Templates / Review contract clauses against your playbook with Google Drive and Claude

Review contract clauses against your playbook with Google Drive and Claude

Ready for 3.0

by SEVENEDGE ✓ · 7 views · created 2026-08-26 · Document Extraction, AI Summarization

Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.

What this workflow does

This AI workflow has 24 nodes and runs on Google Drive events (file created) (plus 1 other trigger). Along the way it connects Google Drive, Anthropic Chat Model and Google Sheets. It also calls api.anthropic.com over HTTP.

How it runs

Trigger: On Google Drive events (file created) (plus 1 other trigger).

  1. Retrieve Contract from Drive (Google Drive): download
  2. Configure Review Settings (Edit Fields (Set)): sets 9 fields: ourSide, playbook, hardLimits…
  3. Encode File to Base (Code): runs custom JavaScript code
  4. Prepare Extraction Request (Code): runs custom JavaScript code
  5. Post Extraction to Anthropic API (HTTP Request): calls api.anthropic.com (POST)
  6. Process Extracted Clauses (Code): runs custom JavaScript code
  7. Batch Process Clauses (Loop Over Items (Split in Batches)): loops over the items in batches
  8. Collate Clause Findings (Code): runs custom JavaScript code
  9. Evaluate Clauses with Agent (AI Agent): runs an AI agent, with model: Claude AI Model for Review; output parser: Structure Assessment Results
  10. Determine Escalation Necessity (If): checks a condition and branches into true / false

…plus 10 more steps. See the full node list below.

Services it uses

Google DriveAnthropic Chat ModelGoogle Sheets

HTTP calls to: api.anthropic.com

Before you upgrade to n8n 3.0

Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.

Nodes used (13)

From the author

Quick overview This workflow watches a Google Drive folder for new contracts, uses Anthropic Claude to extract and assess clauses against your legal playbook and hard limits, then aggregates a verdict, optionally pauses for a human decision, logs the results…

Excerpt from SEVENEDGE's description on n8n.io.

View the original on n8n.io → Check your own copy

Get the weekly “what broke” email

New templates, newly broken ones, and n8n release changes. One short email a week.

Form not loading? Subscribe here.