One-Day AI Agent: Multi-Agent Problem Solver

Overview

This project implements a multi-agent system where two agents (Creative Brainstormer and Harsh Critic) autonomously debate a complex problem for multiple rounds before an Editor agent produces a final structured solution.

Key Concepts Demonstrated

• Multi-agent orchestration (LangGraph)
• Explicit state management
• Conditional routing logic
• Autonomous back-and-forth reasoning
• Final synthesis agent

Architecture

Creative -> Critic -> Creative -> Critic -> ... -> Editor -> END

State includes:

• problem
• history
• round counter
• max rounds
• last speaker

Routing is controlled by the route_next() function.

How to Run

Notebook:

Open one_day_multi_agent.ipynb and run all cells.

Script:

python app.py

Example Use Case

Design a 2-week plan to ship an MVP for an AI-powered project risk predictor.

Prerequisites

You need a Groq API Key to run the agent.

1. Get a free key from Groq.
2. Create a .env file in the root directory:

   GROQ_API_KEY=""

Installation

macOS / Linux

# Set up Python environment
pyenv local 3.11.3
python -m venv .venv
source .venv/bin/activate
pip install --upgrade pip
pip install -r requirements.txt

Windows (PowerShell)

# Set up Python environment
pyenv local 3.11.3
python -m venv .venv
.venv\Scripts\Activate.ps1
python -m pip install --upgrade pip
pip install -r requirements.txt