> For the complete documentation index, see [llms.txt](https://docs.otari.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.otari.ai/guides/dashboard/playground.md).

# Playground

The Playground lets you try models directly in Otari, experiment with prompts, and compare two models' answers, with each response's token usage, latency and cost. How its requests are authorized and billed, what it stores, and how attached files and tools behave is in [Admin dashboard](/guides/dashboard/dashboard.md#playground).

## Test a single model

1. From your workspace, open **Playground**.
2. Make sure **Single** is selected.
3. Choose a model from the dropdown below the prompt box.
4. Enter your prompt, or pick one of the suggested **Starting points**.
5. Optionally, open **Tools** to add web search, code execution or MCP servers to the request, and attach files with the paperclip or by dropping them on the page.
6. Press Enter or click the Send button.
7. Review the model's response and its usage and performance information.

## Compare two models

Compare mode sends the same prompt to two models side by side.

1. Click **Compare** at the top of the Playground.
2. Select the two models with the dropdown menus.
3. Enter your prompt in the text box at the bottom.
4. Optionally, open **Tools** to include tools in the request.
5. Submit the prompt to see both models' responses side by side.
6. Compare their answers and performance figures to choose the model that suits you.

## View your history

1. Click **History**.
2. Filter the history by **All**, **Chats** or **Comparisons**.
3. Use **Search history** to find a conversation or comparison.
4. Select an entry to reopen it, or click **View all** for your complete history.

Saved Playground history is visible only to you.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.otari.ai/guides/dashboard/playground.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

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.