Automation library · AI assistants

AI-powered LinkedIn connection recommender with a local model

Started by an arriving email, and works across Email. It hands the judgement calls to a local model. 9 steps: a working afternoon to understand properly.

MediumCalls a model: a local model

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

The flow

Model 2Logic 4Service 3

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

  1. 1Ollama Model1Lm OllamaModel
  2. 2Get User Data From Email Email Read ImapService
  3. 3AI Profile AnalysisChain LlmModel
  4. 4Your Profile InformationSetLogic
  5. 5Create Final RecommendationsCodeLogic
  6. 6Search LinkedIn ProfilesHttp RequestService
  7. 7Create EmailCodeLogic
  8. 8Process LinkedIn Search ResultsCodeLogic
  9. 9Send emailEmail SendService

How it's built

Starts on
An arriving email
Steps
9
Size
Medium: a working afternoon
Connects to
Email
Model
a local model

Questions

What does it need to run?

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

What starts it?

It starts on an arriving email.

Does it use AI?

Yes. It calls a local model. Model calls are billed by the provider, not by n8n.

How long does it take to set up?

Plan an afternoon. 9 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 9 steps before you point it at anything that matters.