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

# Agents

> Conversational AI that uses tools and executes tasks

<video controls loop preload="metadata">
  <source src="https://mintcdn.com/spot-16018069/GSdjXE6hvFMwIRlK/videos/coworker_video.mp4?fit=max&auto=format&n=GSdjXE6hvFMwIRlK&q=85&s=f620f2c00b42945e3140af18962f915f" type="video/mp4" data-path="videos/coworker_video.mp4" />
</video>

## What is an Agent?

An agent in Noxus is a conversational AI assistant built by connecting capabilities into an intelligent interface. Agents enable:

* **Natural Language Processing**: Process requests naturally, maintain context, and adapt to user needs
* **Tool Integration**: Access web research, human-in-the-loop, knowledge bases, flow execution, and file handling
* **Context Awareness**: Remember conversation history and maintain context across interactions
* **Smart Decision Making**: Make intelligent choices based on context and available tools

<Note>
  Agents combine natural language understanding with the ability to take actions—creating truly autonomous AI assistants.
</Note>

## What are Agents Used For?

Agents enable intelligent, conversational automation that can reason and adapt.

<AccordionGroup>
  <Accordion title="Customer Support" icon="headset">
    * Answer customer questions
    * Troubleshoot issues
    * Create support tickets
    * Escalate to humans when needed
  </Accordion>

  <Accordion title="Internal Assistants" icon="users">
    * Help employees find information
    * Execute business processes
    * Generate reports and summaries
    * Automate routine tasks
  </Accordion>

  <Accordion title="Research & Analysis" icon="search">
    * Gather information from multiple sources
    * Synthesize findings
    * Generate comprehensive reports
    * Provide insights and recommendations
  </Accordion>

  <Accordion title="Task Automation" icon="robot">
    * Multi-step task execution
    * Dynamic decision making
    * Tool orchestration
    * Context-aware processing
  </Accordion>
</AccordionGroup>

## Key Features

<CardGroup cols={2}>
  <Card title="Natural Language" icon="message-circle">
    Interact using conversational language
  </Card>

  <Card title="Tool Use" icon="wrench">
    Execute flows, search knowledge bases, call APIs
  </Card>

  <Card title="Context Awareness" icon="brain">
    Remember conversation history and maintain context
  </Card>

  <Card title="Reasoning" icon="lightbulb">
    Plan multi-step approaches and adapt based on results
  </Card>

  <Card title="Knowledge Access" icon="book-open">
    Search and retrieve information from knowledge bases
  </Card>

  <Card title="Human Handoff" icon="user-plus">
    Escalate to humans when needed
  </Card>
</CardGroup>

## When to Use Agents

<Tabs>
  <Tab title="Use Agents When">
    * Conversational interface needed
    * Dynamic, context-aware decisions required
    * Natural language interaction preferred
    * Multi-turn conversations
    * Tool use and reasoning needed
    * Autonomous task execution
  </Tab>

  <Tab title="Consider Flows When">
    * Predefined, structured process
    * Visual workflow design preferred
    * No conversation needed
    * Deterministic execution required
    * Complex data transformations
  </Tab>
</Tabs>

## Agent Components

Agents are configured with several key elements:

| Component        | Description                      | Examples                                          |
| :--------------- | :------------------------------- | :------------------------------------------------ |
| **Instructions** | Natural language role definition | "You are a customer support agent for..."         |
| **Tools**        | Capabilities the agent can use   | Flows, knowledge bases, APIs, web research        |
| **Model**        | Underlying AI engine             | GPT-4, Claude Opus, GPT-4o                        |
| **Memory**       | Context management               | Conversation history, session state               |
| **Guardrails**   | Safety and limits                | Token limits, content filtering, escalation rules |

<Card title="Learn More About Agents" icon="bot-message-square" href="/core/concepts/agents">
  Complete guide to agents and their capabilities
</Card>

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Prompts & Instructions" icon="message-square" href="/platform/agents/prompts-instructions">
    Learn how to write effective agent instructions
  </Card>

  <Card title="Agent Tools" icon="wrench" href="/platform/agents/tools">
    Configure tools and capabilities for agents
  </Card>
</CardGroup>