Automation library · AI assistants

Automate code reviews for GitLab MRs with Gemini and Jira

Started by another system calling it, and works across Jira. It hands the judgement calls to Gemini. 35 steps, 4 branches: large, and worth reading before you trust it with anything live.

LargeCalls a model: Gemini

35 stepsLarge: read it before trusting it with anything live
4Branches: places the flow splits
0Loops or waits
1Service it connects to

The flow

Starts it 2Model 2Logic 23Service 8

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

  1. 1Google Gemini Chat ModelLm Chat Google GeminiModel
  2. 2Error TriggerError triggerStarts it
  3. 3Listen For Gitlab CommentsWebhookStarts it
  4. 4Basic LLM ChainChain LlmModel
  5. 5Get Static Context Including ErrorCodeLogic
  6. 6Need ReviewIfLogic
  7. 7Merge LLM Output with InputMergeLogic
  8. 8Post Error OccurredHttp RequestService
  9. 9Set workflow execution informationCodeLogic
  10. 10AggregateAggregateLogic
  11. 11Cleanup Static ContextCodeLogic
  12. 12Post Review StartedHttp RequestService
  13. 13Extract MR DetailsSetLogic
  14. 14Process CommentsCodeLogic
  15. 15Get MR ChangesHttp RequestService
  16. 16Extract the JIRA Issue IDCodeLogic
  17. 17Any Issues Found?IfLogic
  18. 18MergeMergeLogic
  19. 19Get JIRA issueJiraService
  20. 20Get Static ContextCodeLogic
  21. 21Split Out CommentsSplit OutLogic
  22. 22Split Out ChangesSplit OutLogic
  23. 23Format JIRA ContextSetLogic
  24. 24If JIRA SubtaskIfLogic
  25. 25Post No Issues FoundHttp RequestService
  26. 26Prepare RequestCodeLogic
  27. 27Skip File ChangesIfLogic
  28. 28Get JIRA Parent IssueJiraService
  29. 29Post Gitlab MR CommentsHttp RequestService
  30. 30Parse DiffCodeLogic
  31. 31Format JIRA Parent ContextSetLogic
  32. 32Prepare Request Without PositionCodeLogic
  33. 33Prepare Code ChangesCodeLogic
  34. 34Post Gitlab MR Comments WIthout PositionHttp RequestService
  35. 35Filter Irrelevant FieldsSetLogic

How it's built

Starts on
Another system calling it
Steps
35, with 4 branches
Size
Large: read it before trusting it with anything live
Connects to
Jira
Model
Gemini

Questions

What does it need to run?

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

What starts it?

It starts on another system calling it.

Does it use AI?

Yes. It calls Gemini. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 35 steps it is large: read it before trusting it with anything live.

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 35 steps before you point it at anything that matters.