The flow
Starts it 2Model 3Logic 4Service 5
The steps in the order they run, from what starts it.
- 1When LinkedIn Reply ReceivedWebhookStarts it
- 2OpenAI GPT-5-mini ModelLm Chat Open AiModel
- 3Parse Linkedin outputOutput Parser StructuredModel
- 4When clicking ‘Execute workflow’Manual triggerStarts it
- 5Filter Valid LinkedIn URLsFilterLogic
- 6LinkedIn Reply AgentAgentModel
- 7Edit FieldsSetLogic
- 8Fetch LinkedIn Public IdentifierHttp RequestService
- 9If Escalation NeededIfLogic
- 10Create webhook UnipileHttp RequestService
- 11Fetch LinkedIn Chat MessagesHttp RequestService
- 12Wait Business Hours DelayWaitLogic
- 13Send Escalation to DiscordDiscordService
- 14Post AI Reply to LinkedIn ChatHttp RequestService
How it's built
- Starts on
- Another system calling it
- Steps
- 14, with 1 branch, 1 loop or waits
- Size
- Medium: a working afternoon
- Connects to
- Discord
- Model
- OpenAI
Questions
What does it need to run?
An n8n account, plus your own Discord account, 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. 14 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 14 steps before you point it at anything that matters.