> ## 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.

<Callout icon="book-open" color="#3B82F6">
  **What you'll learn**

  * How AI classifies test failures into categories (Bug, UI Change, Unstable, Misc)
  * How failure patterns and error grouping work across runs
  * How to connect AI assistants to your test data via MCP
</Callout>

TestDino uses AI across the platform to classify failures, detect patterns, and recommend fixes. Every AI feature works on real execution data from your test runs.

## In this section

The AI & Automation section pairs AI analysis inside the product with ways to connect your own AI agents and automate reporting.

| Page                                                      | Use it to                                                              |
| :-------------------------------------------------------- | :--------------------------------------------------------------------- |
| [AI Onboarding](/ai-onboarding)                           | Connect an AI agent to TestDino with MCP, the CLI, and starter prompts |
| [TestDino MCP](/mcp/overview)                             | Let assistants query live test runs, failures, and flaky tests         |
| [OpenClaw](/integrations/communication/openclaw)          | Ask TestDino about failures from Slack, Telegram, Discord, or WhatsApp |
| [Playwright Skill](/ai/playwright-skill)                  | Give coding agents expert Playwright guidance in your repo             |
| [AI Insights](/platform/playwright-ai-failure-analysis)   | Review AI failure classification and patterns across runs              |
| [Automated Reports](/guides/automated-playwright-reports) | Schedule PDF summaries on a daily, weekly, or monthly cadence          |

## AI features in this page

Each AI capability below works on real execution data and is explained in detail further down.

| Feature                                           | Where                            | What it does                                                  |
| :------------------------------------------------ | :------------------------------- | :------------------------------------------------------------ |
| [Failure Classification](#failure-classification) | Test runs, test cases, dashboard | Labels failures as Bug, UI Change, Unstable, or Misc          |
| [Failure Patterns](#failure-patterns)             | AI Insights, error grouping      | Identifies persistent and emerging failures across runs       |
| [Test Case Analysis](#test-case-analysis)         | Individual test cases            | Provides root cause, recommendations, and quick fixes         |
| [Error Grouping](#error-grouping)                 | Test runs, analytics             | Groups similar errors by message and stack trace              |
| [MCP Integration](#mcp-integration)               | AI assistants                    | Connects Claude, Cursor, and other AI tools to your test data |

<Note>
  **Note**

  All AI features are enabled by default. Disable individual features or all AI analysis from [Project Settings](/platform/project-settings#ai-features). Changes apply from the next test run.

  AI runs on enterprise AI providers that do not train their models on customer content. See [AI data handling](/data-privacy/security-compliance#ai-data-handling).
</Note>

## Failure Classification

Every failed test receives an AI-assigned category with a confidence score.

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

| Category      | Meaning                                                             |
| :------------ | :------------------------------------------------------------------ |
| Actual Bug    | Consistent failure indicating a product defect. Fix first.          |
| UI Change     | Selector or DOM change broke a test step. Update locators.          |
| Unstable Test | Intermittent failure that passes on retry. Stabilize or quarantine. |
| Miscellaneous | Setup, data, or CI issue outside the above categories.              |

Classification appears in:

* [Test run AI Insights](/platform/playwright-test-runs/ai-insights) tab
* [Test case AI Insights](/platform/playwright-test-cases/ai-insights) panel

<Tip>
  **Tip**

  Correct misclassifications through the feedback form on any test case. This improves future analysis.
</Tip>

## Failure Patterns

AI Insights identifies how failures behave across recent runs.

### Persistent Failures

Tests failing across multiple runs in the selected window. These are high-impact, recurring problems.

<img src="https://testdinostr.blob.core.windows.net/docs/docs/ai-insights/persistent-failures.webp" alt="Persistent failures table showing tests failing across multiple runs" />

### Emerging Failures

Tests that started failing recently and are appearing again. Catch regressions early.

<img src="https://testdinostr.blob.core.windows.net/docs/docs/ai-insights/emerging-failures.webp" alt="Emerging failures table showing recently appearing test failures" />

Pattern types also include:

* **New Failures**: tests that started failing within the selected window
* **Regressions**: tests that passed recently but now fail again
* **Consistent Failures**: tests failing across most or all recent runs

See [AI Insights](/platform/playwright-ai-failure-analysis) for the full cross-run view.

## Test Case Analysis

For each failed or flaky test, AI provides a detailed breakdown.

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

| Section                 | What it provides                               |
| :---------------------- | :--------------------------------------------- |
| Category and Confidence | AI label with confidence score                 |
| Recommendations         | Primary evidence and likely cause              |
| Historical Insight      | Behavior across recent runs (new or recurring) |
| Quick Fixes             | Targeted changes to try first                  |

<Warning>
  **Warning**

  AI-generated recommendations are guidance, not definitive solutions. Validate suggestions before implementing them.
</Warning>

See [Test Case AI Insights](/platform/playwright-test-cases/ai-insights) for details.

## Error Grouping

AI groups similar errors by message text, stack trace patterns, and failure location.

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

Error types include:

* Assertion Failures
* Timeout Issues
* Element Not Found
* Network Issues
* JavaScript Errors
* Browser Issues

Selecting any KPI tile (variant, category, or pattern) filters the error analysis table to matching tests.

See [Error Grouping](/guides/playwright-error-grouping) and [Error Analytics](/platform/analytics/errors) for details.

## MCP Integration

Connect Claude Code, Cursor, or Claude Desktop to your TestDino workspace through the [MCP server](/mcp/overview). Assistants query real test data, investigate failures, and suggest fixes using the same AI classification and patterns described above.

See [TestDino MCP Overview](/mcp/overview) for setup and [Tools Reference](/mcp/tools-reference) for all 12 available tools.

To query TestDino from a chat app instead of an IDE, [OpenClaw](/integrations/communication/openclaw) wraps the same MCP server as a bot for Slack, Telegram, Discord, and WhatsApp.

## Feed TestDino Docs to an AI Assistant

To give ChatGPT, Claude, Cursor, or any LLM full context on TestDino in one paste, use the [llms.txt spec](https://llmstxt.org/) bundles. Both files are regenerated on every docs deploy.

| File              | Purpose                                                                                                                      | URL                                                      |
| :---------------- | :--------------------------------------------------------------------------------------------------------------------------- | :------------------------------------------------------- |
| Index             | Page-by-page index with descriptions                                                                                         | [llms.txt](https://docs.testdino.com/llms.txt)           |
| Full content      | Full markdown of every docs page                                                                                             | [llms-full.txt](https://docs.testdino.com/llms-full.txt) |
| Per-page markdown | Append `.md` to any docs URL for the raw markdown source, e.g. [/mcp/overview.md](https://docs.testdino.com/mcp/overview.md) | `https://docs.testdino.com/<path>.md`                    |

Copy-paste prompt:

```
Read https://docs.testdino.com/llms-full.txt as the authoritative reference
for TestDino. Use it to answer my questions about Playwright test reporting,
CI setup, the TestDino CLI, MCP tools, and platform features.
```

For deeper integration, connect the [TestDino MCP server](/mcp/overview) so the assistant queries live test data instead of just static docs. For the full agent setup path, including starter prompts and `llms.txt` grounding, see [AI Onboarding](/ai-onboarding).

## Related

<CardGroup cols={2}>
  <Card title="AI Onboarding" icon="robot" href="/ai-onboarding">
    Onboard an AI agent with MCP, the CLI, and starter prompts
  </Card>

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

  <Card title="Test Run AI" icon="play" href="/platform/playwright-test-runs/ai-insights">
    Per-run failure categorization and error analysis
  </Card>

  <Card title="Test Case AI" icon="flask" href="/platform/playwright-test-cases/ai-insights">
    Individual test recommendations and quick fixes
  </Card>

  <Card title="TestDino MCP" icon="plug" href="/mcp/overview">
    Connect AI assistants to your test data
  </Card>

  <Card title="OpenClaw" icon="comments" href="/integrations/communication/openclaw">
    Ask TestDino about failures from your chat apps
  </Card>
</CardGroup>