Auto-Review Contract Risk and Rewrite Clauses with n8n

Google Drive PDF upload → Groq LLM clause extraction → Notion standard library comparison → risk report & rewrite → Slack alert for high-risk → Notion archive

Who

Legal, procurement, or compliance teams that need to batch-review vendor contracts against company standard clauses

You get

Automatically extract key clauses, assess risk levels, generate negotiation recommendations and rewritten text upon contract upload; trigger Slack alerts for high-risk contracts and archive to Notion

You need

n8n · Google Drive · Notion · Slack

Steps

1. Configure contract upload trigger and text extraction

   In n8n, set up a Google Drive Trigger node in specificFolder mode pointing to your watch folder. When a new file uploads, the Download File node fetches it, the Check if PDF node branches on MIME type; if PDF, route through Extract content from PDF, otherwise through the Extract Content code node to convert binary to text. Output a JSON with fileContent for downstream nodes.

2. Extract clauses and compare against Notion standards

   Feed contract text into the Extract Contract Clauses (Basic LLM Chain) node, connected to Groq Chat Model3 (e.g., llama-3.3-70b-versatile) and Structured Output Parser3, enforcing JSON output with fields: payment_terms, penalties, sla, termination, renewal, liability, data_protection. In parallel, the Fetch Standard Clauses node queries the Notion Standard Clause Library database. The Merge Vendor + Standards node joins both streams, then the Compare Vendor vs Standard Clauses code node compares each clause type and outputs deviation analysis.

   Execution prompt · Source text。Extract Contract Clauses node text parameter (n8n Basic LLM Chain)

   Copy prompt

   =From the contract below extract:
   
   - Payment Terms
   - Late Payment Penalties
   - SLA / Service Levels
   - Termination Clause
   - Renewal Terms
   - Liability Clause
   - Data Protection Clause
   
   Return JSON format:
   
   {
    "payment_terms":"",
    "penalties":"",
    "sla":"",
    "termination":"",
    "renewal":"",
    "liability":"",
    "data_protection":""
   }
   
   Contract:
   {{ $json.fileContent || $json.text }}

   Execution prompt · Source text。Extract Contract Clauses node messages.messageValues[0].message (system message)

   Copy prompt

   You are a legal contract analyst. Extract key procurement clauses from contracts. Return STRICT JSON.

3. Generate legal risk analysis report

   Pass the comparison result into the AI Risk Analysis & Executive Report node, connected to Groq Chat Model4 (e.g., openai/gpt-oss-120b) and Structured Output Parser4, producing a structured report with overall_risk_level, executive_summary, key_risks, clause_risk_review, missing_or_weak_protections, negotiation_recommendations, and final_recommendation. Then the Prepare Clause Comparison Dataset code node attaches risk levels to each clause for the rewrite stage.

   Execution prompt · Source text。AI Risk Analysis & Executive Report node text parameter (n8n Basic LLM Chain)

   Copy prompt

   =Here is the clause comparison data:
   
   {{ JSON.stringify($json.comparison, null, 2) }}
   
   Create a Legal Risk Report with these sections:
   
   1. Executive Summary
   - Overall contract risk level (Low / Medium / High)
   - Short explanation why
   
   2. Key Risk Findings
   Explain the biggest risks and their impact.
   
   3. Clause-by-Clause Risk Review
   For each deviating clause:
   - Why it is risky
   - Possible business impact
   
   4. Missing or Weak Protections
   Identify gaps vs standard protections.
   
   5. Negotiation Recommendations
   Give clear actions procurement/legal should request.
   
   End with a short conclusion suitable for leadership.

   Execution prompt · Source text。AI Risk Analysis & Executive Report node messages.messageValues[0].message (system message)

   Copy prompt

   You are a senior legal counsel reviewing a vendor contract.  You receive structured clause comparison data between: - Company standard clauses - Vendor contract clauses  Your task: Produce a professional legal risk report for executives.  Write in clear business English. Be concise but insightful. Do NOT output JSON. Use formatted sections.

4. AI rewrite medium- and high-risk clauses

   The Loop Through Clauses node iterates over clauses; the Check If Clause Needs Rewrite node filters out Low-risk items. For clauses needing rewrite, the AI Rewrite Risky Clauses node connects to LLM (e.g., meta-llama/llama-4-scout-17b-16e-instruct) and Parse Rewritten Clause Output structured parser, outputting clause_type and revised_clause per item. The Combine All Revised Clauses code node aggregates all rewritten clauses.

   Execution prompt · Source text。AI Rewrite Risky Clauses node text parameter (n8n Basic LLM Chain)

   Copy prompt

   =You are a senior procurement and legal expert.
   
   Your task is to revise the vendor clause so that it fully aligns with the company’s standard clause and risk requirements.
   
   Instructions:
   - Compare the vendor clause against the company standard clause.
   - Identify gaps or deviations.
   - Rewrite the clause so it aligns with company policy.
   - Preserve clear, enforceable legal language.
   - Do NOT summarize.
   - Do NOT explain.
   - Return only valid JSON.
   
   Return JSON format:
   {
     "clause_type": "",
     "risk_level": "",
     "revised_clause": ""
   }
   
   Clause Type:
   {{ $json.clause_type }}
   
   Risk Level:
   {{ $json.risk_level }}
   
   Vendor Clause:
   {{ $json.vendor_clause }}
   
   Company Standard Clause:
   {{ $json.standard_clause }}

   Execution prompt · Source text。AI Rewrite Risky Clauses node messages.messageValues[0].message (system message; note: source uses same system message as AI Risk Analysis node, likely shared template configuration)

   Copy prompt

   You are a senior legal counsel reviewing a vendor contract.  You receive structured clause comparison data between: - Company standard clauses - Vendor contract clauses  Your task: Produce a professional legal risk report for executives.  Write in clear business English. Be concise but insightful. Do NOT output JSON. Use formatted sections.

5. Format record and check risk level

   The Format Final Contract Review Record (Edit Fields) node aggregates revised_clauses, overall_risk_level, executive_summary, key_risks, negotiation_recommendations, and final_recommendation from upstream. The Check If Contract Is Risky node tests whether overall_risk_level equals High to decide if a Slack alert should fire.

6. Slack alert and Notion archive

   If risk level is High, the Send Slack Risk Alert node posts a formatted message to the configured channel with risk level, executive summary, key risks, recommendations, and suggested clause rewrites. Then the Create Contract Review Record node creates an entry in the Notion Contract Reviews database, writing Risk Level, Executive Summary, Key Risks, Recommendations, Final Recommendation, and Alternative Clauses. If risk is not High, only the Notion record is created without Slack notification.

   Execution prompt · Source text。Send Slack Risk Alert node text parameter (n8n Slack node message content)

   Copy prompt

   =*HIGH RISK CONTRACT DETECTED*
   
   *Overall Risk Level:* {{ $('Format Final Contract Review Record').item.json.overall_risk_level }}
   *Executive Summary:*
   {{ $('Format Final Contract Review Record').item.json.executive_summary }}
   
   *Key Risks:*
   {{ $('AI Risk Analysis & Executive Report').item.json.output.key_risks.join("\n• ") }}
   
   *Top Recommendations:*
   {{ $('AI Risk Analysis & Executive Report').item.json.output.negotiation_recommendations.join("\n• ") }}
   
   *Suggested Clause Rewrites*
   {{ Object.entries($items('Format Final Contract Review Record')[0].json.revised_clauses)
     .map(([key, value]) => 
       "• *" + key.replace(/_/g," ").replace(/\b\w/g,l=>l.toUpperCase()) + "*\n" + value
     ).join("\n\n") }}

You are an n8n workflow setup assistant. The user wants to replicate the automated contract risk review and clause rewrite flow. Assist in this order:
1. Confirm the user has n8n, Google Drive OAuth, Groq API key, Notion integration, and Slack OAuth.
2. Guide the user to create the Notion Standard Clause Library database (fields: property_clause_type as select, property_standard_text as rich_text, property_risk_level_if_deviates as select) and Contract Reviews database (fields: Risk Level, Executive Summary, Key Risks, Recommendations, Final Recommendation, Alternative Clauses).
3. Advise importing workflow.json or building manually, with special attention to Groq Chat Model model parameters and Structured Output Parser JSON schemas.
4. Remind that PDFs must be text-searchable; scanned PDFs need an upstream OCR node.
5. Suggest testing end-to-end with a sample contract PDF and verifying exact case-sensitivity of Notion field names.