ATOM Documentation

← Back to App

ATOM SaaS Documentation

"The First AI Workforce You Can Actually Trust"

Welcome to the comprehensive documentation for ATOM SaaS - a multi-tenant AI agent platform with cognitive architectures, learning engines, and enterprise-grade governance.

Quick Links

🚀 Get Started Fast

Documentation by Audience

👤 For Users

Getting Started

Agent Management

Integrations

Canvas & Marketplace

Desktop App

💻 For Developers

Setup & Configuration

Development Standards

Architecture

API Reference

🌐 Public Marketplace API

Development Workflows

🔧 For Administrators

Deployment

Operations

Security

Troubleshooting

📚 Key Concepts

Brain Systems

ATOM SaaS includes six cognitive brain systems that enable human-like intelligence:

  • Cognitive Architecture - Reasoning, memory, attention, language processing
  • Learning Engine - Experience-based learning and adaptation
  • World Model - Long-term memory with semantic search
  • Reasoning Engine - Proactive intelligence and interventions
  • Cross-System Reasoning - Multi-system data correlation
  • Backend Intelligence - Business logic and communication processing

⚠️ Warning: Brain systems are critical - changes affect all agent behavior. See Brain System Usage.

Multi-Tenancy

Every operation is scoped to a tenant using:

  • Subdomain-based routing (tenant.atomagentos.com or custom domains)
  • Row-Level Security (RLS) in PostgreSQL
  • S3 prefix isolation (s3://atom-saas/{tenant_id}/)
  • Redis namespace separation (tenant:{tenant_id}:...)

🔴 Critical: Always extract tenant context. Never skip tenant_id filtering. See Tenant Isolation Patterns.

Agent Maturity

Agents progress through four maturity levels:

  • Student - Read-only, low-complexity tasks
  • Intern - Analyze, suggest, medium-low complexity
  • Supervised - Create, send_email, medium complexity
  • Autonomous - All actions including high-risk (delete, execute)

Graduation is determined by:

  • Zero-intervention ratio (40% weight)
  • Constitutional compliance score (30% weight)
  • Confidence score (20% weight)
  • Success rate (10% weight)

See Agent Graduation for details.

BYOK (Bring Your Own Key)

Tenants provide their own LLM API keys stored in tenant_settings table. The platform automatically routes to tenant-provided keys for all AI operations.

🎯 Architecture Diagram

graph TB
    subgraph "Presentation Layer"
        A[Next.js Web App<br/>:3000]
        B[Tauri Desktop App<br/>Local]
    end

    subgraph "API Layer"
        C[Next.js API Routes<br/>/api/*]
        D[FastAPI Backend<br/>:8000]
    end

    subgraph "Brain Systems"
        E[Cognitive Architecture]
        F[Learning Engine]
        G[World Model<br/>+ pgvector]
        H[Reasoning Engine]
        I[Cross-System Reasoning]
        J[Agent Governance]
    end

    subgraph "Data Layer"
        K[(PostgreSQL + RLS)]
        L[(LanceDB<br/>Vector DB)]
        M[(Redis<br/>Cache/Queue)]
        N[(AWS S3<br/>Storage)]
    end

    subgraph "External Services"
        O[39+ Integrations<br/>CRM, Comm, Storage]
        P[LLM Providers<br/>OpenAI, Anthropic]
    end

    A --> C
    B --> C
    C --> D
    D --> E
    D --> F
    D --> G
    D --> H
    D --> I
    D --> J
    E --> K
    F --> K
    G --> L
    D --> O
    E --> P

See full architecture diagrams →

🚀 Quick Start

For Users

  1. Create Account (2 min)

    # Visit https://app.atomagentos.com
# Click "Sign Up" and verify email

  2. Create Agent (2 min)

    # Navigate to Agents > Create Agent
# Name: "My Assistant"
# Role: General Assistant
# Maturity: Student

  3. Run Task (1 min)

    # Open agent chat
# Type: "Search for recent AI articles"
# Click Execute

📖 Full Quick Start Guide →

For Developers

  1. Clone Repository

    git clone https://github.com/your-org/atom-saas.git
cd atom-saas

  2. Install Dependencies

    # Frontend (Node.js 20+)
npm install

# Backend (Python 3.11+)
cd backend-saas
python -m venv venv
source venv/bin/activate
pip install -r requirements.txt

  3. Start Development Servers

    # Terminal 1: Frontend
npm run dev  # :3000

# Terminal 2: Backend
cd backend-saas
uvicorn core.main:app --reload  # :8000

📖 Full Development Setup →

📖 Documentation Index

Architecture

API Reference

Development

User Guides

Deployment

Operations

Troubleshooting

🤝 Contributing

Found a documentation issue? Please:

  1. Check for existing issues in GitHub
  2. Create a new issue with detailed description
  3. Submit a PR with your improvements

Contribution Guidelines →

📞 Support

  • Documentation Issues: GitHub Issues
  • Platform Support: support@atomagentos.com
  • Developer Community: [Discord/Slack]

Last Updated: 2025-02-06 Documentation Version: 1.0.0 Platform Version: 8.0 (Production Ready)