This n8n workflow automates the process of monitoring customer issues in Linear, analyzing the sentiment of comments, tracking sentiment changes over time, and alerting teams when negativity spikes. It helps support teams proactively address difficult situations before they escalate.

The workflow begins with a scheduled trigger that periodically fetches recent issues from Linear using a GraphQL query. Each issue’s comments are analyzed using an OpenAI language model integrated through the LangChain node to determine overall sentiment. The sentiment results, along with issue details, are then stored or updated in Airtable, capturing transitions from previous sentiment states.

An Airtable trigger monitors updates to sentiment data. When an issue’s sentiment shifts from positive or neutral to negative, a notification is dispatched to a Slack channel, alerting the team for prompt action. Deduplication ensures that notifications are not repeated for the same sentiment transition.

This workflow is particularly useful in customer support or bug tracking scenarios where timely detection of negative sentiment can significantly improve response times and customer satisfaction. By continuously monitoring and analyzing issue conversations, teams can maintain better oversight and act swiftly to mitigate issues.

Node Count	11 – 20 Nodes
Nodes Used	@n8n/n8n-nodes-langchain.informationExtractor, @n8n/n8n-nodes-langchain.lmChatOpenAi, airtable, airtableTrigger, graphql, removeDuplicates, scheduleTrigger, set, slack, splitInBatches, splitOut, stickyNote, switch