# Agents

## 🤖 AI Agents

***

### 1. Overview

Conjure uses specialized AI Agents to handle various aspects of the software development lifecycle. Each agent is fine-tuned for specific tasks, ensuring high productivity and optimal code quality.

***

### 2. Agent Types

#### • WebAppAgent

• Role: Focuses on modern web application development (frontend + backend).\
• Common Tasks:

* Setting up React components and pages.
* Managing server routes with Node.js and Express.
* Generating Tailwind CSS utilities for styling.
* Rapid prototyping of responsive UIs.
* Creating RESTful APIs.
* Integrating authentication (e.g., JWT).

#### • GameDevAgent

• Role: Specializes in gaming features such as physics, rendering, and real-time interaction.\
• Common Tasks:

* Updating custom game logic.
* Handling asset management.
* Optimizing frames per second (FPS) and performance metrics.
* Advanced game mechanics and collision systems.
* Integrating 2D/3D rendering pipelines.
* Prototyping gameplay loops quickly.

***

### 3. How They Interact

1. You provide a prompt or a set of requirements.
2. The targeted agent analyzes, provides suggestions, and/or completes a set of code changes.
3. If the changes overlap (for example, game mechanics that require a backend server), both agents may coordinate through shared data structures.
4. Output is visible in real-time via Conjure’s built-in browser or game preview.

> **Info:** Agents often log metrics like memory usage, processing time, and network status to help you diagnose performance or debugging issues.

***

### 4. Best Practices

• Keep your prompts concise: Provide clear objectives and descriptions so agents perform more accurately.\
• Use incremental updates: Tackle tasks step-by-step to maintain control and clarity.\
• Monitor terminal logs: Detailed system logs from agents help you spot issues quickly.

***

### 5. FAQs

1. **How do I switch between agents?**\
   Navigate to each agent’s dedicated page or interface in the Conjure UI. Specify which agent you want to use for a given task.
2. **What about security concerns?**\
   AI Agents follow best practices like environment-based configurations, JWT authentication, and robust permission checks at the code generation layer.
3. **Are these agents customizable?**\
   Absolutely! You can create specialized versions or parameterize them for your specific needs.

> **Tip:** Still have questions? Reach out to the Conjure community or explore additional docs to get detailed answers!


---

# 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://conjureai.gitbook.io/conjureai/agents.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.