AI Support Sentiment Detector & Escalator

1. In your automation platform, add a Gmail trigger that watches for new customer emails (e.g., labeled "Support" or sent to support@yourcompany.com). 2. Add a Set/Function node to extract the email body, subject, sender name, and email address. 3. Add an HTTP Request node to call the Claude API (POST https://api.anthropic.com/v1/messages). Set headers: x-api-key: {{YOUR_ANTHROPIC_API_KEY}}, anthropic-version: 2023-06-01, Content-Type: application/json. Use model claude-sonnet-4-20250514. 4. In the request body, instruct Claude to analyze the message sentiment and return JSON: {"sentiment": "angry|frustrated|neutral|satisfied|positive", "confidence": 0.0-1.0, "escalation_reason": "brief explanation if negative", "customer_emotion_summary": "1-sentence summary of how the customer feels"}. 5. Add a Router/Switch node based on the sentiment value. Route angry/frustrated messages to an escalation branch and positive messages to a wins branch. 6. For escalations: add a Slack node that posts to #escalations with @here mention, customer name, sentiment score, escalation reason, and the original message excerpt. Include a link to the email thread. 7. For positive messages: add a Google Sheets node to log to a "Customer Wins" sheet for team morale and review. 8. Add a master Google Sheets logging node that captures ALL messages: Timestamp, Customer, Subject, Sentiment, Confidence, Escalated (Y/N), Resolution Status.