WhatsApp support routing

A workflow explanation by Jayson Bautista · Original robot guide: Dennice

1 / 24
Read the complete transcript
  1. The question: Let’s follow whatsapp support routing through the source diagram.
  2. The challenge: A diagram shows the connections, but not every configuration or runtime result.
  3. Our route: Therefore, we’ll trace the visible steps and finish with the evidence limits.
  4. Receive a message: A WhatsApp Trigger starts the diagram.
  5. Receive a message: Customer Log and an If branch lead into sheet updates and field preparation.
  6. Receive a message: Set Fields prepares data before classification.
  7. Classify the request: An AI Agent Classifier connects to a Gemini model.
  8. Classify the request: An output parser feeds an If node.
  9. Classify the request: The exact classification labels and routing condition are not shown.
  10. Escalate a branch: One branch sends a WhatsApp message.
  11. Escalate a branch: Slack Send Message follows on that branch.
  12. Escalate a branch: A HubSpot create-or-update-contact node is also visible.
  13. Use FAQ context: The other branch reads rows before an AI Agent Responder.
  14. Use FAQ context: The responder has Simple Memory and a SkincareFAQs Sheets tool.
  15. Use FAQ context: Parsed output routes to WhatsApp, HubSpot and a sheet update.
  16. Scope of evidence: SkincareFAQs is a visible tool label, not evidence of a client relationship.
  17. Scope of evidence: Response quality, escalation thresholds and production use are unverified.
  18. Scope of evidence: The case study describes the visible routing and integrations only.
  19. Recap: start: A WhatsApp Trigger starts the diagram.
  20. Recap: process: An AI Agent Classifier connects to a Gemini model.
  21. Recap: route: One branch sends a WhatsApp message.
  22. Recap: output: The other branch reads rows before an AI Agent Responder.
  23. Evidence boundary: The supplied screenshots show architecture. They do not verify production outcomes.
  24. Takeaway: Follow the connections, inspect the source, and validate configuration before operational use.

Source: local automation4 screenshot. This film explains visible node connections; prompts, credentials and execution results are not supplied. Robot and props are explanatory illustrations. Back to the case study.