> For the complete documentation index, see [llms.txt](https://docs.jetadmin.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.jetadmin.io/ai-agents/run-agents-in-apps-workflows-and-tasks/the-agent-interface.md).

# The Agent Interface

Explore the key sections of the Jetadmin Agent configuration interface, where you define your agent’s purpose, inputs, behavior, and access to tools.

When configuring an agent, you’ll find these  key sections:

1. **Instruction**
   * Define the main goal or purpose of the agent.
   * Example: *“Act as a customer support assistant that answers product-related questions.”*
2. **Agent Inputs**
   * Provide custom input fields that can be referenced inside instructions.
   * Useful for passing dynamic data into the agent’s reasoning.
3. **Additional Settings**
   * **Steps Maximum**: limit the number of reasoning loops (up to 30).
   * **Temperature**: adjust randomness (lower = more predictable, higher = more creative).
4. **Tools Available to Agent**
   * Choose which tools the agent can use (data sources, actions, other agents, etc.).
   * Add tool-specific instructions to guide behavior.
   * Control permissions (CRUD levels) for each tool.

{% @arcade/embed flowId="RQdtlMFTx4VSejQcbVZU" url="<https://app.arcade.software/share/RQdtlMFTx4VSejQcbVZU>" %}

{% hint style="info" %}
**Key Considerations for Agent Setup**\
Effective agents start with clear and detailed configuration. Providing precise instructions, well-defined inputs, and carefully selected settings and tools ensures your agent performs accurately and reliably.
{% endhint %}


---

# 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.jetadmin.io/ai-agents/run-agents-in-apps-workflows-and-tasks/the-agent-interface.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.