The flow
Starts it 1Model 7Logic 4Service 2
The steps in the order they run, from what starts it.
- 1Chat Message TriggerChat triggerStarts it
- 2LLM Response Provider (OpenRouter)Lm Chat Open RouterModel
- 3LLM Memory Buffer (Input Context)Memory Buffer WindowModel
- 4LLM Memory Buffer (Report Context)Memory Buffer WindowModel
- 5Fetch Wikipedia InformationTool WikipediaModel
- 6Generate Search Queries using LLMChain LlmModel
- 7Extract Relevant Context via LLMAgentModel
- 8Generate Comprehensive Research ReportAgentModel
- 9Parse and Chunk JSON DataCodeLogic
- 10Split Data for SerpAPI BatchingSplit In BatchesLogic
- 11Format SerpAPI Organic ResultsCodeLogic
- 12Perform SerpAPI Search RequestHttp RequestService
- 13Split Data for Jina AI BatchingSplit In BatchesLogic
- 14Perform Jina AI Analysis RequestHttp RequestService
How it's built
- Starts on
- Someone opening a chat with it
- Steps
- 14, 2 loops or waits
- Size
- Medium: a working afternoon
- Connects to
- Nothing by connector; it calls services over plain HTTP
- Model
- OpenRouter
- Retrieval
- Answers are drawn from documents you supply, not from the model alone
Questions
What does it need to run?
An n8n account, and a key for OpenRouter. 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 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?
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.