legal_document_review · services · workflow
How Agentic Search Unlocks Legal Research Intelligence at Harvey
Traditional retrieval systems reduce legal research to a single query-and-retrieve operation, failing to handle the iterative, multi-source reasoning that complex legal work demands.
How it works
Common implementation structure
How this type of workflow is generally built, generalized across documented cases — not tied to any one vendor's stack. Click any stage to read what happens there. Specific products that implement these stages appear in “Tools commonly seen” below.
Stage 1 · Query Understanding and Planning
The agent analyzes what information is needed and develops a search strategy, identifying relevant knowledge sources for complex queries.
Tools used
HarveyVaultLexisNexis · partneriManage · partnerOpenAI Agent SDKLangSmith
Outcome
Harvey's privacy-preserving evaluation approach improved tool selection precision from near zero to 0.8-0.9, and complex queries now appropriately scale to 3-10 retrieval operations instead of a single tool call.
What failed first
The initial agentic prototype had three failure modes: the model queried only one or two sources when broader coverage was needed, treated nearly every query the same regardless of complexity, and the citation system was built and benchmarked only for single-source queries.
Results
Volume0.8-0.9
Grounding & classification
Source type: technical build writeup
29 fields verified against source quotes.
agentic workflowai agentknowledge searchragsummarizationcontractknowledge basefailure mode describedmetric backedproduction runtime claimedtools describedworkflow describedlegalaccuracy improvementthroughput increasetechnical build writeuplegal document reviewlegal opsagentic task executionrag answering