Draft and review grounded support email replies with Gmail, OpenAI and Claude
Ready for 3.0Ready for 3.0. This template uses no nodes that n8n 3.0 removes. No removed nodes, versions or helpers found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 47 nodes and runs manually, when you click “Execute workflow” (plus 4 other triggers). Along the way it connects Google Drive, Postgres, Postgres PGVector Store and Embeddings OpenAI and 2 more.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 4 other triggers).
- List KB Files (Google Drive): work with file folder
- Normalize Ticket (Code): runs custom JavaScript code
- Query Reply Metrics (Postgres): run a query
- Fetch Ingest Ledger (Postgres): run a query
- Mask PII (Code): runs custom JavaScript code
- Format Metrics Email (Code): runs custom JavaScript code
- Select New Or Changed (Code): runs custom JavaScript code
- Classify Ticket (Basic LLM Chain): sends a prompt to an LLM, with model: Classifier Model; output parser: Classification Schema
- Send Metrics Digest (Gmail): uses Gmail
- Download KB File (Google Drive): download
…plus 21 more steps. See the full node list below.
Services it uses
Before you upgrade to n8n 3.0
Nothing in this workflow is removed in n8n 3.0, so it should import and run after the upgrade.
Nodes used (18)
- Manual Trigger
n8n-nodes-base.manualTrigger - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Google Drive
n8n-nodes-base.googleDrive - Postgres
n8n-nodes-base.postgres - Code
n8n-nodes-base.code - Postgres PGVector Store
@n8n/n8n-nodes-langchain.vectorStorePGVector - Embeddings OpenAI
@n8n/n8n-nodes-langchain.embeddingsOpenAi - Default Data Loader
@n8n/n8n-nodes-langchain.documentDefaultDataLoader - Recursive Character Text Splitter
@n8n/n8n-nodes-langchain.textSplitterRecursiveCharacterTextSplitter - Gmail Trigger
n8n-nodes-base.gmailTrigger - Webhook
n8n-nodes-base.webhook - OpenRouter Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenRouter - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Switch
n8n-nodes-base.switch - AI Agent
@n8n/n8n-nodes-langchain.agent - If
n8n-nodes-base.if - Gmail
n8n-nodes-base.gmail
From the author
Quick overview This workflow ingests a Google Drive knowledge base into Postgres/pgvector, then drafts and quality-checks support email replies using OpenRouter LLMs and OpenAI embeddings, automatically replying in Gmail only when citations and critic scores…