Automation library · Research and reporting

Classify sentiment of incoming text with Hugging Face

Started by another system calling it, and works across Google Sheets and Jira. 12 steps, 1 branch, 1 loop or waits: a working afternoon to understand properly.

Medium

12 stepsMedium: a working afternoon
1Branch: places the flow splits
1Loop or waits
2Services it connects to

The flow

Starts it 1Logic 6Service 5

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

  1. 1Receive FeedbackWebhookStarts it
  2. 2Split Text ItemsSplit OutLogic
  3. 3Rate Limit ControlWaitLogic
  4. 4Preserve Input TextSetLogic
  5. 5Get Sentiment ScoresHttp RequestService
  6. 6Merge Text & ScoresMergeLogic
  7. 7Compute SentimentSetLogic
  8. 8Route by SentimentSwitchLogic
  9. 9Store Positive FeedbackGoogle SheetsService
  10. 10Store Neutral FeedbackGoogle SheetsService
  11. 11Store Negative FeedbackGoogle SheetsService
  12. 12Create Jira TicketJiraService

How it's built

Starts on
Another system calling it
Steps
12, with 1 branch, 1 loop or waits
Size
Medium: a working afternoon
Connects to
Google Sheets, Jira
Model
None. This is plumbing, not judgement

Questions

What does it need to run?

An n8n account, plus your own Google Sheets and Jira accounts. 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?

No. Every step is fixed logic or a call to a service, so it does the same thing every time.

How long does it take to set up?

Plan an afternoon. 12 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 12 steps before you point it at anything that matters.