> ## Documentation Index
> Fetch the complete documentation index at: https://docs.oumi.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# PROMPTS, PARAMETERS, AND TOOLS

> Give each Playground panel its own system prompt and sampling parameters, and let the models call your tools

Each Playground panel has its own system prompt and sampling parameters, so you can compare settings as well as models. Add the same model to two panels and change one setting between them to see its effect on the same prompt. Tools apply to every panel, so you can see which models call your tools correctly.

## SET A SYSTEM PROMPT

Click the gear icon in a panel's header to open **System Prompts**. The dialog shows one text box for each open panel.

* A fine-tuned model performs best with the system prompt it was trained on. Use that prompt when you compare a fine-tuned model with a base model.
* Leave a box empty to send no system prompt.
* Click `Apply to all` on a panel's box to copy its text to every panel.

Click `Update` to apply the prompts. A new system prompt applies to every later request in the panel, including the conversation history it sends.

## SET SAMPLING PARAMETERS

Click the sliders icon in a panel's header to open **Model Parameters** for that panel.

![Model Parameters dialog with Temperature, Top P, Max Tokens, Seed, and Top K](https://mintcdn.com/oumi/D0vKyXNqx2ohrLV9/images/playground-parameters.jpg?fit=max\&auto=format\&n=D0vKyXNqx2ohrLV9\&q=85\&s=e4846452465b1dc83b295c3910bbc530)

| Parameter | What it does |
| - | - |
| **Temperature** | Higher values make the output more varied. Lower values make it more predictable. |
| **Top P** | Samples only from the most likely tokens whose probabilities add up to this value. |
| **Max Tokens** | Limits the length of the response. |
| **Seed** | Makes a repeated prompt return the same answer. |
| **Top K** | Samples only from this number of the most likely tokens. |

The dialog shows only the parameters that the panel's model accepts:

| Model in the panel | Temperature | Top P | Max Tokens | Seed | Top K |
| - | - | - | - | - | - |
| Oumi base models and your own deployed models | Yes | Yes | Yes | Yes | Yes |
| External OpenAI deployments | Yes | Yes | Yes | Yes | No |
| External Anthropic deployments | Yes | Yes | Yes | No | Yes |

Leave a field empty to use the model's default. Click `Update` to apply the parameters to this panel, or `Apply to all` to copy them to every panel. When you apply to all, each panel drops the parameters its model doesn't accept and adjusts values to fit its model, so one strict model doesn't break the comparison.

## LET THE MODELS CALL TOOLS

Tools show how each model behaves as an agent. You can see whether it calls the right tool with the right arguments, and how it uses the result.

1. Click `Tools`, and select an [implementation](https://docs.oumi.ai/guides/agents/tool-implementations.md) for each [tool](https://docs.oumi.ai/guides/agents/tools.md) the models may call.
2. Click `Update`. The button shows how many tools are selected, and the tools apply to every panel.
3. Send a prompt that needs a tool.

![Two Playground panels answering the same prompt with one tool selected. Llama calls lookup\_card\_status and answers from the result, and Gemma shows that tools are not available for it.](https://mintcdn.com/oumi/D0vKyXNqx2ohrLV9/images/playground-tools.jpg?fit=max\&auto=format\&n=D0vKyXNqx2ohrLV9\&q=85\&s=09499d6186180715f94d262e60994458)

Each panel shows the model's tool calls, their arguments, and each tool result before the answer. A panel whose model doesn't support tool calling shows "Tools are not available for this model" and answers without tools.

* **Interactive tools:** An [interactive implementation](https://docs.oumi.ai/guides/agents/tool-implementations.md#interactive) asks you for the answer. Type the reply in the card that appears in the panel. If you skip it, the model reads that the user did not answer.
* **Long tool loops:** A model that keeps calling tools stops after several steps and shows `Continue`. Click it to let the model keep going.
* **Cost:** Each tool step is a separate model request, so a turn with tool calls costs more than a plain answer. Simulated implementations are also billed as inference.

Running tools requires the editor or admin role in the project, or the admin or owner role in the organization.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.