{
  "doc": {
    "id": "ui-coverage/work-with-ai-agents",
    "title": "Work with AI agents | Cypress UI Coverage Documentation",
    "description": "Use AI assistants with UI Coverage and Cypress Cloud MCP: pull coverage scores and untested elements from recorded runs, tune reports for clearer signal, and review coverage deltas alongside passing tests.",
    "section": "ui-coverage",
    "source_path": "/llm/markdown/ui-coverage/work-with-ai-agents.md",
    "version": "e8e7f9bceab232ff57cc6f1a0949a5f7e6ca8ec6",
    "updated_at": "2026-06-09T16:19:42.744Z",
    "headings": [
      {
        "id": "ui-coverage/work-with-ai-agents#work-with-ai-agents",
        "text": "Work with AI agents",
        "level": 1
      },
      {
        "id": "ui-coverage/work-with-ai-agents#cypress-cloud-mcp",
        "text": "Cypress Cloud MCP",
        "level": 2
      },
      {
        "id": "ui-coverage/work-with-ai-agents#example-prompts",
        "text": "Example prompts",
        "level": 3
      },
      {
        "id": "ui-coverage/work-with-ai-agents#tune-ui-coverage-for-agent-friendly-signal",
        "text": "Tune UI Coverage for agent-friendly signal",
        "level": 2
      },
      {
        "id": "ui-coverage/work-with-ai-agents#governance-when-to-involve-a-human",
        "text": "Governance: when to involve a human",
        "level": 2
      }
    ]
  },
  "chunks": [
    {
      "id": "ui-coverage/work-with-ai-agents#cypress-cloud-mcp",
      "doc_id": "ui-coverage/work-with-ai-agents",
      "heading": "Cypress Cloud MCP",
      "heading_level": 2,
      "content_markdown": "## Cypress Cloud MCP\n\n[Cypress Cloud MCP](/llm/markdown/cloud/integrations/cloud-mcp.md) lets compatible agents query UI Coverage for a run using structured tools.\n\nUse it to turn “something changed in coverage” into a concrete next step: which views regressed, which elements are newly untested, and where to add or restore interactions.\n\n### Example prompts\n\nHere are some example prompts to try out:\n\n> \"Using Cypress Cloud, pull the UI Coverage report for the latest run on this branch. Summarize the overall coverage score, the views with the most untested elements, and list the untested elements on the top view.\"\n\n> \"Get UI Coverage for this run URL. For the view named `/checkout`, list untested interactive elements and suggest which existing spec file is the best place to add a test that exercises them.\"\n\n> \"Use this CSV of our most-used pages based on Google Analytics data and create a matrix of risk where pages with large amounts of user interactions have relatively low UI Coverage. Create an action plan around this to backfill missing coverage in small increments starting from the most urgent work and working backwards.\"\n",
      "section": "ui-coverage",
      "anchors": [
        "cypress-cloud-mcp"
      ],
      "path": "/llm/json/chunked/ui-coverage/work-with-ai-agents.json",
      "token_estimate": 244
    },
    {
      "id": "ui-coverage/work-with-ai-agents#example-prompts",
      "doc_id": "ui-coverage/work-with-ai-agents",
      "heading": "Example prompts",
      "heading_level": 3,
      "content_markdown": "### Example prompts\n\nHere are some example prompts to try out:\n\n> \"Using Cypress Cloud, pull the UI Coverage report for the latest run on this branch. Summarize the overall coverage score, the views with the most untested elements, and list the untested elements on the top view.\"\n\n> \"Get UI Coverage for this run URL. For the view named `/checkout`, list untested interactive elements and suggest which existing spec file is the best place to add a test that exercises them.\"\n\n> \"Use this CSV of our most-used pages based on Google Analytics data and create a matrix of risk where pages with large amounts of user interactions have relatively low UI Coverage. Create an action plan around this to backfill missing coverage in small increments starting from the most urgent work and working backwards.\"\n",
      "section": "ui-coverage",
      "anchors": [
        "example-prompts"
      ],
      "path": "/llm/json/chunked/ui-coverage/work-with-ai-agents.json",
      "token_estimate": 181
    },
    {
      "id": "ui-coverage/work-with-ai-agents#tune-ui-coverage-for-agent-friendly-signal",
      "doc_id": "ui-coverage/work-with-ai-agents",
      "heading": "Tune UI Coverage for agent-friendly signal",
      "heading_level": 2,
      "content_markdown": "## Tune UI Coverage for agent-friendly signal\n\nAgents work best when reports emphasize the surfaces your team cares about. Use [configuration](/llm/markdown/ui-coverage/configuration/overview.md) to shape what appears in Cloud and in MCP responses:\n\n*   Use config [profiles](/llm/markdown/ui-coverage/configuration/profiles.md) for team or owner-based customization,\n*   [Reduce noise](/llm/markdown/ui-coverage/guides/reduce-noise.md) with filters to ignore third-party or out-of-scope ui\n*   Create clear [element identification](/llm/markdown/ui-coverage/core-concepts/element-identification.md) and [grouping](/llm/markdown/ui-coverage/core-concepts/element-grouping.md) so your agent can quickly make correct assumptions about an elements purpose.\n\nYou can also use your agent to help you define and shape your configuration, by referencing the Cypress docs and describing intended changes.\n\nThe goal is the same as for human review: high-signal lists of views and elements tied to ownership and critical flows, not an undifferentiated dump of every control on every page.\n",
      "section": "ui-coverage",
      "anchors": [
        "tune-ui-coverage-for-agent-friendly-signal"
      ],
      "path": "/llm/json/chunked/ui-coverage/work-with-ai-agents.json",
      "token_estimate": 165
    },
    {
      "id": "ui-coverage/work-with-ai-agents#governance-when-to-involve-a-human",
      "doc_id": "ui-coverage/work-with-ai-agents",
      "heading": "Governance: when to involve a human",
      "heading_level": 2,
      "content_markdown": "## Governance: when to involve a human\n\nTreat unexpected coverage movement as a **quality gate on the tests and the UI under test**, not noise to ignore by default.\n\n*   Use [Branch Review](/llm/markdown/ui-coverage/guides/compare-reports.md) to see what changed between runs: new untested elements, new links, or new interactables in the application.\n*   Use [monitoring and the Results API](/llm/markdown/ui-coverage/guides/monitor-changes.md) to watch trends and wire checks into CI.\n*   Use [policies and blocking flows](/llm/markdown/ui-coverage/guides/block-pull-requests.md) when you need explicit thresholds or baselines before merge.\n\nAgents can draft tests, suggest spec placement, or narrate diffs; reviewers should still confirm intent, risk, and whether a drop in coverage is acceptable (for example, after a deliberate scope change). That split keeps velocity while avoiding silent drift in what your suite actually exercises.\n",
      "section": "ui-coverage",
      "anchors": [
        "governance-when-to-involve-a-human"
      ],
      "path": "/llm/json/chunked/ui-coverage/work-with-ai-agents.json",
      "token_estimate": 167
    }
  ]
}