# 3. Evaluation

1. ### Create a New Channel

<figure><img src="/files/oCJAeEdnTKkR87DhJyd3" alt=""><figcaption><p>Create a New Channel for your Proposed Challenge</p></figcaption></figure>

Since the default channel is designed to be a draft channel and it's private, you should create a new channel on imean builder, and then move all the tasks you want to include in the challenge to that channel.

<figure><img src="/files/xLZ5qFzyd5Khl9Zl4wfI" alt=""><figcaption><p>Move the Tasks to the Created Channel</p></figcaption></figure>

2. ### Create a Challenge bonded with that Channel

Then you can create a challenge on WebCanvas platform and connect it with the channel in step 1.

<figure><img src="/files/asufDNPnjBoiYXnmQF9A" alt=""><figcaption><p>Create a Challenge and Connect it with the Channel</p></figcaption></figure>

3. ### Export the Data and Run the Evaluation
   1. Check out our GitHub repository for the complete user story on running online evaluation after you set up a challenge. <https://github.com/iMeanAI/WebCanvas>


---

# 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://webcanvas.gitbook.io/webcanvas-docs/3.-evaluation.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.
