# Generate Playwright code

Generate Playwright code when your feature intent is ready and you want a runnable browser test.

The generated code is stored in your repository and can be run from TestVibe.

## Before You Generate

Confirm:

| Check                            | Why it matters                                          |
| -------------------------------- | ------------------------------------------------------- |
| The feature is saved             | Generation uses the repository version of the feature.  |
| The Gherkin is clear             | Better intent produces better code.                     |
| The target site URL is reachable | The runner and generated test need to open the app.     |
| Required secrets exist           | Login and provider keys must be available to workflows. |
| The runner is configured         | GitHub Actions needs a matching runner.                 |

## Steps

1. Open the **Test Suite**.
2. Select the feature you want to generate.
3. Start the generation action from the feature details or test list.
4. Confirm the site URL and options.
5. Keep the default agent and model unless your team has a reason to change them.
6. Start generation.
7. Stay on the generation progress view until it finishes.
8. Open the generated output after success.

## What TestVibe Generates

Generation can create or update:

| Output                     | Purpose                                                        |
| -------------------------- | -------------------------------------------------------------- |
| Playwright test file       | The browser automation that runs the scenario.                 |
| Supporting output          | Helpers, configuration use, or generated metadata when needed. |
| Evidence during generation | Screenshots, section progress, and trace links when available. |
| Repository changes         | Generated files saved back to the selected repository.         |

## Review Before Running

Before running the generated test, check:

* it follows the intended journey
* it uses the right target page
* it verifies the expected result
* it does not depend on private or accidental data
* it does not ignore important setup from the Gherkin

For more detail, see [Read generated output](/ai-generation/read-generated-output.md).

## If The Output Is Not Right

Do not keep regenerating blindly. First improve the feature:

| Problem                     | Better next step                                             |
| --------------------------- | ------------------------------------------------------------ |
| Test clicks the wrong thing | Add visible labels or clearer page context to the Gherkin.   |
| Test misses the assertion   | Add a stronger `Then` step.                                  |
| Test needs setup            | Add `Background`, a prerequisite, or test data instructions. |
| Site could not be reached   | Fix the URL or runner.                                       |
| Provider key is missing     | Add the required secret.                                     |

Then regenerate. See [Regenerate a test](/ai-generation/regenerate-test.md).


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.testvibe.com/ai-generation/generate-playwright-code.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.