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

# AI in TestDino for Playwright Testing

> AI-powered failure classification, pattern detection, and fix recommendations.

TestDino uses AI on your test run data to classify failures, detect patterns across runs, and recommend fixes. Connect your own assistants through MCP when you want the same data in chat.

## Quick Reference

| Feature                | Where                            | Page                                                                 |
| :--------------------- | :------------------------------- | :------------------------------------------------------------------- |
| Failure classification | Test runs, test cases, dashboard | [AI Failure Analysis](/platform/playwright-ai-failure-analysis)      |
| Failure patterns       | AI Insights                      | [AI Failure Analysis](/platform/playwright-ai-failure-analysis)      |
| Per-test analysis      | Test case AI Insights            | [Test Case AI Insights](/platform/playwright-test-cases/ai-insights) |
| Error grouping         | Test runs, analytics             | [Error Grouping](/guides/playwright-error-grouping)                  |
| Test Audit             | Project AI                       | [AI Test Audit](/platform/playwright-ai-test-audit)                  |
| MCP                    | Claude, Cursor, ChatGPT          | [MCP Overview](/mcp/overview)                                        |
| Agent setup            | Docs + prompts                   | [AI Onboarding](/ai-onboarding)                                      |
| Playwright Skill       | Coding agents                    | [Playwright Skill](/ai/playwright-skill)                             |

<Note>
  AI features are on by default. Toggle them in [Project Settings → AI Features](/platform/project-settings#ai-features). Changes apply from the next test run. Providers do not train on customer content: [AI data handling](/data-privacy/security-compliance#ai-data-handling).
</Note>

## Failure classification

Every failed test gets a category and confidence score.

<img src="https://tdstorageus.blob.core.windows.net/public/docs/ai-and-automation/overview/ai-kpi-tiles.webp" alt="AI failure categorization KPI tiles showing error variants, categories, and failure patterns" />

| Category      | Meaning                                               |
| :------------ | :---------------------------------------------------- |
| Actual Bug    | Consistent failure that points to a product defect    |
| UI Change     | Selector or DOM change broke a test step              |
| Unstable Test | Intermittent failure that passes on retry             |
| Miscellaneous | Setup, data, or CI issue outside the categories above |

Classification shows on [Test run AI Insights](/platform/playwright-test-runs/ai-insights) and [Test case AI Insights](/platform/playwright-test-cases/ai-insights). Correct a misclassification from the feedback form on a test case.

## Patterns and analysis

| Signal              | What it shows                                                          |
| :------------------ | :--------------------------------------------------------------------- |
| Persistent failures | Tests failing across multiple runs in the window                       |
| Emerging failures   | Tests that started failing recently                                    |
| Regressions         | Tests that passed recently and fail again                              |
| Per-test analysis   | Category, confidence, recommendations, historical insight, quick fixes |

<img src="https://tdstorageus.blob.core.windows.net/public/docs/ai-and-automation/overview/ai-insights.webp" alt="AI Insights panel showing failure category, confidence score, recommendations, and quick fixes" />

Treat AI recommendations as guidance. Validate before you change product or test code. Full cross-run view: [AI Failure Analysis](/platform/playwright-ai-failure-analysis).

## Error grouping

AI groups similar errors by message, stack trace, and failure location (assertion, timeout, element not found, network, JavaScript, browser).

<video controls loop preload="metadata" aria-label="AI insights error analysis table with filtering by variant, category, and pattern" poster="https://tdstorageus.blob.core.windows.net/public/docs/ai-and-automation/overview/ai-insight-poster.jpg" src="https://tdstorageus.blob.core.windows.net/public/docs/ai-and-automation/overview/ai-insight.mp4" />

Selecting a KPI tile filters the error analysis table. Learn more about clustering in [Error Grouping](/guides/playwright-error-grouping).

## MCP and docs for agents

| Path                                                                                                      | Use when                                                               |
| :-------------------------------------------------------------------------------------------------------- | :--------------------------------------------------------------------- |
| [MCP Overview](/mcp/overview)                                                                             | The assistant needs live runs, failures, and flaky tests               |
| [OpenClaw](/integrations/communication/openclaw)                                                          | You want the same MCP tools from Slack, Telegram, Discord, or WhatsApp |
| [llms.txt](https://docs.testdino.com/llms.txt) / [llms-full.txt](https://docs.testdino.com/llms-full.txt) | The assistant needs docs context only                                  |
| [AI Onboarding](/ai-onboarding)                                                                           | You want the full agent setup path and starter prompt                  |

<CardGroup cols={2}>
  <Card title="AI Onboarding" icon="robot" href="/ai-onboarding">
    Connect an agent with MCP, CLI, or docs
  </Card>

  <Card title="AI Failure Analysis" icon="brain" href="/platform/playwright-ai-failure-analysis">
    Cross-run classification and patterns
  </Card>

  <Card title="TestDino MCP" icon="plug" href="/mcp/overview">
    Query live test data from an assistant
  </Card>

  <Card title="AI Test Audit" icon="clipboard-check" href="/platform/playwright-ai-test-audit">
    Audit suite quality and coverage gaps
  </Card>
</CardGroup>