The flow
Starts it 1Model 2Logic 7Service 8
The steps in the order they run, from what starts it.
- 1Trigger Reefer Incident WebhookWebhookStarts it
- 2Choose Claims ModelLm Chat Open AiModel
- 3Normalise Voyage ClaimSetLogic
- 4Judge Event NarrativeChain LlmModel
- 5Fetch Terminal Event CollectionHttp RequestService
- 6Judge Event LiabilityCodeLogic
- 7Split Container EventsSplit OutLogic
- 8Check Evidence CompletenessIfLogic
- 9Fetch Reefer TelemetryHttp RequestService
- 10Request Missing Terminal EvidenceGmailService
- 11Merge Container EvidenceMergeLogic
- 12Aggregate Dispute EvidenceCodeLogic
- 13Check Claim MaterialityIfLogic
- 14Archive Dispute PacketDropboxService
- 15Log Non-Material IncidentNotionService
- 16Record Claim PacketAirtableService
- 17Submit Carrier DisputeHttp RequestService
- 18Notify Claims DeskMicrosoft TeamsService
How it's built
- Starts on
- Another system calling it
- Steps
- 18, with 2 branches
- Size
- Medium: a working afternoon
- Connects to
- Airtable, Dropbox, Gmail, Notion
- Model
- OpenAI
Questions
What does it need to run?
An n8n account, plus your own Airtable, Dropbox, Gmail and Notion 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. Model calls are billed by the provider, not by n8n.
How long does it take to set up?
Plan an afternoon. 18 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.
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 18 steps before you point it at anything that matters.