Back to Projects
Completed

Juris AI

AI-powered legal contract analysis and negotiation assistant

Juris AI screenshot 1
Timeline

1 week

Role

Full Stack Developer

Team

Solo

Technology Stack

TypeScriptNext.jsNode.jsExpressRedisGeminiPassport.jsTailwind CSS

Challenges

  • Secure in-memory file processing
  • Reliable contract summarization
  • Ephemeral data handling with Redis

Insights

  • AI-driven document analysis
  • Privacy-first system design
  • File parsing and text extraction pipelines

Overview

Juris AI is an intelligent legal assistant built to simplify complex legal contracts.
It leverages generative AI to break down dense legal language, highlight critical clauses, and provide actionable negotiation insights — all while maintaining a strong privacy-first architecture.

The platform is designed to assist users in understanding contracts, not to replace professional legal advice.

Note: All uploaded documents are processed ephemerally and are never permanently stored.


Key Features

Core Capabilities Implemented

  • AI-Powered Contract Summaries
    Converts dense legal clauses into clear, easy-to-understand summaries

  • Key Clause & Term Highlighting
    Automatically identifies important legal terms and sections within contracts

  • Negotiation Insights
    Provides intelligent suggestions to help users strengthen their negotiation position

  • Privacy-First Processing
    Files are processed entirely in-memory and discarded immediately after analysis

  • Temporary Data Storage with TTL
    Extracted text is cached briefly in Redis and deleted automatically post-processing

  • Flexible Authentication
    Supports Google OAuth and email/password authentication using Passport.js


Tech Stack Overview

Frontend

  • Next.js (App Router)
  • Tailwind CSS

Backend

  • Node.js
  • Express

AI Engine

  • Google Gemini

Authentication

  • Passport.js
    • Google OAuth 2.0
    • Local email/password strategy

Storage & File Handling

  • Redis (temporary text storage with TTL)
  • PDF and DOCX file upload support

Data Flow & Privacy Model

User privacy and data security are central to Juris AI’s architecture.

End-to-End Data Flow

  1. Authentication
    User securely logs in via Google OAuth or email/password.

  2. File Upload
    User uploads a legal contract (PDF or DOCX) through the frontend.

  3. Text Extraction & Temporary Storage

    • Backend extracts raw text from the document
    • Text is stored temporarily in Redis with a short TTL
    • Original file is immediately discarded
  4. AI Analysis
    Extracted text is sent to the Gemini API for summarization and insights.

  5. Result Delivery
    AI-generated summaries, highlighted clauses, and negotiation insights are returned to the user dashboard.

  6. Automatic Data Deletion
    Redis entries are deleted immediately after successful processing.


Outcome

Juris AI demonstrates a privacy-first, AI-driven document analysis system, combining secure file handling, ephemeral data storage, and structured AI outputs to make legal contracts more accessible and understandable.