← back
Knowledge Graphs in Litigation Agents — Tom Smoker, WhyHow
Original: Knowledge Graphs in Litigation Agents — Tom Smoker, WhyHow
Takeaway
For litigation and other relation-heavy domains, schematized knowledge graphs beat vector RAG because the value is in explicit multi-hop connections.
Summary
- WhyHow finds class-action mass-tort cases before law firms by scraping the web, extracting structured graphs of victims, products, ingredients, concentrations, and IDs, then qualifying with proprietary signals.
- Schema-driven KG approach: explicit relations (person→product→ingredient→concentration) enable multi-hop analytics that vector RAG can't do.
- Multi-agent system on top of the graph handles scraping, qualification, and case packaging for partner law firms.
- Argues graphs win in legal because relations and provenance are the value, not similarity search.
knowledge-graphsagentslegal
Original description
Structured Representations are pretty important in the law, where the relationships between clauses, documents, entities, and multiple parties matter. Structured Representation means Structured Context Injection. Better Context, Less Hallucinations. We walk through a couple of case studies of systems that we’ve built in production for legal use-cases - from recursive contractual clause retrieval, to HITL legal reasoning news agents. You'll gain insights into how structured representations significantly improve the effectiveness and reliability of legal agents. ---related links--- https://www.linkedin.com/in/thomassmoker https://www.whyhow.ai/