Auto-assign Support Tickets with JIRA, Supabase and AI
This n8n template builds a simple automation to ensure no JIRA issues go unassigned for more than a week to prevent them falling through the cracks. It uses AI to perform searching tasks against a Supabase Vector Store. This can be one way to help reduce the amount of manual work in managing the issue backlog for busy teams with little effort. How it works This template contains 2 separate flows which run continuously via schedule triggers. The first populates our Supabase vector store with resolved issues within the last day. This helps keep our vector store up-to-date and relevant for the purpose of finding similar issues. It does this by pulling the latest resolved issues from JIRA and populating the Supabase vectorstore with carefully chosen metadata. This will come in handy later. The second flow watches for stale, unassigned issues for the purpose of aut-assigning to a relevant team member. It does this by comparing the stale issue against our vector store of resolved issues with the goal of identifying which team member would have best context regarding the issue. In a busy team, this may net a few team members as possible candidates to assign.
Tags
Related workflows
See all AI Automation→AI: Summarize podcast episode and enhance using Wikipedia
The workflow automates the process of creating a summarized and enriched podcast digest, which is then sent via email. Note that to use this template, you need to be on n8n version 1.19.4 or later.
Scrape and summarize webpages with AI
This workflow integrates both web scraping and NLP functionalities. It uses HTML parsing to extract links, HTTP requests to fetch essay content, and AI-based summarization using GPT-4o. It's an excellent example of an end-to-end automated task that is not only efficient but also provides real value by summarizing valuable content. Note that to use this template, you need to be on n8n version 1.50.0 or later.
Ask questions about a PDF using AI
The workflow first populates a Pinecone index with vectors from a Bitcoin whitepaper. Then, it waits for a manual chat message. When received, the chat message is turned into a vector and compared to the vectors in Pinecone. The most similar vectors are retrieved and passed to OpenAI for generating a chat response. Note that to use this template, you need to be on n8n version 1.19.4 or later.