AI-powered email to Jira ticket creation with Llama 3.2
Needs changesNeeds changes. This template uses 1 thing(s) that n8n 3.0 removes: AI Agent v1 (old agent modes). 1 breaking item(s) found. Static check, last run 2026-10-19.
What this workflow does
This AI workflow has 10 nodes and runs on Gmail events. Along the way it connects Gmail, Ollama Chat Model and Jira Software.
How it runs
Trigger: On Gmail events.
- Fetch Full Email Content (Gmail): get
- Analyze Email & Extract Tasks (AI Agent): runs an AI agent, with model: Chat Model; 1 tool (AI Tool - Think Support)
- Wait: pauses before continuing
- Parse JSON Output from AI (Code): runs custom JavaScript code
- Jira - Create Main Issue (Jira Software): uses Jira Software
- Split Subtasks JSON to Items (Code): runs custom JavaScript code
- Create Subtasks (Jira Software): uses Jira Software
Services it uses
Before you upgrade to n8n 3.0
1 thing in this workflow is removed in n8n 3.0. Fix it before you upgrade:
- AI Agent v1 (old agent modes) in Analyze Email & Extract Tasks (v1.8): replace with Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent.
- Also check Gmail Trigger below v1.4 runs as v1.4 (drafts skipped, max emails per poll).
| Removed in 3.0 | Replace with |
|---|---|
| AI Agent v1 (old agent modes) Analyze Email & Extract Tasks (v1.8) | Latest AI Agent node (Tools Agent). For SQL Agent, use a Postgres or MySQL tool with a recent AI Agent. |
Nodes used (8)
- Gmail
n8n-nodes-base.gmail - AI Agent
@n8n/n8n-nodes-langchain.agent - Think Tool
@n8n/n8n-nodes-langchain.toolThink - Ollama Chat Model
@n8n/n8n-nodes-langchain.lmChatOllama - Code
n8n-nodes-base.code - Gmail Trigger
n8n-nodes-base.gmailTrigger - Jira Software
n8n-nodes-base.jira - Wait
n8n-nodes-base.wait
From the author
This AI-powered workflow reads emails, understands the request using an LLM, and creates structured Jira issues. Key Insights - Poll for new emails every 5 minutes; ensure Gmail/IMAP is properly configured. - AI analysis requires a reliable LLM model (e.g.,…