{
  "doc": {
    "id": "app/ai/overview",
    "title": "AI in Cypress: test generation, agent skills, and agentic debugging",
    "description": "A map of every AI capability in Cypress: author tests with Cypress Studio and cy.prompt, give AI coding agents real Cypress context with skills and Cloud MCP, and analyze runs with Cypress AI.",
    "section": "app",
    "source_path": "/llm/markdown/app/ai/overview.md",
    "version": "e4f4d57da4cfedd520d3d465137d387fd54b532f",
    "updated_at": "2026-09-08T17:49:12.214Z",
    "headings": [
      {
        "id": "app/ai/overview#ai-in-cypress",
        "text": "AI in Cypress",
        "level": 1
      },
      {
        "id": "app/ai/overview#write-tests-with-ai",
        "text": "Write tests with AI",
        "level": 2
      },
      {
        "id": "app/ai/overview#give-agents-cypress-context",
        "text": "Give agents Cypress context",
        "level": 2
      },
      {
        "id": "app/ai/overview#analyze-and-debug-with-ai",
        "text": "Analyze and debug with AI",
        "level": 2
      },
      {
        "id": "app/ai/overview#what-each-capability-needs",
        "text": "What each capability needs",
        "level": 2
      },
      {
        "id": "app/ai/overview#see-also",
        "text": "See also",
        "level": 2
      }
    ]
  },
  "chunks": [
    {
      "id": "app/ai/overview#write-tests-with-ai",
      "doc_id": "app/ai/overview",
      "heading": "Write tests with AI",
      "heading_level": 2,
      "content_markdown": "## Write tests with AI\n\nBoth options below produce ordinary Cypress code that you can read, edit, and commit. Neither is a black box: `cy.prompt` exposes the generated commands in the Command Log, and Studio writes directly into your spec file.\n\n*   **[Cypress Studio](/llm/markdown/app/guides/cypress-studio.md)** records real interactions in your app and turns them into end-to-end tests. Connected to Cypress Cloud, Studio AI also recommends assertions as you record. Reach for it when you want to author a test by clicking through your app.\n*   **[Generate tests with `cy.prompt`](/llm/markdown/app/guides/ai-test-generation.md)** turns natural language steps into executable Cypress commands, and can keep them working as your UI changes. Reach for it when describing a flow is faster than recording one.\n",
      "section": "app",
      "anchors": [
        "write-tests-with-ai"
      ],
      "path": "/llm/json/chunked/app/ai/overview.json",
      "token_estimate": 156
    },
    {
      "id": "app/ai/overview#give-agents-cypress-context",
      "doc_id": "app/ai/overview",
      "heading": "Give agents Cypress context",
      "heading_level": 2,
      "content_markdown": "## Give agents Cypress context\n\nAn AI coding agent that knows nothing about Cypress writes tests that look plausible and then fail in CI: brittle selectors, arbitrary waits, and assertions that do not retry. These capabilities give it better information to work from.\n\n*   **[Cypress skills for AI agents](/llm/markdown/app/tooling/ai-skills.md)** teach your coding agent to write, review, and explain tests the way an experienced Cypress engineer would. Install them once per project.\n*   **[`cypress tap`](/llm/markdown/app/tooling/cypress-tap.md)** attaches your agent to a running open mode session from the terminal, so it can run a spec and then read the Command Log, the error, and the DOM as the Cypress app shows them. That closes the loop: the agent can verify its own fix instead of reporting pass or fail. The [`cypress-tap` skill](/llm/markdown/app/tooling/ai-skills.md#cypress-tap) packages this workflow so your agent drives it correctly.\n*   **[Cloud MCP](/llm/markdown/cloud/integrations/cloud-mcp.md)** connects your agent to Cypress Cloud so it can read real run results, failures, and [Test Replay](/llm/markdown/cloud/features/test-replay.md) data while you work, rather than guessing at why something failed.\n*   **[Cloud CLI](/llm/markdown/cloud/integrations/cloud-cli.md)** is the scriptable counterpart to Cloud MCP: the same Cloud run data as JSON in the terminal, for agents that work through a shell and for your own automation. The [`cypress-cloud-cli` skill](/llm/markdown/app/tooling/ai-skills.md#cypress-cloud-cli) instructs your agent on how to work through that recorded run and test data to find a failure's root cause.\n",
      "section": "app",
      "anchors": [
        "give-agents-cypress-context"
      ],
      "path": "/llm/json/chunked/app/ai/overview.json",
      "token_estimate": 299
    },
    {
      "id": "app/ai/overview#analyze-and-debug-with-ai",
      "doc_id": "app/ai/overview",
      "heading": "Analyze and debug with AI",
      "heading_level": 2,
      "content_markdown": "## Analyze and debug with AI\n\n*   **[Cypress AI](/llm/markdown/cloud/features/cypress-ai-features.md)** explains failures and summarizes test intent across recorded runs in Cypress Cloud.\n*   **[Work with AI agents in Cypress Accessibility](/llm/markdown/accessibility/work-with-ai-agents.md)** and **[Work with AI agents in UI Coverage](/llm/markdown/ui-coverage/work-with-ai-agents.md)** cover tuning those reports so an agent can act on them, then prompting it to triage findings and plan the work.\n",
      "section": "app",
      "anchors": [
        "analyze-and-debug-with-ai"
      ],
      "path": "/llm/json/chunked/app/ai/overview.json",
      "token_estimate": 77
    },
    {
      "id": "app/ai/overview#what-each-capability-needs",
      "doc_id": "app/ai/overview",
      "heading": "What each capability needs",
      "heading_level": 2,
      "content_markdown": "## What each capability needs\n\n**No AI capability in Cypress requires a paid subscription.** Everything below works on the free [Starter plan](https://www.cypress.io/pricing?utm_source=docs.cypress.io&utm_medium=ai-overview), and some of it never touches Cypress Cloud at all. The exceptions are the agent-ready reports at the bottom of the table, which come with the Cypress Accessibility and UI Coverage solutions rather than with a Cloud plan.\n\nPaying raises limits rather than unlocking capabilities: a paid plan gets you a larger `cy.prompt` execution allowance and higher hourly limits on `cy.prompt` and Studio AI. See [AI usage limits](/llm/markdown/cloud/features/cypress-ai-features.md#Usage-limits) for the numbers.\n\n| Capability | Where it runs | Cypress Cloud account | Paid plan |\n| --- | --- | --- | --- |\n| Cypress Studio recording | Cypress App | Not needed | No |\n| Studio AI assertion suggestions | Cypress App | Free plan works | No |\n| `cy.prompt` | Cypress App | Free plan works | No |\n| Cypress skills for AI agents | Your editor | Not needed | No |\n| `cypress tap` | Your terminal | Not needed | No |\n| Cloud MCP | Your editor | Free plan works | No |\n| Cloud CLI | Your terminal | Free plan works | No |\n| Cypress AI failure and intent summaries | Cypress Cloud | Free plan works | No |\n| Agent-ready accessibility reports | Cypress Cloud | Yes | Included with Cypress Accessibility |\n| Agent-ready coverage reports | Cypress Cloud | Yes | Included with UI Coverage |\n\nThe capabilities that need a Cloud account need one because Cypress Cloud is what routes their AI requests securely, applies your organization's controls, and tracks usage. See [Why do I need a Cloud account?](/llm/markdown/cloud/features/cypress-ai-features.md#Why-do-I-need-a-Cloud-Account)\n\nOrganization admins and owners can turn AI capabilities on or off for everyone in the organization. See [Disabling AI features](/llm/markdown/cloud/features/cypress-ai-features.md#Disabling-AI-features).\n",
      "section": "app",
      "anchors": [
        "what-each-capability-needs"
      ],
      "path": "/llm/json/chunked/app/ai/overview.json",
      "token_estimate": 413
    },
    {
      "id": "app/ai/overview#see-also",
      "doc_id": "app/ai/overview",
      "heading": "See also",
      "heading_level": 2,
      "content_markdown": "## See also\n\n*   [`cy.prompt()`](/llm/markdown/api/commands/prompt.md) - the command reference\n*   [Cypress Studio](/llm/markdown/app/guides/cypress-studio.md)\n*   [Cypress skills for AI agents](/llm/markdown/app/tooling/ai-skills.md)\n*   [`cypress tap`](/llm/markdown/app/tooling/cypress-tap.md)\n*   [Cloud MCP](/llm/markdown/cloud/integrations/cloud-mcp.md)\n*   [Cloud CLI](/llm/markdown/cloud/integrations/cloud-cli.md)\n*   [Cypress AI](/llm/markdown/cloud/features/cypress-ai-features.md) - availability, usage limits, and pricing for every AI capability\n",
      "section": "app",
      "anchors": [
        "see-also"
      ],
      "path": "/llm/json/chunked/app/ai/overview.json",
      "token_estimate": 53
    }
  ]
}