Automation library · Research and reporting

Extract insights from LinkedIn with Apify

Started by someone opening a chat with it, and works across Apify. It hands the judgement calls to OpenAI. 13 steps, 1 branch: a working afternoon to understand properly.

MediumCalls a model: OpenAI

13 stepsMedium: a working afternoon
1Branch: places the flow splits
0Loops or waits
1Service it connects to

The flow

Starts it 2Model 2Logic 4Service 5

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

  1. 1Run weeklySchedule triggerStarts it
  2. 2When chat message receivedChat triggerStarts it
  3. 3OpenAI Chat ModelLm Chat Open AiModel
  4. 4Pinecone Assistant toolPinecone Assistant ToolService
  5. 5Set LinkedIn urlSetLogic
  6. 6AI AgentAgentModel
  7. 7Run actor to scrape dataApifyService
  8. 8Get dataset itemsApifyService
  9. 9Filter postsFilterLogic
  10. 10If has commentsIfLogic
  11. 11Extract commentsSetLogic
  12. 12Convert to FileConvert To FileService
  13. 13Upload filePinecone AssistantService

How it's built

Starts on
Someone opening a chat with it
Steps
13, with 1 branch
Size
Medium: a working afternoon
Connects to
Apify
Model
OpenAI

Questions

What does it need to run?

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

What starts it?

It starts on someone opening a chat with 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. 13 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 13 steps before you point it at anything that matters.