An AI-powered auto-bidding platform that reduces proposal writing time from 30 minutes to 2 minutes using RAG-based knowledge retrieval and AI proposal generation.
An autonomous multi-agent system that monitors procurement opportunities, evaluates bid fit, generates proposal content, and manages submission workflows. Reduces the manual overhead of competitive bidding for enterprise buyers and suppliers.
**Services: ** Bid monitoring, Fit scoring, Proposal generation, Submission automation, Spend analytics
Highlights:
- Multi-agent system: Coordinated autonomous agents
- Real-time decisions: Bid/no-bid in seconds
- Proposal drafting: LLM-generated content
- ISC-aligned: Gov procurement potential
Main dashboard showing active projects and key metrics
Browse and track jobs you're bidding on
The signature feature of Auto-Bidder: AI fuses each project's requirements with your portfolio, experience, and strengths to craft the best-matched proposal for every client in about 1 minute, then auto-organizes it for customer email delivery and moves the project to Bidding Stage 1 to kick off the bidding process instantly.
AI-powered proposal generation with RAG, structured job context, and one-click email delivery
Upload portfolio documents, case studies, and team profiles for AI context
Create reusable AI prompt templates for different proposal tones
Filter jobs and emphasize your skills in AI-generated proposals
Performance analytics, win rate tracking, and time savings metrics
Account preferences and application configuration
- 🔍 Job Discovery - Import jobs from HuggingFace datasets with automated ETL
- 📚 Knowledge Base - Upload portfolio docs for RAG-powered context (ChromaDB + LangChain)
- 🤖 AI Proposals - Generate personalized proposals in 60 seconds using GPT-4/DeepSeek
- 📧 Email Delivery - Auto-send HTML emails from verified domain with BCC archiving
- 🎯 Smart Strategies - Reusable AI prompt templates for different tones
- 🔑 Keyword Filtering - Filter jobs and emphasize skills in proposals
- 📊 Analytics - Track win rates, performance metrics, and time savings
Quick Workflow: Discover Jobs → Upload Portfolio → Generate AI Proposal → Submit via Email
📄 Detailed workflow docs | Email system guide
Frontend: Next.js 15 • React 19 • TypeScript • TailwindCSS 4 • shadcn/ui • TanStack Query
Backend: FastAPI • PostgreSQL • ChromaDB • LangChain • OpenAI/DeepSeek • JWT Auth • Resend (Email)
Infrastructure: Docker Compose • Vercel • Railway
Prerequisites: Node.js 20+ • Python 3.11+ • Docker • make
# One-time setup
cp backend/.env.example backend/.env # Configure env vars
cp frontend/.env.example frontend/.env.local
# Start everything
make infra-up # Start PostgreSQL + ChromaDB
make install # Install all dependencies
make dev # Run backend (:5555) + frontend (:5556)Or set up manually:
docker-compose up -d
# Frontend
cd frontend && npm install && cp .env.example .env.local
npm run dev # http://localhost:5556
# Backend
cd backend && pip install -r requirements.txt && cp .env.example .env
# Edit .env: Add JWT_SECRET, OPENAI_API_KEY/DEEPSEEK_API_KEY, RESEND_API_KEY
uvicorn app.main:app --reload --port 5555Required ENV vars: JWT_SECRET • OPENAI_API_KEY or DEEPSEEK_API_KEY • RESEND_API_KEY • DATABASE_URL
💡 Makefile: Run
make helpfor all available commands, or see docs/makefile-commands.md.
JWT Authentication with bcrypt password hashing, 30-day token expiration, and secure secrets.
📄 Setup guide | Auth flow diagram
| Guide | Description |
|---|---|
| Setup | Quick start, auth, ChromaDB & Railway deployment |
| User Guide | How to use the platform |
| Proposals | Proposal workflow & AI generation |
| Email System | Email config & troubleshooting |
| Configuration | Keywords, strategies & settings |
| Architecture | System diagrams |
Frontend: Vercel • Backend: Railway/Fly.io • Database: PostgreSQL
Built with ❤️ by the Auto Bidder Team