What I Built
AI Boardroom OS is a multi-agent business decision simulator that runs on a local LLM. You describe a business decision, optionally upload supporting documents, and a virtual boardroom of 10+ executive personas (CFO, CTO, CMO, and others) analyzes it, debates it, and hands it to a CEO agent that synthesizes a final recommendation. A last validation stage checks that the decision is coherent.
Who would pay: solo founders, small agencies and consultancies who want a structured second opinion on pricing, hiring, or go-to-market calls but can't afford an advisory board or send confidential numbers to a third-party API. Everything runs on the user's own machine.
Side hustle angle: [your model, e.g. "sell it as a one-off 'decision review' service at ₹X per session", or "offer a self-hosted license to small consultancies". Fill in what you'd actually do.]
Code
krushnakodgirwar
/
AI-Boardroom
AI-powered multi-agent business decision simulator with executive agents and an AI CEO decision system.
🏛️ AI Boardroom OS
A Multi-Agent AI Business Decision Simulator
Analyze business challenges through specialized AI executives, collaborative reasoning, and structured decision-making
🌐 Live Application
🔗 Live Website: https://ai-boardroom-xexp.onrender.com
🔗 GitHub Repository: https://github.com/krushnakodgirwar/AI-Boardroom
Deployment note: The frontend is hosted on Render. Full AI analysis requires the FastAPI backend to be running and the frontend to be configured with a reachable backend URL.
📑 Table of Contents
📖 Explore the README sections
- ✨ Introduction
- 🎯 Problem Statement
- 💡 Project Vision
- 🚀 Key Features
- 👥 The Executive Board
- ⚡ Intelligence Modes
- 🎛️ Agent Selection
- 📋 Response Formats
- 🧠 AI Decision Workflow
- 🏗️ System Architecture
- 🛠️ Technology Stack
- 📂 Project Structure
- ⚙️ Installation
▶️ Run Locally- 🔌 API Documentation
- ☁️ Deployment
- 🧪 Example Scenario
⚠️ Limitations- 🔮 Future Improvements
- 👨💻 Author
✨ Introduction
AI Boardroom OS is a multi-agent AI business decision simulator that explores how specialized…
How I Built It
- Model: Qwen2.5-3B-Instruct (open weights), 4-bit NF4 quantized, running on an RTX 3050 with 4 GB VRAM. I started with TinyLlama-1.1B, moved to Qwen2.5-1.5B, then to 3B as I got better at working around small-model limits.
- Pipeline: four stages: executive analysis → debate → CEO synthesis → decision validation.
- Small-model tricks: JSON-schema-constrained outputs, role-specific grounding hints, and compressed "cards" passed between stages so context stays small. A truncation-retry function handles incomplete generations.
- Retrieval: Sentence Transformers + ChromaDB for RAG over uploaded documents.
-
Stack: Python, PyTorch, Hugging Face
transformers, FastAPI backend (/boardroom/analyze), Streamlit multipage frontend with a landing page and a "Command Center" page. - Modes: 2 intelligence modes, 3 response formats, and auto or manual agent selection.
Why Does Open Innovation Matter?
A closed API would have meant per-token costs on every multi-agent debate, which is a lot of calls for one decision, and my clients' business data leaving their machine. Open weights let me quantize the model to fit a 4 GB laptop GPU, constrain its output with schemas, and tune prompts per role. That is what makes a private, near-zero marginal cost advisory product possible for the small businesses I'd sell it to.
Top comments (0)