Answer Gmail support emails from your docs with Gemini and Slack

by Daniel Shashko ✓ · 3 views · created 2026-08-31

What this workflow does

This AI workflow has 33 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Gmail, Google Gemini Chat Model and Slack.

How it runs

Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).

1. Indexing Settings (Edit Fields (Set)): sets 6 fields: docs_sitemap, url_must_contain, max_pages…
2. Answer Settings (Edit Fields (Set)): sets 5 fields: embedding_model, dimensions, passages…
3. Fetch The Sitemap (HTTP Request): calls an HTTP API
4. Read The Question (Code): runs custom JavaScript code
5. Read The Sitemap (Code): runs custom JavaScript code
6. Embed The Question (HTTP Request): calls an HTTP API (POST)
7. Is It An Index Of Sitemaps? (If): checks a condition and branches into true / false
8. Load The Whole Index (Data table): get
9. Fetch Each Child Sitemap (HTTP Request): calls an HTTP API
10. Gather Every Page URL (Merge): merges the data from its input branches

…plus 20 more steps. See the full node list below.

Services it uses

GmailGoogle Gemini Chat ModelSlack

Before you upgrade to n8n 3.0

Nodes used (12)

• Manual Triggern8n-nodes-base.manualTrigger
• Edit Fields (Set)n8n-nodes-base.set
• HTTP Requestn8n-nodes-base.httpRequest
• Coden8n-nodes-base.code
• Ifn8n-nodes-base.if
• Mergen8n-nodes-base.merge
• Data tablen8n-nodes-base.dataTable
• Gmail Triggern8n-nodes-base.gmailTrigger
• Basic LLM Chain@n8n/n8n-nodes-langchain.chainLlm
• Google Gemini Chat Model@n8n/n8n-nodes-langchain.lmChatGoogleGemini
• Gmailn8n-nodes-base.gmail
• Slackn8n-nodes-base.slack

From the author

Quick Overview This workflow indexes your documentation from a sitemap into an n8n Data Table using Google Gemini embeddings, then monitors a Gmail support label to draft grounded replies from the closest passages or escalate gaps to Slack and log them for…

View the original on n8n.io → Check your own copy