Draft Gmail replies to stock and visit inquiries with Claude Haiku
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 19 nodes and runs on a schedule (every 5 minutes). Along the way it connects Gmail, Text Classifier, Anthropic Chat Model and Information Extractor and 1 more.
How it runs
Trigger: On a schedule (every 5 minutes).
- Config (Edit Fields (Set)): sets 4 fields: inboxAddress, signature, timezone…
- Get new inquiry emails (Gmail): get many (message)
- Loop over emails (Loop Over Items (Split in Batches)): loops over the items in batches
- Classify inquiry (Text Classifier): classifies text into categories with AI, with model: Claude Haiku 4.
- Extract product category (Information Extractor): extracts structured fields from text with AI, with model: Claude Haiku 4.
- Extract visit request (Information Extractor): extracts structured fields from text with AI, with model: Claude Haiku 4.
- Label as needs-human (Gmail): add labels (message)
- Look up stock (Data table): get (row)
- Look up visit slots (Data table): get (row)
- Combine products (Aggregate): combines items into one
…plus 6 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 (11)
- Schedule Trigger
n8n-nodes-base.scheduleTrigger - Gmail
n8n-nodes-base.gmail - No Operation, do nothing
n8n-nodes-base.noOp - Text Classifier
@n8n/n8n-nodes-langchain.textClassifier - Anthropic Chat Model
@n8n/n8n-nodes-langchain.lmChatAnthropic - Loop Over Items (Split in Batches)
n8n-nodes-base.splitInBatches - Information Extractor
@n8n/n8n-nodes-langchain.informationExtractor - Data table
n8n-nodes-base.dataTable - Aggregate
n8n-nodes-base.aggregate - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Edit Fields (Set)
n8n-nodes-base.set
From the author
Quick Overview This workflow checks a Gmail inbox every 5 minutes for new inquiry emails, uses Anthropic Claude to classify them as stock or store-visit requests, looks up matching data in n8n Data Tables, and saves a suggested reply as a Gmail draft while…