# Agent Templates

## Example Agent Templates

### Agent Configuration

#### Temperature Settings

* **0.1-0.3**: Best for factual, precise responses
* **0.4-0.6**: Balanced creativity and accuracy
* **0.7-0.9**: More creative and varied responses

#### Tool Selection

1. Choose tools based on specific use cases (You can find tools ->[ Tools](/kidjig-docs/agents-api/api-reference/tools.md))
2. Combine complementary tools
3. Avoid tool redundancy

### Research Assistant

```json
{
    "name": "Academic Research Assistant",
    "description": "Comprehensive research assistant for academic work",
    "agent_role": "You are a specialized research assistant focused on academic topics",
    "agent_instructions": "Help users find and analyze academic papers and research topics",
    "tools": ["Search"],
    "provider_id": "openai",
    "model": "gpt-4o",
    "temperature": 0.7
}
```

### Code Reviewer

```json
{
    "name": "GitHub Code Reviewer",
    "description": "Expert code reviewer for GitHub repositories",
    "agent_role": "You are a senior code reviewer",
    "agent_instructions": "Review code, provide feedback on quality and improvements",
    "tools": ["Github"],
    "provider_id": "anthropic",
    "model": "claude-3-5-sonnet-20241022",
    "temperature": 0.3
}
```

### Content Researcher

```json
{
    "name": "Content Research Expert",
    "description": "Multi-source content researcher and analyzer",
    "agent_role": "You are a content research specialist",
    "agent_instructions": "Research topics across multiple sources and synthesize information",
    "tools": ["Search", "Media"],
    "provider_id": "google",
    "model": "gemini-1.5-pro",
    "temperature": 0.6
}
```


---

# 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://kidjig.gitbook.io/kidjig-docs/agents-api/agent-templates.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.