the runtime is about to execute. |
running | The executor is in flight. |
succeeded | Completed successfully. |
failed | The executor threw. The error is in the run's output summary. |
cancelled | A teammate rejected, or the customer declined an in-chat confirmation. |
Runs blocked by policy (insufficient auth, blocked tier) appear in Audit with status blocked and do not surface here.
Tips
Tighten the policy instead of approving the same kind of run twice. If you find yourself rubber-stamping the same capability call every day, the right move is to lower its risk tier in Capabilities. The agent will then handle it autonomously and only the unusual cases come to you.
Use the Audit tab to spot patterns. Frequent failed runs for the same capability often point at an expired integration credential or a schema mismatch — neither of which approval can fix. The error message on the audit record points you at the cause.
A rejected run does not silence the conversation. The chat stays open. Reply directly to the customer, or hand the conversation off to a teammate from the Tickets queue if they need to act outside Lira.