# How to Use the Single-Prompt Evaluation Feature

This guide walks you through how to test the responses across multiple AI models at one time with a **single question.**

This is useful for testing out which AI model gives the best quality answers for your knowledge base.

Use this tool for quick checks if you only have a couple of simple questions you want to test across different AI models.

***

### Step-by-Step Instructions

#### 1. Open the Evaluation Page

Go to: 👉 <https://app.wonderchat.io/evaluation>

<figure><img src="/files/s5eGYArxl4bpXFFwKckv" alt=""><figcaption></figcaption></figure>

***

#### 2. Select Single-Prompt Mode

On the Evaluation page, choose **Single-Prompt**.

<figure><img src="/files/3EN6dZr7Py1rKOJxOHm8" alt=""><figcaption></figcaption></figure>

***

#### 3. Choose a Chatbot

Select the chatbot you want to test from the dropdown list.

<figure><img src="/files/51s0hrxHW9JJt3jCwdO2" alt=""><figcaption></figcaption></figure>

***

#### 4. Enter Your Prompt

In the prompt input field, type the question or scenario you want to evaluate.\
This can be a real user question, an edge case, or a safety or governance test.

<figure><img src="/files/7Dm05rHPnyv2HjutdL2L" alt=""><figcaption></figcaption></figure>

***

#### 5. Select AI Model(s)

Choose one or more AI models you want to test the prompt against.\
This allows you to compare how different models respond to the same input.

<figure><img src="/files/EooUFJlGXgAlILZFSL8t" alt=""><figcaption></figcaption></figure>

***

#### 7. Review the Results

Responses will appear immediately on the screen.\
You can review each model’s answer to compare accuracy, tone, grounding, and safety behavior.


---

# 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.wonderchat.io/setup-guides/adding-chatbot-workflows-1/how-to-use-the-single-prompt-evaluation-feature.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.