ConTrack: AI-Powered Contract Intelligence

Overview

ConTrack—derived from Contract + Track—is designed to transform contract confusion into clarity. Contracts are the backbone of business, yet they remain complex, time-consuming, and difficult to manage. ConTrack leverages AI to streamline contract analysis, helping professionals understand agreements faster and mitigate risks effectively. Powered by IBM Granite and an Agentic RAG system, ConTrack extracts key terms, assigns obligations, scores compliance risks, and tracks critical deadlines. Users can instantly query contracts, receive concise summaries, and automate key workflows. With AI-driven automation, ConTrack ensures contracts work for you—not against you.

Features

• AI-Powered Contract Analysis: Extracts key terms, obligations, and clauses from contracts.
• Compliance Obligatory Score (COS): Evaluates contract risk and compliance.
• Obligation Tracking: Tracks commitments for each party and generates reminders.
• AI Query System: Enables natural language queries to quickly retrieve contract insights.
• Summarization & Insights: Generates concise summaries and key takeaways.
• Integration with Trello: Automates task management based on contract obligations.
• Event & Timeline Tracking: Automatically tracks key contract milestones.

Installation

Front-End Setup

1. Navigate to the client directory:

   cd client

2. Install dependencies:

   npm install

3. Run the development server:

   npm run dev

Back-End Setup

Creating the Virtual Environment

1. Navigate to the server directory:

   cd server

2. Create a virtual environment named venv:

   python -m venv venv

3. Activate the virtual environment:
   • Windows:

     venv\Scripts\activate

   • MacOS/Linux:

     source venv/bin/activate

4. Install the required packages:

   pip install -r requirements.txt

Generating an LLM API Key from Watson Cloud

1. Create a .env file in the server directory with the following content (fill in your keys and credentials):

   IBM_WATSONX_APIKEY="your-api-key"
   IBM_WATSONX_PROJECT_ID="your-project-id"
   IBM_WATSONX_URL="your-watson-url"

Starting the Service

Run the backend service:

python app.py

Tools & Technologies Used

Programming Languages

• Python (Flask backend)
• JavaScript (React frontend)

Databases

• ChromaDB

AI Models

• IBM Granite-3.1-8B-Instruct
• Granite Embedding 107M Multilingual

Architecture

👥 Team

Gabriel Kuek

Rafael Macam

Calvin Septyanto

Made by Hawk Tuah Reborn