n8n Workflow: Route Salesforce & Jira Customer Feedback with Qwen AI

Route Salesforce & Jira Customer Feedback with Qwen AI—automatically cluster, classify, and action it

This n8n workflow connects Salesforce Cases and Jira tickets, redacts sensitive data, classifies feedback with an OpenAI-compatible LLM (Qwen via Featherless AI), then clusters issues by category and routes them into Jira VOC and Salesforce follow-up tasks.

What this workflow does

• Runs weekly (or on-demand): calculates a lookback window to fetch only recent feedback.
• Collects customer signals: pulls recent Salesforce Cases, Jira issues for a configured project, and Salesforce account data (optionally using built-in sample feedback when enabled).
• Prepares the data: normalizes text, redacts emails and phone numbers, removes duplicates using workflow static data, and flags VIP items based on account revenue/rating or an allowlist.
• AI-driven classification: sends batches to an OpenAI-compatible chat model to classify each feedback item by `category`, `theme`, `sentiment`, `urgency`, and churn risk.
• Creates actionable routing: aggregates results into category clusters, assigns priority, generates an HTML weekly digest, and—when live mode is enabled—routes clusters by team by:
  • commenting on or creating labeled VOC issues in Jira for product topics
  • creating Salesforce tasks for billing, onboarding, sales/engagement, and escalations

Use cases

• SaaS teams that want a weekly customer feedback pipeline across Salesforce and Jira
• Product/support ops teams that need VOC issue updates with prioritized clusters and churn risk
• Automation engineers building an n8n automation workflow for AI-assisted triage and routing

Technical details

• Automation logic: if, set, code, merge
• Integrations: Jira, Gmail (for digest delivery), Salesforce
• LLM: OpenAI-compatible chat model configured for Featherless AI (using Qwen), with customizable base URL/model