AI-powered customer feedback routing with Gmail, Slack, Pipedrive, Zendesk & Notion
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 18 nodes and runs manually, when you click “Execute workflow” (plus 1 other trigger). Along the way it connects Gmail, Pipedrive, Slack and Zendesk and 2 more.
How it runs
Trigger: Manually, when you click “Execute workflow” (plus 1 other trigger).
- Set CSM email (Edit Fields (Set)): sets 1 field: CSM email
- Data agent (AI Agent): runs an AI agent, with model: LLM; 3 tools (Get many messages in Gmail, Get many notes in Pipedrive, Search for messages in Slack); memory: Simple Memory
- Signals agent (Basic LLM Chain): sends a prompt to an LLM, with model: LLM; output parser: Structured Output Parser
- Clustering agent (Basic LLM Chain): sends a prompt to an LLM, with model: LLM; output parser: Structured Output Parser
- Action agent (AI Agent): runs an AI agent, with model: LLM; 4 tools (Send a message in Gmail, Send a message in Slack, Create a ticket in Zendesk, Create a database page in Notion)
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 (13)
- Gmail Tool
n8n-nodes-base.gmailTool - Simple Memory
@n8n/n8n-nodes-langchain.memoryBufferWindow - Pipedrive Tool
n8n-nodes-base.pipedriveTool - Slack Tool
n8n-nodes-base.slackTool - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Zendesk Tool
n8n-nodes-base.zendeskTool - AI Agent
@n8n/n8n-nodes-langchain.agent - Basic LLM Chain
@n8n/n8n-nodes-langchain.chainLlm - Notion Tool
n8n-nodes-base.notionTool - Schedule Trigger
n8n-nodes-base.scheduleTrigger - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Edit Fields (Set)
n8n-nodes-base.set - Manual Trigger
n8n-nodes-base.manualTrigger
From the author
Who’s it for This workflow is built for B2B SaaS and CX teams that are drowning in unstructured customer feedback across tools. It’s ideal for Customer Success, Product and Support leaders who want a light “voice of customer engine” without rebuilding their…