Problem
Claims adjusters spend the front of every claim on manual reading, field extraction, priority assessment, and routing, before any actual claims work begins. At volume, that is repeatable cognitive work.
Solution
An n8n workflow triggered by incoming claims. Claude AI reads the full unstructured description, extracts all key fields, assigns priority and specialist routing, flags fraud indicators, and fires alerts. Critical claims go directly to a named specialist with a full brief. Standard claims get an automatic acknowledgment.
Demo
Webhook receives claim payload from any intake form or system. Normalize Claim Input reads from the webhook body and standardizes all fields with safe fallbacks. Build Extraction Prompt constructs a detailed Claude prompt with the full claim context and a precise JSON schema: priority rules, category taxonomy, specialist routing logic, SLA thresholds, fraud indicator patterns, and a claimant message template. HTTP Request calls Claude 3.5 Sonnet via OpenRouter. Parse Triage Result extracts the structured JSON with error fallback to a senior adjuster. IF node branches on CRITICAL/HIGH vs STANDARD/LOW. High path: Assign Specialist Code node maps recommended_specialist to a named adjuster with email and queue. Gmail sends a full adjuster brief (priority badge, SLA deadline, extracted fields, red flags, missing info checklist, confidence score). Slack posts an urgent alert. Google Sheets logs the claim. Standard path: Gmail sends claimant acknowledgment using Claude's pre-written message. Slack posts a routine digest. Error Trigger catches failures and routes to a Slack error alert. IF node uses typeVersion 2.2 to avoid known routing bugs in earlier versions.
Tech Stack
- n8n
- Claude AI
- Gmail API
- Google Sheets API
- Slack
- JavaScript
- Conditional Routing