Automation library · Research and reporting

Deep research agent - research & Notion report builder

Started by another system calling it, and works across Notion. It puts Gemini, OpenAI and one other behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 36 steps, 1 branch, 2 loops or waits: large, and worth reading before you trust it with anything live.

LargeCalls a model: Gemini, OpenAIRetrieval

Download free
36 stepsLarge: read it before trusting it with anything live
1Branch: places the flow splits
2Loops or waits
1Service it connects to

The flow

Starts it 3Model 13Logic 13Service 7

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

  1. 1Simple MemoryMemory Buffer WindowModel
  2. 2Structured Output ParserOutput Parser StructuredModel
  3. 3Structured Output Parser1Output Parser StructuredModel
  4. 4Google Gemini Chat ModelLm Chat Google GeminiModel
  5. 5OpenRouter Chat ModelLm Chat Open RouterModel
  6. 6OpenRouter Chat Model1Lm Chat Open RouterModel
  7. 7OpenRouter Chat Model2Lm Chat Open RouterModel
  8. 8WebhookWebhookStarts it
  9. 9Strategy AgentAgentModel
  10. 10Search Query AgentAgentModel
  11. 11Notion Block GeneratorChain LlmModel
  12. 12Report AgentAgentModel
  13. 13SwitchSwitchLogic
  14. 14Split OutSplit OutLogic
  15. 15Parse JSON blocksSetLogic
  16. 16Get Existing RowNotionService
  17. 17Respond to WebhookRespond To WebhookStarts it
  18. 18Respond to Webhook1Respond To WebhookStarts it
  19. 19Loop Over QueriesSplit In BatchesLogic
  20. 20Valid BlocksFilterLogic
  21. 21Convert to HTMLMarkdownLogic
  22. 22CodeCodeLogic
  23. 23AggregateAggregateLogic
  24. 24HTTP RequestHttp RequestService
  25. 25For Each Block...Split In BatchesLogic
  26. 26HTML to ArraySetLogic
  27. 27OpenAI1Open AiModel
  28. 28Edit FieldsSetLogic
  29. 29Aggregate1AggregateLogic
  30. 30HTTP Request2Http RequestService
  31. 31Tags to ItemsSplit OutLogic
  32. 32NotionNotionService
  33. 33OpenAIOpen AiModel
  34. 34Notion1NotionService
  35. 35HTTP Request1Http RequestService
  36. 36HTTP Request3Http RequestService

How it's built

Starts on
Another system calling it
Steps
36, with 1 branch, 2 loops or waits
Size
Large: read it before trusting it with anything live
Connects to
Notion
Model
Gemini, OpenAI, OpenRouter
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 Notion account, and a key for Gemini and 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 Gemini, OpenAI and OpenRouter. 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 36 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 36 steps before you point it at anything that matters.