# How to Use the Multi‑Prompt Evaluation Feature

This guide walks you through how to test a chatbot against multiple prompts at once using the **Multi‑Prompt** feature in Wonderchat’s Evaluation tool.

***

### What You’ll Need

* Access to the Wonderchat app
* An existing chatbot
* A CSV or Excel file with a column named **`questions`** (each row will be treated as a test prompt)

***

### Step‑by‑Step Instructions

#### 1. Open the Evaluation Page

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

<figure><img src="/files/QCQ1UPr2HnBAjsIKiD7u" alt=""><figcaption></figcaption></figure>

***

#### 2. Select **Multi‑Prompt** Mode

On the Evaluation page, choose **Multi‑Prompt**.

<figure><img src="/files/krirAGjVkSwV78ze8yyp" alt=""><figcaption></figcaption></figure>

***

#### 3. Choose a Chatbot

Select the chatbot you want to run the test prompts against.

<figure><img src="/files/PDrryMdvDSbA9dkpfI5c" alt=""><figcaption></figcaption></figure>

***

#### 4. Create a New Prompt Set

Click **Create New Set**.

<figure><img src="/files/aIT1Da7YJWSNB6NDHaBh" alt=""><figcaption></figcaption></figure>

***

#### 5. Import Your CSV or Excel File

1. Give your prompt set a clear, descriptive name.
2. Click **Import CSV / Excel**.
3. Select the file you want to upload.

⚠️ **Important:**

* Your file **must** contain a column called **`questions`**.
* Each row in this column will be used as an individual test prompt.

<figure><img src="/files/8qMvOWsB3nQVREHJG0pj" alt=""><figcaption></figcaption></figure>

***

#### 6. Save the Prompt Set

Once the file is uploaded, click **Save prompt set**.

***

#### 7. Run the Evaluation

* You’ll see your prompt set appear in the list below.
* Select one or more **AI models** you want to test against.
* Click **Run** to start the evaluation.

<figure><img src="/files/RKaUlXehDZg04mfzDAyw" alt=""><figcaption></figcaption></figure>

***

#### 8. Download the Results

* Responses will appear in real time as the evaluation runs.
* You don’t need to wait or monitor this step.
* Click the **Download** button in the top‑right corner to export the full results.

***

That’s it! You’ve successfully run a Multi‑Prompt evaluation and exported your results.


---

# 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-multi-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.