# Gate an AI Agent Release Against a Baseline

**Use case:** 

Compare current AI-agent runs with a previous model or release. Detect reliability, quality, latency, cost-per-success, and margin regressions before production rollout.

## Input

```json
{
  "runs": [
    {
      "id": "run-101",
      "success": true,
      "costUsd": 0.04,
      "revenueUsd": 0.2,
      "latencyMs": 1200,
      "qualityScore": 92,
      "version": "1.1",
      "model": "model-a"
    },
    {
      "id": "run-102",
      "success": true,
      "costUsd": 0.05,
      "revenueUsd": 0.2,
      "latencyMs": 1350,
      "qualityScore": 89,
      "version": "1.1",
      "model": "model-a"
    },
    {
      "id": "run-103",
      "success": false,
      "costUsd": 0.03,
      "revenueUsd": 0,
      "latencyMs": 2400,
      "qualityScore": 55,
      "version": "1.1",
      "model": "model-a"
    }
  ],
  "baselineRuns": [
    {
      "id": "run-001",
      "success": true,
      "costUsd": 0.06,
      "revenueUsd": 0.2,
      "latencyMs": 1700,
      "qualityScore": 84,
      "version": "1.0",
      "model": "model-a"
    },
    {
      "id": "run-002",
      "success": false,
      "costUsd": 0.05,
      "revenueUsd": 0,
      "latencyMs": 2900,
      "qualityScore": 62,
      "version": "1.0",
      "model": "model-a"
    }
  ],
  "thresholds": {
    "successRateDropPoints": 5,
    "qualityDropPoints": 5,
    "latencyIncreasePercent": 20,
    "costPerSuccessIncreasePercent": 20,
    "marginDropPoints": 5
  }
}
```

## Output

```json
{
  "releaseDecision": {
    "label": "Release decision",
    "format": "string"
  },
  "healthScore": {
    "label": "Health score",
    "format": "number"
  },
  "status": {
    "label": "Status",
    "format": "string"
  },
  "metrics": {
    "label": "Performance metrics",
    "format": "object"
  },
  "regressions": {
    "label": "Regressions",
    "format": "array"
  },
  "byVersion": {
    "label": "Versions",
    "format": "array"
  },
  "byModel": {
    "label": "Models",
    "format": "array"
  },
  "recommendations": {
    "label": "Recommended actions",
    "format": "array"
  },
  "checkedAt": {
    "label": "Checked",
    "format": "string"
  }
}
```

## About this Actor

This example demonstrates how to use [AI Agent Performance Auditor](https://apify.com/wintry_nutmeg/ai-agent-performance-auditor.md) with a specific input configuration. Visit the [Actor detail page](https://apify.com/wintry_nutmeg/ai-agent-performance-auditor.md) to learn more, explore other use cases, and run it yourself.


## How to integrate an Actor?

If asked about integration, you help developers integrate Actors into their projects.
You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready.
This Task's input is already configured above — use it as-is rather than inventing a new one.

- **AI agents and MCP clients** — the [Apify MCP server](https://docs.apify.com/integrations/mcp.md) at `https://mcp.apify.com` (remote, streamable HTTP, OAuth on first use).
- **Agentic workflows and local Actor development** — [Agent Skills](https://apify.com/.well-known/agent-skills/index.json) with the [Apify CLI](https://docs.apify.com/cli/docs.md): `npm install -g apify-cli`, then `apify login`.
- **JavaScript/TypeScript projects** — the official [JS/TS client](https://docs.apify.com/api/client/js/docs.md): `npm install apify-client`.
- **Python projects** — the official [Python client](https://docs.apify.com/api/client/python/docs.md): `pip install apify-client`.
- **Any other language** — the [REST API](https://docs.apify.com/api/v2.md).

For full API examples (JavaScript, Python, CLI, MCP, OpenAPI), see this Task's Actor page: https://apify.com/wintry_nutmeg/ai-agent-performance-auditor.md

For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt).