> For the complete documentation index, see [llms.txt](https://docs.testvibe.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.testvibe.com/assistant.md).

# AI Assistant

The Assistant is a project-aware chat, reached from the navigation rail. It can explain a feature, improve Gherkin, generate test code, explore your app and propose new tests, triage a failing run, and navigate you to the right view. Conversations are saved per project, so you can return to earlier threads from the list rail.

![The Assistant view](/files/dRH07lzJ9nzsjEETBks8)

## Ways To Reach It

| Entry point                                               | What it does                                                                                                                                                 |
| --------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------ |
| Navigation rail → Assistant                               | Opens the conversation list and the active chat.                                                                                                             |
| Search bar → "Ask assistant"                              | Sends whatever you typed in the command bar (Ctrl/Cmd+K) as a new conversation.                                                                              |
| ✨ Suggestions menu → **Explore my app and suggest tests** | The Assistant drives a real cloud browser against your site and proposes ready-to-run tests. See below.                                                      |
| Per-view **Ask AI** buttons                               | Runs, Features, and Load results each have an Ask AI button that seeds a conversation with a data-rich summary of the selected run, feature, or load result. |
| **Debug with AI**                                         | On a failed test result, opens the trace viewer with a docked assistant that diagnoses the failure and can fix the test or open a source-code pull request.  |
| **Fix with assistant**                                    | From a failing test result, opens a guided flow that reproduces the failure and proposes a fix.                                                              |

## Explore Your App And Suggest Tests

"Explore my app and suggest tests" is not a list of ideas — every proposed test is already written and has passed a real verification run before it's suggested. Accepting one keeps a ready-to-run test; it does not trigger a fresh generation.

* Behaviors are proposed **as soon as they're verified**, not saved up until the whole session finishes. A validation dialog, an empty-search state, or a "no results found" screen is proposed on its own, with the same priority as a happy-path flow.
* If a session is cut short — it ran out of time or was interrupted — TestVibe keeps everything it already verified instead of discarding the session, and offers a one-click **Continue exploring** card so you can pick up where it left off.

## What To Ask

* "Why did run #25 fail?" — the Assistant reads the run's results and evidence.
* "Tighten the scenarios in NewFeature.feature" — it can propose Gherkin edits.
* "Summarize load test run #31" — or use the Ask AI button on the load result for the same thing with the data pre-attached.
* "Explore my app and suggest tests" — see above.

## Tips

* Quick actions on the empty chat state (grouped under Discover / Generate / Diagnose / Scale & automate) cover the most common starting points.
* Seeded conversations (Ask AI, per-view buttons, quick actions) render as a compact card — an icon, a one-line summary, and a "Show full prompt" link — instead of the raw instruction text. The Assistant still receives the full prompt; the card just keeps the transcript readable. Click "Show full prompt" if you want to edit and resend it to steer the analysis.
* The Assistant works against the currently selected project; switch projects from the header first if needed.

## Related Help

* [Assistant form reference](/reference/forms/assistant.md)
* [Troubleshoot failed generation](/ai-generation/troubleshoot-failed-generation.md)
* [Run failed](/troubleshooting/run-failed.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## 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, and the optional `goal` query parameter:

```
GET https://docs.testvibe.com/assistant.md?ask=<question>&goal=<endgoal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is optional and describes the broader end goal you are ultimately trying to accomplish on behalf of the user. GitBook uses it to tailor the answer towards what is most useful for that goal.

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.