# 3.1 Evaluation and Post Interview

{% tabs %}
{% tab title="✓  INSTRUCTIONS & DELIVERABLE" %}
Plan another evaluation to test your live chatbot using the **think-aloud protocol** with at least six people. While you did a basic functional test (code testing) earlier, this evaluation will help you determine if the chatbot is fully usable *and engaging for people*. Prepare a few prompts for participants to complete the main tasks your chatbot supports. For example, you could ask them, "How would you go about reviewing a glossary of terms in our *Chemistry Bot* to prepare for a quiz?". By observing the interaction and any comments from the participant you will gain insight. Be sure to record your findings promptly. Be sure to evaluate the conversation flow and the quality of the chatbot messages and feedback. 

Follow up this evaluation with an informal **post interview** of participants to get feedback on the overall effectiveness of your solution in addressing your chosen health issue. You want to learn as much as you can while using people's time wisely and respectfully.

[***Thinking Aloud*** **from Nielsen Norman Group**](https://www.nngroup.com/articles/thinking-aloud-the-1-usability-tool/).

**❏ Deliverable**\
A document or slide that summarizes the results of your user experience evaluation.
{% endtab %}

{% tab title="★  RUBRIC" %}

| ✓-  Below Standard                                                                                                           | ✓  At Standard                                                                                                             | ✓+  Above Standard                                                                                                                                                          |
| ---------------------------------------------------------------------------------------------------------------------------- | -------------------------------------------------------------------------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| The evaluation was completed but did demonstrate a clear effort to understand the user's experience while using the chatbot. | The evaluation and conclusions demonstrate an intentional process to improve the chatbot that led to some useful insights. | The evaluation was exceptionally detailed and the conclusions were insightful, leading to identified improvements that should make the user experience noticeably improved. |
| {% endtab %}                                                                                                                 |                                                                                                                            |                                                                                                                                                                             |
| {% endtabs %}                                                                                                                |                                                                                                                            |                                                                                                                                                                             |


---

# 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.idew.org/project-chatbot/project-instructions/3-evaluate-and-refine-solution/3.1-evaluation-and-post-interview.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.