> ## Documentation Index
> Fetch the complete documentation index at: https://mintlify.com/SynkraAI/aiox-core/llms.txt
> Use this file to discover all available pages before exploring further.

# Agent Overview

> Comprehensive guide to Synkra AIOX specialized AI agents

## Introduction

Synkra AIOX uses a **squad-based AI architecture** with 12 specialized agents, each with distinct roles, authorities, and workflows. This agent ecosystem enables complete software development lifecycle automation—from research and planning to implementation, quality assurance, and deployment.

## Agent Squad

<CardGroup cols={2}>
  <Card title="Dev (Dex)" icon="code" href="/agents/dev">
    **Full Stack Developer**

    Implements stories, writes tests, fixes bugs. The builder of the squad.
  </Card>

  <Card title="QA (Quinn)" icon="check" href="/agents/qa">
    **Test Architect & Quality Advisor**

    Reviews code, creates test strategies, enforces quality gates.
  </Card>

  <Card title="Architect (Aria)" icon="building" href="/agents/architect">
    **System Architect**

    Designs full-stack architecture, selects tech stack, defines API patterns.
  </Card>

  <Card title="PM (Morgan)" icon="clipboard" href="/agents/pm">
    **Product Manager**

    Creates PRDs, manages epics, defines product strategy.
  </Card>

  <Card title="PO (Pax)" icon="target" href="/agents/po">
    **Product Owner**

    Manages backlog, validates stories, coordinates sprint planning.
  </Card>

  <Card title="SM (River)" icon="wave" href="/agents/sm">
    **Scrum Master**

    Creates user stories, manages sprints, facilitates agile workflow.
  </Card>

  <Card title="Analyst (Atlas)" icon="search" href="/agents/analyst">
    **Business Analyst**

    Conducts market research, facilitates brainstorming, creates project briefs.
  </Card>

  <Card title="DevOps (Gage)" icon="bolt" href="/agents/devops">
    **GitHub & DevOps Specialist**

    Handles git push, PR creation, CI/CD, releases. ONLY agent authorized to push.
  </Card>

  <Card title="Data Engineer (Dara)" icon="database" href="/agents/data-engineer">
    **Database Architect**

    Designs schemas, writes migrations, optimizes queries, manages RLS policies.
  </Card>

  <Card title="UX Expert (Uma)" icon="palette" href="/agents/ux-design-expert">
    **UX/UI Designer**

    Conducts user research, creates wireframes, builds design systems.
  </Card>

  <Card title="Squad Creator" icon="users-gear" href="/agents/squad-creator">
    **Squad Creation Specialist**

    Creates, validates, and publishes AIOX squads for specific domains.
  </Card>

  <Card title="AIOX Master (Orion)" icon="crown" href="/agents/aiox-master">
    **Master Orchestrator**

    Orchestrates workflows, creates framework components, executes any task.
  </Card>
</CardGroup>

## Agent Activation

Agents are activated using the `@` syntax:

```bash theme={null}
@dev              # Activate Dev agent
@qa *review       # Activate QA and run review command
@architect        # Activate Architect agent
```

Alternative activation methods:

```bash theme={null}
/dev              # Slash syntax
/dev.md           # Direct file reference
```

## Agent Collaboration Patterns

### Story Development Workflow

```mermaid theme={null}
graph LR
    PM["@pm\n(Creates PRD)"] --> SM["@sm\n(Creates Story)"]
    SM --> Dev["@dev\n(Implements)"]
    Dev --> QA["@qa\n(Reviews)"]
    QA --> DevOps["@devops\n(Pushes & PR)"]
```

### Architecture Design Workflow

```mermaid theme={null}
graph TD
    Architect["@architect\n(System Design)"] --> DataEng["@data-engineer\n(Schema Design)"]
    Architect --> UX["@ux-design-expert\n(Frontend Design)"]
    DataEng --> Dev["@dev\n(Implementation)"]
    UX --> Dev
```

## Agent Authority Model

Each agent has **exclusive authorities** that cannot be violated. This prevents chaos and ensures governance.

<Accordion title="Exclusive Agent Authorities">
  <table>
    <thead>
      <tr>
        <th>Authority</th>
        <th>Exclusive Agent</th>
        <th>Enforcement</th>
      </tr>
    </thead>

    <tbody>
      <tr>
        <td>git push</td>
        <td>@devops</td>
        <td>Git pre-push hook blocks all others</td>
      </tr>

      <tr>
        <td>Pull Request creation</td>
        <td>@devops</td>
        <td>Agent definition restriction</td>
      </tr>

      <tr>
        <td>Release & tagging</td>
        <td>@devops</td>
        <td>Agent definition restriction</td>
      </tr>

      <tr>
        <td>Story creation</td>
        <td>@sm, @po</td>
        <td>Workflow delegation</td>
      </tr>

      <tr>
        <td>Epic creation</td>
        <td>@pm</td>
        <td>Workflow delegation</td>
      </tr>

      <tr>
        <td>Architecture decisions</td>
        <td>@architect</td>
        <td>Responsibility boundary</td>
      </tr>

      <tr>
        <td>Quality gate verdicts</td>
        <td>@qa</td>
        <td>Workflow enforcement</td>
      </tr>

      <tr>
        <td>Database schema design</td>
        <td>@data-engineer</td>
        <td>Delegation from @architect</td>
      </tr>
    </tbody>
  </table>
</Accordion>

## Command Structure

All agent commands use the `*` prefix:

```bash theme={null}
*help              # Show all commands
*develop story-1   # Dev: Implement story
*review story-1    # QA: Review story
*push              # DevOps: Push changes
```

### Common Commands Across Agents

<CardGroup cols={3}>
  <Card title="*help" icon="circle-question">
    Show all available commands with descriptions
  </Card>

  <Card title="*guide" icon="book">
    Show comprehensive usage guide for the agent
  </Card>

  <Card title="*exit" icon="right-from-bracket">
    Exit agent mode and return to base context
  </Card>

  <Card title="*yolo" icon="forward">
    Toggle permission mode (ask → auto → explore)
  </Card>

  <Card title="*session-info" icon="info">
    Show current session details and agent history
  </Card>
</CardGroup>

## Agent Personas

Each agent has a unique personality archetype inspired by zodiac characteristics:

| Agent         | Name   | Archetype    | Zodiac        | Communication Style       |
| ------------- | ------ | ------------ | ------------- | ------------------------- |
| Dev           | Dex    | Builder      | ♒ Aquarius    | Pragmatic, concise        |
| QA            | Quinn  | Guardian     | ♍ Virgo       | Analytical, thorough      |
| Architect     | Aria   | Visionary    | ♐ Sagittarius | Conceptual, strategic     |
| PM            | Morgan | Strategist   | ♑ Capricorn   | Strategic, data-driven    |
| PO            | Pax    | Balancer     | ♎ Libra       | Collaborative, balanced   |
| SM            | River  | Facilitator  | ♓ Pisces      | Empathetic, adaptive      |
| Analyst       | Atlas  | Decoder      | ♏ Scorpio     | Analytical, investigative |
| DevOps        | Gage   | Operator     | ♈ Aries       | Decisive, systematic      |
| Data Engineer | Dara   | Sage         | ♊ Gemini      | Technical, methodical     |
| UX Expert     | Uma    | Empathizer   | ♋ Cancer      | Empathetic, creative      |
| AIOX Master   | Orion  | Orchestrator | ♌ Leo         | Commanding, coordinated   |

## Agent Delegation

Agents delegate tasks outside their authority:

<Accordion title="Delegation Examples">
  **@dev needs to push code:**

  * ❌ Cannot run `git push` directly
  * ✅ Delegates to `@devops *push`

  **@pm needs a story created:**

  * ❌ Cannot create detailed user stories
  * ✅ Delegates to `@sm *draft`

  **@architect needs database schema:**

  * ❌ Does not design table structure
  * ✅ Delegates to `@data-engineer *create-schema`
</Accordion>

## Agent Configuration

Each agent is defined in `.aiox-core/development/agents/{agent-id}.md` with:

* **Persona profile** (archetype, zodiac, communication style)
* **Commands** (full, quick, key visibility levels)
* **Dependencies** (tasks, templates, checklists, tools)
* **Authority boundaries** (allowed/blocked operations)
* **Workflow rules** (activation instructions, core principles)

## Next Steps

<CardGroup cols={2}>
  <Card title="Learn Agent Commands" icon="terminal" href="/agents/dev">
    Explore each agent's available commands and workflows
  </Card>

  <Card title="Understand Workflows" icon="diagram-project" href="/workflows/story-development">
    See how agents collaborate in complete workflows
  </Card>

  <Card title="Agent Constitution" icon="scroll" href="/concepts/constitution">
    Review the governance model and authority matrix
  </Card>
</CardGroup>