Automated HR Service System with WhatsApp, GPT-4 Classification & Google Workspace
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 57 nodes and runs on WhatsApp events (messages). Along the way it connects WhatsApp Business Cloud, OpenAI, OpenAI Chat Model and Supabase Vector Store and 5 more.
How it runs
Trigger: On WhatsApp events (messages).
- Delegatory LLM (Basic LLM Chain): sends a prompt to an LLM, with model: OpenAI Chat Model
- Merge: merges the data from its input branches
- Merge: merges the data from its input branches
- Merge: merges the data from its input branches
- Switch: routes items into 5 branches
- Code: runs custom JavaScript code
- Verify Message Type (Switch): routes items into 3 branches
- Edit Fields (Edit Fields (Set)): sets 1 field: messages[0].text.body
- Email Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 2 tools (Gmail, dept head email)
- Shortlist Agent (AI Agent): runs an AI agent, with model: OpenAI Chat Model; 3 tools (n8n, JD tool, applicants); output parser: Structured Output Parser
…plus 18 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in HR Chatbot (v1.7), Shortlist Agent (v1.7): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
Rather not rewrite it? Many of these flows can be rebuilt in Make (free plan).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) HR Chatbot (v1.7), Shortlist Agent (v1.7) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (21)
- WhatsApp Trigger
n8n-nodes-base.whatsAppTrigger - Switch
n8n-nodes-base.switch - OpenAI
@n8n/n8n-nodes-langchain.openAi - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Edit Fields (Set)
n8n-nodes-base.set - HTTP Request
n8n-nodes-base.httpRequest - Code
n8n-nodes-base.code - Supabase Vector Store
@n8n/n8n-nodes-langchain.vectorStoreSupabase - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Gmail Tool
n8n-nodes-base.gmailTool - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Google Calendar Tool
n8n-nodes-base.googleCalendarTool - Google Sheets
n8n-nodes-base.googleSheets - Google Sheets Tool
n8n-nodes-base.googleSheetsTool - Call n8n Workflow Tool
@n8n/n8n-nodes-langchain.toolWorkflow - If
n8n-nodes-base.if - Merge
n8n-nodes-base.merge - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - AI Agent
@n8n/n8n-nodes-langchain.agent - Vector Store Question Answer Tool
@n8n/n8n-nodes-langchain.toolVectorStore - WhatsApp Business Cloud
n8n-nodes-base.whatsApp
From the author
Who is this for? This workflow is ideal for HR teams, startups, and enterprises that want to handle employee interactions through WhatsApp and automate responses using LLM (OpenAI) and intelligent routing. What problem is this workflow solving? Managing…