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

# Incident remediation

> Walkthrough — baseline monitor-mode agent investigating production incidents.

Your on-call agent investigates production incidents by searching Sentry and correlating observability data. This recipe shows the simplest useful instrumentation: one run, one guarded tool call, Monitor mode.

**Source:** [incident-remediation-agent.ts](https://github.com/apie-sh/javascript-sdk/blob/main/examples/incident-remediation-agent.ts) · [incident\_remediation\_agent.py](https://github.com/apie-sh/python-sdk/blob/main/examples/incident_remediation_agent.py)

## Scenario

An incident remediation agent receives an alert about elevated error rates. It searches Sentry for related issues and reports findings. You want this traced in Apie before adding guardrails.

## Step 1 — Create the client

Monitor mode is the default — guardrails evaluate but never block.

<CodeGroup>
  ```ts TypeScript theme={null}
  const apie = await Apie.create({
    agent: {
      key: "incident-remediation-agent",
      name: "Incident Remediation Agent",
    },
    runtime: { environment: process.env.NODE_ENV ?? "development" },
    mode: "monitor",
  });
  ```

  ```python Python theme={null}
  apie = Apie.create({
      "agent": {
          "key": "incident-remediation-agent",
          "name": "Incident Remediation Agent",
      },
      "runtime": {"environment": "development"},
      "mode": "monitor",
  })
  ```
</CodeGroup>

## Step 2 — Start a run

One investigation = one run.

<CodeGroup>
  ```ts TypeScript theme={null}
  const run = await apie.runs.start({
    inputSummary: "Investigate production error rate spike",
  });
  ```

  ```python Python theme={null}
  run = apie.runs.start({
      "inputSummary": "Investigate production error rate spike",
  })
  ```
</CodeGroup>

## Step 3 — Instrument the Sentry search

Use `withCanonicalToolAction` to map the Sentry call to consistent metadata:

<CodeGroup>
  ```ts TypeScript theme={null}
  await withCanonicalToolAction(apie, {
    runId: run.id,
    toolName: "sentry.search_issues",
    provider: "sentry",
    actionType: "read",
    resourceType: "incident",
    environment: "production",
    riskLevel: "medium",
    metadata: { service: "api" },
  }, async () => {
    // Perform Sentry search here
  });
  ```

  ```python Python theme={null}
  from apie import with_canonical_tool_action

  with_canonical_tool_action(apie, {
      "runId": run.id,
      "toolName": "sentry.search_issues",
      "provider": "sentry",
      "actionType": "read",
      "resourceType": "incident",
      "environment": "production",
      "riskLevel": "medium",
      "metadata": {"service": "api"},
  }, lambda: None)  # Perform Sentry search here
  ```
</CodeGroup>

## Step 4 — Complete the run

<CodeGroup>
  ```ts TypeScript theme={null}
  await apie.runs.complete(run.id, {
    status: "completed",
    metadata: { outputSummary: "Incident narrowed to release rollback candidate." },
  });
  await apie.flush();
  await apie.shutdown();
  ```

  ```python Python theme={null}
  apie.runs.complete(run.id, {
      "status": "completed",
      "metadata": {"outputSummary": "Incident narrowed to release rollback candidate."},
  })
  apie.flush()
  apie.shutdown()
  ```
</CodeGroup>

### What you'll see

A single run in the dashboard with one tool call (`sentry.search_issues`), action type `read`, resource type `incident`, and your output summary.

## What to try next

1. [Declare capabilities](/boundaries/declare-capabilities) for `sentry.search_issues`
2. Run in [monitor mode](/guardrails/monitor-mode) with deploy/vault scenarios from [Guardrail packs](/recipes/guardrail-packs)
3. Add more tool calls as your agent's capabilities grow

## Next steps

<CardGroup cols={2}>
  <Card title="Platform connectors" icon="building" href="/integrations/platform-connectors">
    Sentry, Datadog, PagerDuty helpers.
  </Card>

  <Card title="Production release gate" icon="rocket" href="/recipes/production-release-gate">
    Pipeline with risky actions.
  </Card>
</CardGroup>