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

# Agent System

> AI agents for mind cloning, operational roles, and multi-agent deliberation

Mega Brain includes a sophisticated agent system with four distinct agent types, each serving different purposes in the knowledge ecosystem.

## Agent Types Overview

<CardGroup cols={2}>
  <Card title="MINDS" icon="brain" color="#9333ea">
    **Expert Mind Clones (L3)**

    AI agents that reason like specific experts, grounded in their actual materials (5 active agents)
  </Card>

  <Card title="CARGO" icon="briefcase" color="#2563eb">
    **Functional Roles (L4)**

    Operational role agents that synthesize knowledge from multiple sources (14 active agents)
  </Card>

  <Card title="CONCLAVE" icon="users" color="#dc2626">
    **Deliberative Agents (L1)**

    Constitutional deliberation agents for structured debate (3 active agents)
  </Card>

  <Card title="SYSTEM" icon="robot" color="#059669">
    **System Orchestrators (L0)**

    Core system agents like JARVIS that manage operations
  </Card>
</CardGroup>

## MINDS: Expert Mind Clones (L3)

<Accordion title="Overview">
  Mind clones are AI agents trained on an expert's actual materials. They reason using extracted DNA (5 layers) and can be consulted for advice that mirrors the expert's thinking.
</Accordion>

### Active Mind Clones (5)

<Tabs>
  <Tab title="Alex Hormozi">
    **ID:** `alex-hormozi`\
    **Path:** `agents/minds/alex-hormozi/`

    **DNA Layers:**

    * L1: Price as value consequence, scale before optimize
    * L2: Value Equation, Product Ladder
    * L3: Value anchoring, volume focus
    * L4: Offer Stack Formula, Lead Magnet systems
    * L5: 30-day onboarding, launch sequences

    **Expertise:** Business scaling, offer creation, monetization
  </Tab>

  <Tab title="Cole Gordon">
    **ID:** `cole-gordon`\
    **Path:** `agents/minds/cole-gordon/`

    **DNA Layers:**

    * L1: Speed over perfection, qualification over persuasion
    * L2: NEPQ framework, response velocity
    * L3: 5-minute lead response, price anchoring
    * L4: SPIN Selling, NEPQ methodology
    * L5: Sales team scaling, onboarding sequences

    **Expertise:** High-ticket sales, NEPQ, team scaling
  </Tab>

  <Tab title="Jeremy Haynes">
    **ID:** `jeremy-haynes`\
    **Path:** `agents/minds/jeremy-haynes/`

    **Expertise:** Sales operations, process optimization
  </Tab>

  <Tab title="Jeremy Miner">
    **ID:** `jeremy-miner`\
    **Path:** `agents/minds/jeremy-miner/`

    **Expertise:** NEPQ methodology, neuro-emotional selling
  </Tab>

  <Tab title="The Scalable Company">
    **ID:** `the-scalable-company`\
    **Path:** `agents/minds/the-scalable-company/`

    **Expertise:** Business systems, operational scaling
  </Tab>
</Tabs>

### Mind Clone Structure

Each mind clone has:

```
agents/minds/{expert}/
├── AGENT.md           # Agent definition (identity, role, reasoning)
├── DNA-CONFIG.yaml    # 5-layer DNA extracted from sources
├── MEMORY.md          # Episodic memory (Team Agreement style)
└── SOUL.md            # Core personality and voice
```

### Using Mind Clones

```bash theme={null}
# Query a specific mind clone
/ask alex-hormozi "How should I price my high-ticket offer?"

# Get DNA-grounded reasoning
/ask cole-gordon "What's the best way to scale a sales team?"
```

<Note>
  Mind clones provide **traced reasoning** — every recommendation links back to source material with chunk IDs.
</Note>

## CARGO: Functional Roles (L4)

<Accordion title="Overview">
  Cargo agents are operational roles that synthesize knowledge from multiple experts. They're designed for day-to-day business functions.
</Accordion>

### Active Cargo Agents (14)

<Tabs>
  <Tab title="Sales Roles (9)">
    * **SDS** (Sales Development Specialist)
    * **LNS** (Lead Nurturing Specialist)
    * **BDR** (Business Development Rep)
    * **NEPQ Specialist**
    * **Sales Coordinator**
    * **Sales Manager**
    * **Sales Lead**
    * **Customer Success**
    * **Closer**
  </Tab>

  <Tab title="Marketing (1)">
    * **Paid Media Specialist**
  </Tab>

  <Tab title="C-Level (4)">
    * **CFO** (Chief Financial Officer)
    * **COO** (Chief Operating Officer)
    * **CMO** (Chief Marketing Officer)
    * **CRO** (Chief Revenue Officer)
  </Tab>
</Tabs>

### Cargo Agent Structure

```
agents/cargo/{department}/{role}/
├── AGENT.md           # Role definition and responsibilities
├── MEMORY.md          # Organizational knowledge
└── DNA-CONFIG.yaml    # Synthesized DNA from multiple experts
```

### DNA Synthesis

Cargo agents combine DNA from multiple sources:

**Example: Sales-Lead Agent**

Synthesizes knowledge from:

* Cole Gordon (team scaling)
* Alex Hormozi (offer optimization)
* Jeremy Haynes (operations)
* Jeremy Miner (NEPQ methodology)

### Threshold-Based Creation

Cargo agents are created automatically when role mentions reach thresholds:

* **>=10 mentions:** 🔴 Create new agent
* **>=5 mentions:** 🟡 Monitor role

## CONCLAVE: Deliberative Agents (L1)

<Accordion title="Overview">
  Conclave agents engage in structured multi-agent deliberation. They debate, critique, and synthesize ideas following constitutional principles.
</Accordion>

### Active Conclave Agents (3)

<CardGroup cols={3}>
  <Card title="Crítico Metodológico" icon="microscope">
    **ID:** `critico-metodologico`

    Challenges assumptions, identifies weaknesses, demands evidence.
  </Card>

  <Card title="Sintetizador" icon="compress">
    **ID:** `sintetizador`

    Synthesizes multiple perspectives into coherent recommendations.
  </Card>

  <Card title="Advogado do Diabo" icon="scale-balanced">
    **ID:** `advogado-do-diabo`

    Presents counter-arguments, explores alternative perspectives.
  </Card>
</CardGroup>

### Conclave Process

<Steps>
  <Step title="Present Question">
    User poses a question or decision to the conclave
  </Step>

  <Step title="Individual Analysis">
    Each agent analyzes independently from their perspective
  </Step>

  <Step title="Cross-Examination">
    Agents challenge each other's reasoning
  </Step>

  <Step title="Evidence Gathering">
    Pull from knowledge base with RAG for supporting evidence
  </Step>

  <Step title="Synthesis">
    Sintetizador compiles final recommendation with dissenting views
  </Step>
</Steps>

### Running a Conclave

```bash theme={null}
# Start deliberation session
/conclave "Should we prioritize scaling or optimization right now?"
```

**Output includes:**

* Individual agent positions
* Evidence from knowledge base
* Points of consensus
* Points of disagreement
* Final synthesized recommendation
* Dissenting opinions

## SYSTEM: Orchestrators (L0)

<Accordion title="Overview">
  System agents manage core operations. JARVIS is the primary orchestrator.
</Accordion>

### JARVIS

**Path:** `core/jarvis/`

**Responsibilities:**

* Pipeline orchestration
* Agent supervision
* Quality control
* Session management
* Knowledge curation

**DNA:** Hand-crafted 5-layer cognitive framework (see `core/jarvis/03-JARVIS-DNA.yaml`)

**Key Philosophies:**

* "The master is always right, except when wrong — and it's my duty to say when"
* "Anticipate needs rather than react to requests"
* "Knowledge without action is waste. Action without knowledge is danger."

## Agent Architecture

### Standard Agent Template (V3)

All agents follow the template in `agents/_templates/TEMPLATE-AGENT-MD-ULTRA-ROBUSTO-V3.md` with 11 mandatory parts:

<Accordion title="11 Mandatory Parts">
  1. **COMPOSIÇÃO ATÔMICA** - Architecture, DNA integration
  2. **GRÁFICO DE IDENTIDADE** - Radar chart of capabilities
  3. **MAPA NEURAL** - Top insights and mental models
  4. **NÚCLEO OPERACIONAL** - Mission, triggers, boundaries
  5. **SISTEMA DE VOZ** - Tone, phrases, communication style
  6. **MOTOR DE DECISÃO** - Heuristics and decision trees
  7. **INTERFACES DE CONEXÃO** - Related agents and interactions
  8. **PROTOCOLO DE DEBATE** - Council participation rules
  9. **MEMÓRIA EXPERIENCIAL** - Cases, calibration, evolution
  10. **EXPANSÕES E REFERÊNCIAS** - Knowledge base links
  11. **METADATA** - Version, sources, hash
</Accordion>

### Agent Components

<Tabs>
  <Tab title="AGENT.md">
    **Agent Definition**

    * Identity and role
    * DNA integration
    * Reasoning protocols
    * Decision frameworks
    * Communication style
  </Tab>

  <Tab title="SOUL.md">
    **Personality Core**

    * Voice and tone
    * Core values
    * Behavioral patterns
    * Communication preferences
  </Tab>

  <Tab title="MEMORY.md">
    **Episodic Memory**

    * Team Agreement format
    * Past decisions
    * Learned lessons
    * Calibration history
  </Tab>

  <Tab title="DNA-CONFIG.yaml">
    **Cognitive DNA**

    * 5-layer framework
    * Source traceability
    * Confidence scores
    * Cross-references
  </Tab>
</Tabs>

## Agent Registry

**File:** `agents/AGENT-INDEX.yaml`

Auto-updated registry of all agents:

```yaml theme={null}
version: "4.1.0"
updated: "2026-02-27"

totals:
  minds: 5
  cargo: 14
  conclave: 3
  total: 22

minds:
  - id: alex-hormozi
    path: agents/minds/alex-hormozi/
    has_soul: true
    has_memory: true
    status: active

cargo:
  sales:
    - id: sales-lead
      path: agents/cargo/sales/sales-lead/
      status: active
```

## Agent Operations

### Creating New Agents

```bash theme={null}
# Create new agent with template
/create-agent --layer L4 --id sales-trainer --name "Sales Trainer" --role "Training and development"
```

### Updating Agent Memory

Memories are updated automatically during pipeline Phase 7 when new knowledge is discovered.

**Approval options:**

* **SIM** - Update AGENT.md + MEMORY.md
* **APENAS MEMORY** - Update memory only
* **PULAR** - Skip for now

### Querying Agents

```bash theme={null}
# Query specific agent
/ask [agent-id] "[question]"

# Examples
/ask alex-hormozi "How do I structure a value ladder?"
/ask sales-lead "What's the best onboarding sequence for new closers?"
```

## Agent Commands

| Command         | Action                     |
| --------------- | -------------------------- |
| `/create-agent` | Create new agent           |
| `/ask [id]`     | Query specific agent       |
| `/conclave`     | Start council deliberation |
| `/agents`       | Show agent status          |

## Agent Hooks

Automatic agent maintenance via hooks:

* `agent_index_updater.py` - Auto-update AGENT-INDEX.yaml
* `agent_memory_persister.py` - Persist memory changes
* `agent_creation_trigger.py` - Trigger creation at thresholds
* `claude_md_agent_sync.py` - Sync agent files

## Next Steps

<CardGroup cols={2}>
  <Card title="DNA Schema" icon="dna" href="/concepts/dna-schema">
    Learn how agent DNA is extracted
  </Card>

  <Card title="Knowledge Pipeline" icon="arrows-spin" href="/concepts/knowledge-pipeline">
    See how agents are enriched in Phase 7
  </Card>

  <Card title="Layer System" icon="layer-group" href="/concepts/layer-system">
    Understand L1/L2/L3 agent distribution
  </Card>

  <Card title="Architecture" icon="sitemap" href="/concepts/architecture">
    Explore the complete system architecture
  </Card>
</CardGroup>