legal_document_review · services · workflow

Harvey's Word Add-In enables document-wide edits on 100+ page legal documents via orchestrator-subagent architecture

Harvey's initial Word Add-In was optimized only for targeted local edits, leaving longer documents requiring complex multi-page coordinated changes unsupported. Direct OOXML manipulation by LLMs produced poor outcomes and degraded reasoning quality, while one-shot edits on long documents missed large portions due to position bias.

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 · User submits edit query
A user submits a single edit query against a document in Harvey's Word Add-In.
Tools used
HarveyOffice JavaScript APIOffice Open XMLVault
Outcome

Harvey's Word Add-In now supports editing 100+ page documents with a single query, transforming hours of manual legal editing into a single seamless interaction.

What failed first

Direct OOXML generation by LLMs produced invalid or schema-nonconformant XML and caused regression on legal reasoning tasks. One-shot edits on long documents suffered from position bias, missing content in the middle even with explicitly long-context models.

Results
Time savedtransforming hours of manual effort into a single seamless interaction
Volume100+
Source

https://www.harvey.ai/blog/enabling-document-wide-edits-in-harveys-word-add-in

How we source this →

Grounding & classification
Source type: technical build writeup
29 fields verified against source quotes.
agentic workflowcontent generationdocument aimulti agent workflowcontractemailknowledge basefailure mode describedmetric backedproduction runtime claimedtools describedworkflow describedlegalemployee productivitytime savedtechnical build writeuplegal document reviewlegal opsagentic task executiondocument to record