Harvey Boosts Contract Review Efficiency with Multi-Agent System

Harvey, an AI-driven platform for legal contract review, has overhauled its playbook review engine to tackle the complexities of contract negotiations. The revamped system introduces a multi-agent system architecture that enhances accuracy while addressing scalability challenges, promising significant efficiency gains for legal teams.

The new system improves risk classification accuracy by 18% and redline quality by 34%, according to Harvey's internal benchmarks. It leverages multiple autonomous agents working in parallel, coordinated by an orchestrator agent that ensures consistency and quality in the final output.

Contract review is deceptively complex, with each contract containing conditional logic, interdependent clauses, and terms that vary based on deal context. The multi-agent architecture resolves these issues by assigning subagents to focus on individual rules while an orchestrator agent reconciles their outputs.

The system employs several optimizations, including streaming results, prompt caching, and selectively using the best AI models for each task. For example, Harvey's team adjusted the platform to switch models depending on whether the task involves classification, redlining, or summarization, balancing quality, cost, and speed.

Harvey's upgrades place it at the forefront of the trend towards more sophisticated agent frameworks in enterprise AI, particularly in domains requiring high accuracy and context sensitivity. The global multi-agent systems market is expected to grow rapidly, driven by industries like legal tech that demand automation for labor-intensive tasks.