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

# Quick Start Guide

> Create your first AI agent in 5 minutes

## What will you build?

Junis is an AI workforce platform where you create, orchestrate, and deploy teams of AI agents through a web interface — no code required. In this tutorial, you sign in, configure your first LLM agent, connect it to your organization's orchestrator, and test it in a live chat, all in about 5 minutes.

In this tutorial, you'll create a **Customer Support Agent** that can:

* Answer common questions about your product
* Route complex issues to the right team
* Maintain context across conversations

**Time Required**: 5 minutes
**Prerequisites**: Google account (for login)

***

## Step 1: Sign In

<Steps>
  <Step title="Go to Junis">
    Navigate to [https://junis.ai](https://junis.ai) and click **"Sign in with Google"**
  </Step>

  <Step title="Authorize Access">
    Grant Junis permission to access your Google account. We only use this for authentication.

    <Info>
      Junis never accesses your Gmail, Drive, or other Google services without explicit permission.
    </Info>
  </Step>

  <Step title="Complete Onboarding">
    You'll be prompted to:

    * Create or join an AI Team
    * Set your display name
    * Choose your role

    For this tutorial, select **"Create New AI Team"** and name it anything you like (e.g., "Acme Support").
  </Step>
</Steps>

***

## Step 2: Create Your First Agent

<Steps>
  <Step title="Navigate to Orchestration">
    After logging in, you'll see the main dashboard. Click **"Team Management"** dropdown in the Navigation Bar, then select **"Agent Orchestration"**.
  </Step>

  <Step title="View Agent Configuration">
    In the Orchestration tab, you'll see a pre-configured **Orchestrator** agent (don't modify this yet).

    <Tip>
      The Orchestrator is the "brain" that routes user messages to the right agents. Every AI Team has one.
    </Tip>
  </Step>

  <Step title="Create New Agent">
    Click the **"New Agent"** button.
  </Step>
</Steps>

***

## Step 3: Configure Your Agent

Fill in the agent creation form:

<CodeGroup>
  ```yaml Basic Info theme={null}
  Name: Customer Support Agent
  Description: Helps customers with common questions and routes complex issues
  Agent Type: LLM Agent
  Status: Active ✅
  ```

  ```yaml Model Settings theme={null}
  Model: Claude Sonnet 4.5 (default)
  Temperature: 0.7
  Max Output Tokens: 1000
  ```

  ```yaml Instructions theme={null}
  You are a helpful customer support agent for Acme Corp.

  Your responsibilities:
  1. Answer common questions about our product
  2. Help troubleshoot basic issues
  3. Route complex technical problems to the engineering team
  4. Be friendly, professional, and concise

  Our product: Acme Widgets - cloud-based widget management software

  Common questions:
  - Pricing: $29/month for Pro, $99/month for Enterprise
  - Free trial: 14 days, no credit card required
  - Support hours: 9 AM - 6 PM EST, Monday-Friday
  - Contact: support@acme.com or live chat

  If you cannot help, politely ask the user to contact support@acme.com.
  ```
</CodeGroup>

<Accordion title="What do these settings mean?">
  * **Agent Type**: LLM Agent uses a language model to generate responses
  * **Model**: Claude Sonnet 4.5 is fast and cost-effective for most tasks
  * **Temperature**: 0.7 balances creativity and consistency (0 = deterministic, 1 = creative)
  * **Max Output Tokens**: Limits response length to control costs
  * **Instructions**: The "system prompt" that defines the agent's behavior
</Accordion>

Click **"Save"** to create your agent.

***

## Step 4: Connect Agent to Orchestrator

<Steps>
  <Step title="Edit the Orchestrator">
    Go back to the Agents list and click **"Edit"** on the **Orchestrator** agent.
  </Step>

  <Step title="Add Your Agent as a Sub-Agent">
    Scroll to the **"Sub-Agents"** section and click **"+ Add Sub-Agent"**.

    Select **"Customer Support Agent"** from the dropdown and set:

    * **Order**: 1 (execution priority)
    * **Description**: "Handles customer support questions"
  </Step>

  <Step title="Update Orchestrator Instructions">
    In the **Instructions** field, add:

    ```yaml theme={null}
    You are the Orchestrator for Acme Corp.

    Route user messages to the appropriate agent:
    - Customer support questions → Customer Support Agent
    - General conversation → Respond directly

    Always be helpful and professional.
    ```

    Click **"Save"**.
  </Step>
</Steps>

***

## Step 5: Test Your Agent

<Steps>
  <Step title="Start a New Chat">
    Click **"Chat"** in the sidebar, then click **"+ New Chat"**.
  </Step>

  <Step title="Send a Test Message">
    Try these example messages:

    <CodeGroup>
      ```text Example 1 theme={null}
      How much does Acme Widgets cost?
      ```

      ```text Example 2 theme={null}
      What's your free trial policy?
      ```

      ```text Example 3 theme={null}
      I'm having trouble logging in to my account
      ```
    </CodeGroup>
  </Step>

  <Step title="Observe Agent Routing">
    Watch the **Agent Pipeline Viewer** at the bottom of the chat:

    1. **Orchestrator** receives your message
    2. Routes to **Customer Support Agent**
    3. Response streams back in real-time

    <Info>
      The agent should correctly answer pricing and trial questions based on the instructions you provided.
    </Info>
  </Step>
</Steps>

***

## Congratulations! 🎉

You've created your first AI agent! Here's what you learned:

<Check>
  ✅ How to create and configure an LLM Agent
  ✅ How to write effective agent instructions
  ✅ How to connect agents to the Orchestrator
  ✅ How to test agents in the chat interface
</Check>

***

## Next Steps

<CardGroup cols={2}>
  <Card title="Add Tools to Your Agent" icon="hammer" href="/guides/tools/overview">
    Connect to APIs, databases, and external services
  </Card>

  <Card title="Create a Sequential Workflow" icon="arrow-right-arrow-left" href="/getting-started/agent-system#sequential-agent">
    Chain multiple agents together
  </Card>

  <Card title="Connect MCP Platforms" icon="plug" href="/guides/mcp/overview">
    Integrate GitHub, Firecrawl, and custom MCP servers
  </Card>
</CardGroup>

***

## Tips for Better Agents

<AccordionGroup>
  <Accordion title="Write Clear Instructions" icon="pen">
    * Be specific about the agent's role and responsibilities
    * Provide examples of expected inputs and outputs
    * Include edge cases (e.g., "If you cannot help, say X")
    * Use bullet points for readability
  </Accordion>

  <Accordion title="Start Simple, Then Iterate" icon="rotate">
    * Begin with basic functionality
    * Test thoroughly with real user messages
    * Add complexity (tools, RAG, sub-agents) gradually
    * Monitor agent performance and refine instructions
  </Accordion>

  <Accordion title="Use the Right Model" icon="microchip">
    * **Claude Haiku**: Fast, cheap, good for simple tasks (\$0.25/1M tokens)
    * **Claude Sonnet**: Balanced speed and quality (\$3/1M tokens)
    * **Claude Opus**: Most capable, best reasoning (\$15/1M tokens)
    * **GPT-4o**: Best for structured outputs and function calling
  </Accordion>

  <Accordion title="Test Edge Cases" icon="bug">
    Try these scenarios:

    * Ambiguous questions
    * Out-of-scope requests
    * Multi-turn conversations
    * Requests in different languages
    * Adversarial inputs (jailbreaks, prompt injections)
  </Accordion>
</AccordionGroup>

***

## Common Issues

<AccordionGroup>
  <Accordion title="Agent not responding">
    **Possible causes:**

    * Agent is inactive (check Status toggle)
    * Orchestrator didn't route to your agent (check Agent Pipeline Viewer)
    * API key missing for the selected model

    **Solution:**

    * Ensure agent Status is **Active** (green toggle)
    * Check Orchestrator instructions include your agent
    * Verify API keys in Settings > Organization
  </Accordion>

  <Accordion title="Responses are generic or off-topic">
    **Possible causes:**

    * Instructions are too vague
    * Temperature is too high (> 0.9)
    * Agent doesn't have enough context

    **Solution:**

    * Rewrite instructions with specific examples
    * Lower temperature to 0.5-0.7 for consistency
    * Add relevant information to the system prompt
  </Accordion>

  <Accordion title="Slow response times">
    **Possible causes:**

    * Using a slow model (Opus, GPT-4)
    * Agent is calling multiple tools/sub-agents
    * Network latency

    **Solution:**

    * Switch to Haiku or Sonnet for faster responses
    * Optimize tool calls (reduce number of API requests)
    * Use streaming for better perceived performance
  </Accordion>
</AccordionGroup>

***

## Need Help?

<CardGroup cols={2}>
  <Card title="Email Support" icon="envelope" href="mailto:contact@junis.ai">
    Contact our team directly
  </Card>

  <Card title="API Reference" icon="code" href="/api-reference/chat-completions">
    Integrate with OpenAI-compatible API
  </Card>
</CardGroup>

<Note>
  **Pro Tip**: Explore **Public Agents** in Agent Orchestration > New Agent > Public Agent to discover pre-built templates you can clone and customize for your AI Team.
</Note>