# Evaluate a Prompt

Imagine that you're developing an AI feature for a SaaS product and you wrote a prompt for it. You have done "vibe checks" and found that it seems to do a pretty good job. But thousands of people will use it once it's out in the wild, so you need to actually *prove* that it will perform consistently.

That's called Evaluation, or Evals for short—and Entry Point AI can help.

The first thing you need to do is take your prompt and turn it into a Template.


---

# 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.entrypointai.com/guides/evaluate-a-prompt.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.