Automation library · Customer support

AI-powered email to Jira ticket creation with Llama

Started by an arriving email, and works across Gmail and Jira. It hands the judgement calls to a local model. 10 steps, 1 loop or waits: a working afternoon to understand properly.

MediumCalls a model: a local model

10 stepsMedium: a working afternoon
0Branches: places the flow splits
1Loop or waits
2Services it connects to

The flow

Starts it 1Model 3Logic 3Service 3

The steps in the order they run, from what starts it.

  1. 1AI Tool - Think Support Tool ThinkModel
  2. 2Chat ModelLm Chat OllamaModel
  3. 3Check for New Emails Gmail triggerStarts it
  4. 4Analyze Email & Extract Tasks AgentModel
  5. 5Fetch Full Email Content GmailService
  6. 6WaitWaitLogic
  7. 7Parse JSON Output from AI CodeLogic
  8. 8Jira - Create Main IssueJiraService
  9. 9Split Subtasks JSON to Items CodeLogic
  10. 10Create Subtasks JiraService

How it's built

Starts on
An arriving email
Steps
10, 1 loop or waits
Size
Medium: a working afternoon
Connects to
Gmail, Jira
Model
a local model

Questions

What does it need to run?

An n8n account, plus your own Gmail and Jira accounts, and a key for a local model. You connect your own accounts after importing it; none are included.

What starts it?

It starts on an arriving email.

Does it use AI?

Yes. It calls a local model. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 10 steps is enough that you should read each one before running it.

How do I import it?

Copy the workflow, open a new workflow in n8n and paste. The steps appear on the canvas, ready for your own accounts.

Before you run it

Nothing here has been tested by us. It is somebody's working automation, read and described from its own steps. Treat the connections it wants as a list of accounts it will touch, and read the 10 steps before you point it at anything that matters.