Triage customer feedback emails into deduplicated Linear issues with OpenAI
Ready for 3.0What this workflow does
This AI workflow has 30 nodes and runs on Gmail events (plus 1 other trigger). Along the way it connects Gmail, OpenAI Chat Model, HTTP Request and Linear. It also calls api.linear.app over HTTP.
How it runs
Trigger: On Gmail events (plus 1 other trigger).
- Feedback Rules (Edit Fields (Set)): sets 10 fields: linear_team_key, team_email, min_match_confidence…
- Email Or Weekly Ranking? (If): checks a condition and branches into true / false
- Clean The Email (Code): runs custom JavaScript code
- Read Requested Issues (HTTP Request): calls api.linear.app (POST)
- Real Feedback? (If): checks a condition and branches into true / false
- Rank The Most Requested (Code): runs custom JavaScript code
- Read Open Issues (HTTP Request): calls api.linear.app (POST)
- Mark The Noise As Read (Gmail): mark as read (message)
- Any Requests To Rank? (If): checks a condition and branches into true / false
- List Open Issues For Triage (Code): runs custom JavaScript code
…plus 15 more steps. See the full node list below.
Services it uses
HTTP calls to: api.linear.app
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.
- Still check Gmail Trigger below v1.4 runs as v1.4 (drafts skipped, max emails per poll) (Feedback Email Arrives).
Nodes used (13)
- Gmail Trigger
n8n-nodes-base.gmailTrigger - Schedule Trigger
n8n-nodes-base.scheduleTrigger - Edit Fields (Set)
n8n-nodes-base.set - If
n8n-nodes-base.if - Code
n8n-nodes-base.code - HTTP Request
n8n-nodes-base.httpRequest - Switch
n8n-nodes-base.switch - AI Agent
@n8n/n8n-nodes-langchain.agent - OpenAI Chat Model
@n8n/n8n-nodes-langchain.lmChatOpenAi - Structured Output Parser
@n8n/n8n-nodes-langchain.outputParserStructured - Http Request Tool
n8n-nodes-base.httpRequestTool - Linear
n8n-nodes-base.linear - Gmail
n8n-nodes-base.gmail
From the author
Quick overview This workflow monitors a Gmail inbox for unread customer feedback, uses OpenAI to triage and deduplicate requests against existing Linear issues, and then creates a new issue, adds a comment to a matched issue, or asks the customer for…