> ## 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. # Playwright AI Test Audit > Run an AI audit of a Playwright suite for a quality score and prioritized fixes, then read the report and track its history. Test Audit produces a 0–100 health score for a Playwright suite, plus prioritized issues with file-level evidence and fix recommendations. Audits run through your AI agent via the [TestDino MCP server](/mcp/overview). Test Audit tab showing score badge, audit metadata, Overview tab with Issues list and Quick Actions sidebar ## Setup Test Audit runs through the [TestDino MCP Server](/mcp/overview). Once MCP is configured, every audit is a single prompt to your AI agent. Follow [MCP Overview](/mcp/overview) to install the server, generate a PAT, and configure your client. Skip this step if MCP is already working in your client. Open the Playwright repo in your IDE so the agent can read your test files. Then send one of these prompts: | Scope | Sample Prompt | | :- | :- | | **Suite** | `Run a TestDino test audit on the full suite.` | | **Feature** | `Run a TestDino audit on the feature.` | | **Spec File** | `Run a TestDino audit on .` | | **Test Case** | `Run a TestDino audit on the test case .` | Critical and High issues are always reported, even outside the chosen scope. Open **AI Insights → Test Audit** in [TestDino ↗](https://app.testdino.com). The new audit appears at the top of the history with the score, issues, and full report. ## Reading the Report ### Audit Score Every audit returns a single **0–100 score**. TestDino computes it from the issues the audit found; the AI agent does not choose the number. The same issues always produce the same score. | Severity | Points per issue | | :- | :- | | Critical | −15 | | High | −8 | | Medium | −3 | | Low | −1 | The score starts at 100, subtracts the points for every issue, and stops at 0. Fixing an issue raises the next audit's score by exactly its points. The **Score Breakdown** card under the score lists each category with its issue counts and the points it costs, so you can see what to fix first. | Band | Score | Meaning | | :- | :- | :- | | **Excellent** | 85–100 | Strong validation, low flake risk, well-structured | | **Fair** | 65–84 | Localized weaknesses; targeted fixes recommended | | **Poor** | 0–64 | Critical gaps in validation, stability, or coverage | Two Critical issues alone place a suite in the Fair band; three put it in Poor. Each audit also receives the previous audit's findings and re-checks them before looking for new issues, so back-to-back audits of an unchanged suite report the same issues and the same score. ### Overview Tab The Overview tab splits the audit into 2 panels side by side: a prioritized **Issues** list on the left and a **Quick Actions** sidebar on the right. #### Issues Each Issue card collapses to a single row with the severity badge, title, category badge, and citation count. Expanding the card reveals 3 blocks: * **Summary**: what the issue is and why it matters. * **Recommendation**: a concrete fix, often a one-line change at a `file:line` reference. * **Evidence**: one or more `file:line` references, each with a short observation. Expanded Issue card showing severity badge, title, category, citation count, Summary, Recommendation, and Evidence with file:line references #### Quick Actions A sidebar listing fixes that apply to the whole test suite rather than to one issue, with the count shown in the header. Suggestions are free-text and do not carry severity, category, or evidence metadata. Quick Actions sidebar listing lightweight improvement suggestions with file:line references ### Full Report Tab The Full Report tab renders the complete markdown audit document. Use the **Download** button to save it as a `.md` file for pull-request reviews or wikis. Full Report tab with title row, Download button, Executive Summary, and Category Snapshot table | Section | Contents | | :- | :- | | **Executive Summary** | 2–3 sentences: top finding, what changed since the previous audit, trend direction | | **Category Snapshot** | Issue counts grouped by category | | **Test Composition** | Breakdown of tests by type (Full Flows, Interactions, Render Checks, Page Loads, Accessibility, Other) | | **Audit Coverage** | Folders scanned and bounded counts for Critical/High patterns | | **Findings by Severity** | Issues grouped by severity | | **Critical & High Issue Map** | Each cluster, why it matters, strongest evidence | | **Recommendations** | Quick Wins, Medium Effort, Deep Refactors | ## Categories and Severity ### Issue Categories Each finding is tagged with one of 9 categories. | Category | What It Flags | | :- | :- | | **Surface-Level Tests** | Tests only check page load or basic UI presence, not real behavior | | **Missing Validation** | An action runs but the important outcome is never asserted | | **Flaky or Unstable** | Hardcoded waits, race conditions, shared state, order-dependent steps | | **Hard to Maintain** | Brittle selectors, repeated `.first()`, no fixtures or page objects | | **Missing Scenarios** | Gaps in error, empty-state, mobile, accessibility, or modal coverage | | **Organization & Ownership** | Unowned `test.skip` or `test.fixme`, weak tagging, quarantine bloat | | **Setup & Configuration** | Retries hiding flakes, weak CI artifacts, risky worker isolation | | **Duplication & Overlap** | Multiple weak variants that should collapse into one stronger test | | **General Issues** | Findings that do not fit the categories above | ### Severity Levels | Level | Definition | | :- | :- | | **Critical** | Broken product behavior can ship, or confidence in a major area is invalidated | | **High** | Widespread reliability or validation weakness across multiple files or features | | **Medium** | Important but localized issue | | **Low** | Narrow cleanup | A scope with more than 50% surface-level tests is automatically reported as Critical. ## Audit History Past audits are stored per project and shown in the picker at the top of the Test Audit tab. Audit history dropdown listing past audits with score badge, audit name, branch, timestamp, and pagination controls * **Navigate**: use the `<` and `>` arrows, or open the dropdown to jump to any audit. * **Pagination**: 10 audits per page. * **Select**: click any past audit to load its Overview and Full Report. * **Delete**: the trash icon removes the selected audit. This cannot be undone. * **Re-run**: ask your AI agent for a new audit at any time. New reports are added to history without overwriting previous ones. ## Related Cross-run failure categorization and patterns Connect AI agents to TestDino All MCP tool specifications Per-run failure categorization Per-case AI diagnosis AI controls and access tokens This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.