Handle WhatsApp HVAC reception with Gemini, Claude, and Meta WhatsApp API
Needs changesNeeds changes. This template uses 2 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes), SerpApi (Google Search). 2 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 27 nodes and runs on WhatsApp events (messages). Along the way it connects WhatsApp Business Cloud, Anthropic Chat Model, Postgres Chat Memory and SerpApi (Google Search). It also calls openrouter.ai over HTTP.
How it runs
Trigger: On WhatsApp events (messages).
- Route by Type (Switch): routes items into 3 branches
- Get Voice Note URL (WhatsApp Business Cloud): media url get
- Get Photo URL (WhatsApp Business Cloud): media url get
- Prepare Text Message (Edit Fields (Set)): sets 1 field: text
- Download Voice Note (HTTP Request): calls an HTTP API
- Download Photo (HTTP Request): calls an HTTP API
- Save to Inbox (Data table): uses Data table
- Convert Voice to Base (Extract from File): extracts data from a file (binary to propery)
- Convert Photo to Base (Extract from File): extracts data from a file (binary to propery)
- Wait: waits 10 seconds
…plus 12 more steps. See the full node list below.
Services it uses
HTTP calls to: openrouter.ai
Before you upgrade to n8n 3.0
2 things in this workflow are removed in n8n 3.0. Fix them before you upgrade:
- AI Agent v1 (old agent modes) in Receptionist Agent (v1.9): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
- SerpApi (Google Search) in Web Search: no direct replacement: call the SerpApi REST API with an HTTP Request tool, or use a verified community node.
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Receptionist Agent (v1.9) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
| SerpApi (Google Search) Web Search | No direct replacement: call the SerpApi REST API with an HTTP Request tool, or use a verified community node |
Nodes used (15)
- WhatsApp Trigger
n8n-nodes-base.whatsAppTrigger - Switch
n8n-nodes-base.switch - WhatsApp Business Cloud
n8n-nodes-base.whatsApp - HTTP Request
n8n-nodes-base.httpRequest - Extract from File
n8n-nodes-base.extractFromFile - Edit Fields (Set)
n8n-nodes-base.set - Data table
n8n-nodes-base.dataTable - Wait
n8n-nodes-base.wait - AI Agent
@n8n/n8n-nodes-langchain.agent - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic - Postgres Chat Memory
@n8n/n8n-nodes-langchain.memoryPostgresChat - SerpApi (Google Search)
@n8n/n8n-nodes-langchain.toolSerpApi - Calculator
@n8n/n8n-nodes-langchain.toolCalculator - Code
n8n-nodes-base.code - Filter
n8n-nodes-base.filter
From the author
Quick overview This workflow acts as a WhatsApp AI receptionist: it receives text, voice notes, and photos via WhatsApp Cloud API, transcribes audio and describes images through OpenRouter, then uses Anthropic Claude with PostgreSQL chat memory to reply,…