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

---

2. Select Multi‑Prompt Mode

On the Evaluation page, choose Multi‑Prompt.

---

3. Choose a Chatbot

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

---

4. Create a New Prompt Set

Click Create New Set.

---

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.

---

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.

---

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.