AI GTM Stakeholder Engine

Strategic Translation for Every Stakeholder

🚀 LIVE DEMO: https://ace-hsu-gtm-engine.hf.space/

The gap isn't strategy quality—it's strategy translation: turning comprehensive strategic assets into precise guidance that sales teams, designers, and every stakeholder can immediately act on without having to spend time reading strategy documents.

Key Features

• 11 AI Agents with self-improving orchestration pipeline
• Multi-stakeholder translation - 9 department interfaces (design, sales, product, PR, etc.)
• Strategic consistency - 95% alignment from planning to execution
• Production ready - Docker deployment, real-time analytics, enterprise security

Project Structure

├── backend/
│   ├── agents/                    # 11 AI agents + orchestration
│   │   ├── agent_0a_configurator/ # Auto-prompt engineering
│   │   ├── agent_0b_orchestrator/ # Pipeline orchestration
│   │   ├── message_house_agent/   # Strategic foundation
│   │   ├── [8 more agents]/       # Specialized content generation
│   │   └── rag_system_agent/      # Vector database integration
│   ├── config.template.json       # API configuration
│   └── requirements.txt           # Python dependencies
├── frontend/
│   ├── src/                       # React stakeholder interfaces
│   ├── Dockerfile                 # Production deployment
│   ├── package.json              # Node.js dependencies
│   └── nginx.conf                # Production server config
├── docs/                          # User-friendly documentation
├── technical/                     # Technical implementation details
├── contrib/                       # Plugin development framework
└── examples/                      # Live demonstrations

Tech Stack

Backend Agents (Python)

• AI Models: Anthropic Claude 3.5 Sonnet API
• Orchestration: Custom multi-agent pipeline with dependency management
• RAG System: LangChain + pgvector-compatible vector database
• Processing: pandas, numpy for data transformation
• Configuration: JSON-based agent configuration system

RAG Knowledge System (Node.js/TypeScript)

• Vector Database: pgvector-compatible database (Supabase, PostgreSQL, etc.)
• Embeddings: OpenAI text-embedding-3-small
• Framework: LangChain for document processing and retrieval
• Processing: Recursive character text splitting, semantic search

Frontend Application (React)

• Framework: React 18 with TypeScript
• Styling: Tailwind CSS with shadcn/ui components
• Build: Vite for fast development and optimized production builds
• State Management: React hooks with context patterns

APIs & Services

• Anthropic Claude API: Primary LLM for content generation
• OpenAI API: Embeddings for vector search
• Vector Database: Any pgvector-compatible database (Supabase recommended)

DevOps & Deployment

• Containerization: Docker with multi-stage builds
• Frontend Deployment: nginx with optimized static serving
• Environment Management: dotenv for secure configuration
• Version Control: Git with comprehensive .gitignore protection

Environment Setup

Required API Keys

# Anthropic Claude API (Primary LLM)
ANTHROPIC_API_KEY=your_claude_api_key

# OpenAI API (Embeddings for RAG)
OPENAI_API_KEY=your_openai_api_key

# Vector Database (pgvector-compatible)
DATABASE_URL=your_database_url
DATABASE_ANON_KEY=your_database_key  # If required

Configuration Files

• backend/config.template.json → Copy to config.json and add your API keys
• backend/agents/rag_system_agent/gtm_rag_core/.env.example → Copy to .env and configure database
• frontend/.env.example → Copy to .env and configure API endpoints

Quick Start

Prerequisites

• Python 3.8+
• Node.js 18+
• Anthropic API key (Get here)
• OpenAI API key (Get here)
• pgvector-compatible database (Supabase recommended)

1. Clone Repository

git clone https://github.com/username/AI-GTM-Stakeholder-Engine
cd AI-GTM-Stakeholder-Engine

2. Backend Setup

cd backend

# Install Python dependencies
pip install -r requirements.txt

# Configure environment
cp config.template.json config.json
# Edit config.json with your API keys

3. RAG System Setup

cd backend/agents/rag_system_agent/gtm_rag_core

# Install Node.js dependencies
npm install

# Configure environment
cp .env.example .env
# Edit .env with your API keys and database credentials

4. Frontend Setup

cd frontend

# Install dependencies
npm install

# Configure environment
cp .env.example .env
# Edit .env with your API endpoints

# Start development server
npm run dev

5. Run Full Pipeline

# Navigate to orchestrator
cd backend/agents/agent_0b_orchestrator/scripts

# Run complete multi-agent pipeline
python run_unified_pipeline.py

User Roadmap

• PM/PMM: Live demo → Deploy locally → Upload your strategic assets
• Developers: Clone repo → Follow technical docs → Explore multi-agent backend
• Plugin Developers: Use contrib framework → Create custom agents → Integrate with pipeline

Live System Proof

✅ Production deployment with <2s response time ✅ Real conversations - 17 stakeholder examples with measurable results ✅ Enterprise architecture - Multi-project isolation, proven scalability

Documentation

• Getting Started - Setup & first run
• Technical Documentation - System architecture & deployment
• Plugin Development - Create custom agents
• Examples - Real stakeholder outputs