# Playground

You can manually enter information for each field under the "Prompt" heading, or simply press "Synthesize" to fill it in for you, along with a synthesized completion. 

<figure><img src="/files/OXIGkddULT1QH1LNNnFJ" alt=""><figcaption></figcaption></figure>

When you have a prompt and a model selected, press Generate.

<figure><img src="/files/k6mcwACYvC9HSyNY4lhW" alt=""><figcaption></figcaption></figure>

For any completion, you can press the info icon (i) to see the exact HTTP endpoint, request, and response. This information is helpful when it's time to move a model into production and makes it straightforward to show developers how to perform the same request in code.

<figure><img src="/files/1BcNb5sYWCoGEaaLWAz4" alt=""><figcaption></figcaption></figure>

Next, we'll talk about inference parameters.


---

# 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/generate-completions/playground.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.