Automation library · Chat assistants

Investigate batch deviation root causes with OpenAI and QMS

Started by another system calling it, and works across Postgres and Slack. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 22 steps, 3 branches, 1 loop or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

Download free
22 stepsLarge: read it before trusting it with anything live
3Branches: places the flow splits
1Loop or waits
2Services it connects to

The flow

Starts it 2Model 7Logic 6Service 7

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

  1. 1When Deviation SubmittedWebhookStarts it
  2. 2Query Equipment EventsTool Http RequestModel
  3. 3Query Operator ActionsTool Http RequestModel
  4. 4Query Environmental DataTool Http RequestModel
  5. 5Search Historical CAPAsTool Vector StoreModel
  6. 6OpenAI GPT-4 ChatLm Chat Open AiModel
  7. 7Buffer AI MemoryMemory Buffer WindowModel
  8. 8Set Deviation ConfigurationSetLogic
  9. 9Deviation Analysis AgentAgentModel
  10. 10Parse Agent OutputSetLogic
  11. 11Log RCA InvestigationPostgresService
  12. 12If Hypothesis Confidence HighIfLogic
  13. 13Send QA Review RequestSlackService
  14. 14Notify Manual InvestigationSlackService
  15. 15Wait for QA DecisionWaitLogic
  16. 16Respond Investigation LoggedRespond To WebhookStarts it
  17. 17If QA ApprovedIfLogic
  18. 18Patch Deviation Record in QMSHttp RequestService
  19. 19Notify QA RejectionSlackService
  20. 20If CAPA RecommendedIfLogic
  21. 21Create CAPA DraftHttp RequestService
  22. 22Post Investigation SummarySlackService

How it's built

Starts on
Another system calling it
Steps
22, with 3 branches, 1 loop or waits
Size
Large: read it before trusting it with anything live
Connects to
Postgres, Slack
Model
OpenAI
Retrieval
Answers are drawn from documents you supply, not from the model alone

Questions

What does it need to run?

An n8n account, plus your own Postgres and Slack accounts, and a key for OpenAI. 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 OpenAI. Its answers draw on documents you give it, not on the model alone. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Take your time. At 22 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 22 steps before you point it at anything that matters.