NLP & LLMsMachine LearningData Engineering
AI-Powered Legal Citation Analyzer
Client capstone with Wolters Kluwer: Agentic RAG system using Neo4j knowledge graphs and multi-LLM orchestration to automate legal precedent research.
The Problem
Context & Challenge
Attorneys spend hours manually verifying if legal precedents remain valid ("Good Law"). Wolters Kluwer needed an AI-powered solution to automate citation analysis and reduce research time.
The Approach
Architecture & Implementation
Built an agentic RAG system with Neo4j knowledge graphs storing 3,500+ ADA cases and 5,500+ citations. Orchestrated multi-LLM pipelines (Claude 3.5 Sonnet, Llama 3-70B) using LangChain and LangGraph on AWS Bedrock, with a Streamlit interface.
The Results
Impact & Metrics
Delivered production MVP with dual-mode interface: Case Lookup for citation analysis + Conversational Legal Research chatbot for natural language queries.
Key Result
Delivered production MVP with dual-mode interface: Case Lookup + Conversational Legal Research
Technologies & Methods
PythonNeo4jLangChainLangGraphRAG/GraphRAGClaude 3.5 SonnetLlama 3-70BAWS BedrockStreamlit