legal_document_review · services · workflow
Harvey Builds Enterprise-Grade RAG Systems for Legal and Professional Services Using LanceDB and Postgres
Deploying enterprise RAG for legal and professional services requires solving for sparse vs. dense retrieval trade-offs, performance and accuracy at massive scale, complex domain-specific data structures, and strict data privacy requirements that prevent sensitive client documents from leaving customer-controlled environments.
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 · Multi-source document ingestion
Documents arrive from three sources: user-uploaded thread files, long-term Vault project documents, and private and public third-party legal data sources providing regulations, laws, and statutes.
Tools used
LanceDB EnterprisePostgresPGVector
Outcome
Harvey now serves users in 45 countries, and its PwC Tax AI collaboration produced a system 91% preferred over off-the-shelf ChatGPT, bringing highly accurate answers to hundreds of professional service firms worldwide.
Results
Time saved<2s P50
Volume91%
Grounding & classification
Source type: technical build writeup
23 fields verified against source quotes, 1 dropped as unverifiable.
document aienterprise searchknowledge searchragknowledge basepolicy documentmetric backednamed customerproduction runtime claimedtools describedworkflow describedlegalprofessional servicesaccuracy improvementtechnical build writeuplegal document reviewlegal opsrag answering