Bridge AI

We turn departing employees into specialized agents to preserve knowledge and keep work going.

Bridge AI is an intelligent knowledge transfer platform that captures tribal knowledge from departing employees and transforms it into actionable deliverables: enhanced documentation, workflow memos, and AI-powered agents that can answer questions about their processes.

Features

• Guided Knowledge Capture - Interactive interview flow that identifies knowledge gaps from scanned documents and artifacts
• Document Enhancement - AI-proposed updates to existing documentation with human-in-the-loop review
• Automated Memo Generation - Comprehensive knowledge transfer memos with editable sections
• AI Agent Creation - Specialized agents trained on captured knowledge that teammates can query
• Source Attribution - All agent responses include traceable sources back to conversations, documents, and memos

Tech Stack

• Framework: Next.js 14 (App Router)
• Language: TypeScript
• Styling: Tailwind CSS
• AI: Anthropic Claude API
• Runtime: Node.js

Getting Started

Prerequisites

• Node.js 18+
• npm or yarn
• Anthropic API key

Installation

1. Clone the repository

   git clone https://github.com/yourusername/bridge_ai.git
   cd bridge_ai

2. Install dependencies

   npm install

3. Set up environment variables

   cp .env.example .env.local

   Add your Anthropic API key:

   ANTHROPIC_API_KEY=your_api_key_here
   

4. Run the development server

   npm run dev

5. Open http://localhost:3000

Project Structure

src/
├── app/                    # Next.js App Router pages
│   ├── api/               # API routes
│   │   ├── chat/          # Agent chat endpoint
│   │   └── generate-agent/ # Agent creation endpoint
│   ├── conversation/      # Knowledge capture interview
│   ├── handoff/           # Document review & agent creation
│   └── page.tsx           # Landing page
├── components/            # React components
│   └── conversation/      # Interview UI components
├── context/               # React context providers
├── data/                  # Data and responses
├── lib/                   # Utilities and stores
└── types/                 # TypeScript type definitions

Demo Scenario

The demo follows Alice Chen, a Risk Analyst managing quarterly credit loss forecasts. Bridge AI:

1. Scans her artifacts (Excel files, Python scripts, policy docs)
2. Identifies undocumented knowledge gaps
3. Conducts a guided interview to capture her expertise
4. Proposes documentation enhancements
5. Generates a knowledge transfer memo
6. Creates an AI agent her team can query after she leaves