WhatsApp Grounded Customer Research

Overview

Per inbound WhatsApp message: classify intent, route free-form questions through Scavio + LLM, return sourced answer to user.

Trigger

Inbound WhatsApp message

Schedule

Event-driven (per inbound)

Workflow Steps

WhatsApp Trigger node fires on incoming message

n8n native node.

Switch node: scripted vs free-form intent

Regex or quick-classifier.

Free-form path: Scavio HTTP node

Search user's question scoped to your domain.

LLM node: ground answer in top 3 Scavio results

Strict citation prompt.

WhatsApp Send node: reply with grounded answer + source links

Conversational tone.

Log Q + A + sources to Postgres

For later analysis of common questions.

Python Implementation

Python

# n8n is the deliverable; HTTP node body shape:
# POST https://api.scavio.dev/api/v1/search
# headers: { x-api-key: <key> }
# body: { "query": "{{$json.messages[0].text.body}} site:yourcompany.com" }

JavaScript Implementation

JavaScript

// Same — n8n's HTTP node is the integration surface.

Platforms Used

Google

Web search with knowledge graph, PAA, and AI overviews

Frequently Asked Questions

Per inbound WhatsApp message: classify intent, route free-form questions through Scavio + LLM, return sourced answer to user.

This workflow uses a inbound whatsapp message. Event-driven (per inbound).

This workflow uses the following Scavio platforms: google. Each platform is called via the same unified API endpoint.

Yes. Scavio's free tier includes 500 credits per month with no credit card required. That is enough to test and validate this workflow before scaling it.

WhatsApp Grounded Customer Research Workflow