Automation library · AI assistants

Filter cybersecurity news for your tech stack with OpenAI

Started by someone opening a chat with it, and works across Gmail, Pinecone and RSS. It puts OpenAI behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 35 steps, 3 branches, 4 loops or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: OpenAIRetrieval

Download free
35 stepsLarge: read it before trusting it with anything live
3Branches: places the flow splits
4Loops or waits
3Services it connects to

The flow

Starts it 3Model 12Logic 13Service 7

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

  1. 1Schedule TriggerSchedule triggerStarts it
  2. 2OpenAI Chat ModelLm Chat Open AiModel
  3. 3Embeddings OpenAIEmbeddings Open AiModel
  4. 4Default Data LoaderDocument Default Data LoaderModel
  5. 5On form submissionForm triggerStarts it
  6. 6When chat message receivedChat triggerStarts it
  7. 7OpenAI Chat Model1Lm Chat Open AiModel
  8. 8Simple MemoryMemory Buffer WindowModel
  9. 9o4-miniLm Chat Open AiModel
  10. 10Bleeping ComputerRss Feed ReadService
  11. 11The Hacker NewsRss Feed ReadService
  12. 12Security WeekRss Feed ReadService
  13. 13Nist.GovRss Feed ReadService
  14. 14Krebson SecurityRss Feed ReadService
  15. 15CISA.govRss Feed ReadService
  16. 16Threat Intelligence Analyst AIAgentModel
  17. 17Pinecone Vector Store2Vector Store PineconeModel
  18. 18Pinecone Vector Store1Vector Store PineconeModel
  19. 19Pinecone Vector Store SubmissionVector Store PineconeModel
  20. 20Pinecone RAG testAgentModel
  21. 21Second Reviewer AgentAgentModel
  22. 22Merge all RSS itemsMergeLogic
  23. 23Wait 1 minute (rate-limits)WaitLogic
  24. 24Wait 1 minuteWaitLogic
  25. 25Newer than 24 hoursIfLogic
  26. 26Loop Over Items (Batch = 4)Split In BatchesLogic
  27. 27Loop Over Items (Batch = 10)Split In BatchesLogic
  28. 28Limit Length of articleCodeLogic
  29. 29News older than 24 hoursNo OpLogic
  30. 30If AI Agent thinks article is relevant to youIfLogic
  31. 31If second ai agent thinks article is relevantIfLogic
  32. 32Do nothing - Article is irrelevantNo OpLogic
  33. 33Aggregate articles into one emailAggregateLogic
  34. 34Do nothing - Ai Agent thinks article is irrelevantNo OpLogic
  35. 35Send message to work emailGmailService

How it's built

Starts on
Someone opening a chat with it
Steps
35, with 3 branches, 4 loops or waits
Size
Large: read it before trusting it with anything live
Connects to
Gmail, Pinecone, RSS
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 Gmail, Pinecone and RSS accounts, 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. 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 35 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 35 steps before you point it at anything that matters.