> For the complete documentation index, see [llms.txt](https://docs.walnutai.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.walnutai.ai/core-features/intelligence-hub/generate-test-cases/smart-recording/generator-mode/web.md).

# Web

**When to Use Web Smart Recording:**\
Use this feature when you want to generate real-time, structured test cases by interacting with a live web application using WalnutAI.

**Supported Platform:** Web Applications

**Execution Type:** AI-driven browser interaction

**Steps to Generate:**

* **Enter Application URL:** Click the **Web** option under **Generate Test Cases → Smart Recording** and enter the web application URL.

<figure><img src="/files/Aw9AnPixqOCo3KzZTmMq" alt=""><figcaption></figcaption></figure>

* **Connect:** Click **Connect** to launch the AI-controlled browser session and establish a live connection.

<figure><img src="/files/UDosmm6eS4gI6hT9OW7t" alt=""><figcaption></figcaption></figure>

* **Provide Prompt:** Enter a prompt describing the functionality (for example: *Login to application*, *Create a new user*, *Validate dashboard widgets*). Walnut AI performs the interactions based on the prompt.&#x20;
  * You don’t need to overthink or write detailed steps to get started. Just give a simple prompt describing what you want to test, and WalnutAI takes it from there. I
  * If something is unclear or missing, WalnutAI doesn’t assume but it asks. Its question-back mechanism helps fill in the gaps by coming back to you with the right questions, making sure every scenario is properly covered.&#x20;
  * It even thinks beyond the obvious to ensure nothing important is left out.

    At any point, you can jump into the chat, clarify things, tweak the flow, or refine the test case. It feels more like a conversation than a process, giving you full control while keeping the effort minimal.
  * When a test case flow has already been created and multiple scenarios need to be handled without breaking it, Smart Recording allows Multiple Test Case Generation while keeping the same flow intact. This ensures all scenarios are covered smoothly, without missing anything.
* **AI Analysis & Recording:** Walnut AI interacts with the application and automatically records structured test steps, captures screenshots, detects validations, and manages page navigations.

<figure><img src="/files/KDyxDqlOIPzFetLtNb1O" alt=""><figcaption></figcaption></figure>

* **Multiple Test Case Generation:** You can generate multiple test cases in the same session by providing additional prompts. Instead of capturing just one path, the given flow is automatically understood and split into multiple test cases. This ensures that different possibilities, conditions, and outcomes are covered in a simple and complete way, so scenario is missed.

<figure><img src="/files/L9pNdf1WbP1idUcb3CFV" alt=""><figcaption></figcaption></figure>

* **Parameter Generation:** Input values such as usernames, passwords, form data, URLs are automatically converted into reusable parameters.

<figure><img src="/files/wqpiAKXOfQ7MTN9sz6Ph" alt=""><figcaption></figcaption></figure>

* **Enhance Coverage:** You can add more prompts to introduce negative scenarios, improve validations, or expand the workflow.
* **Finalize Session:** Click **Disconnect** and then **Done** to complete the recording session.

<figure><img src="/files/HEtJxgkhNWO8hOxR6QNF" alt=""><figcaption></figcaption></figure>

* **Save:** Click **Save** to store the generated test case. If not saved, the generated test case will not be retained.

<figure><img src="/files/v1zdT0Y3uIhZsttMwoYV" alt=""><figcaption></figcaption></figure>

{% hint style="info" %}
**Result:** Saved **Test Cases** will appear in the **Test Case Module** reflected accordingly.
{% endhint %}


---

# 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.walnutai.ai/core-features/intelligence-hub/generate-test-cases/smart-recording/generator-mode/web.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.