Automation library · AI assistants

Compare sequential, agent-based, and parallel LLM processing

Started by another system calling it. It calls services over plain HTTP rather than through connectors. It puts Claude behind a retrieval step, so answers are drawn from documents you supply rather than from the model alone. 31 steps: large, and worth reading before you trust it with anything live.

LargeCalls a model: ClaudeRetrieval

Download free
31 stepsLarge: read it before trusting it with anything live
0Branches: places the flow splits
0Loops or waits
0Services by connector: it calls them over plain HTTP

The flow

Starts it 2Model 14Logic 13Service 2

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

  1. 1When clicking ‘Test workflow’Manual triggerStarts it
  2. 2Anthropic Chat ModelLm Chat AnthropicModel
  3. 3Anthropic Chat Model1Lm Chat AnthropicModel
  4. 4Anthropic Chat Model2Lm Chat AnthropicModel
  5. 5Anthropic Chat Model3Lm Chat AnthropicModel
  6. 6Simple MemoryMemory Buffer WindowModel
  7. 7Anthropic Chat Model4Lm Chat AnthropicModel
  8. 8Anthropic Chat Model5Lm Chat AnthropicModel
  9. 9WebhookWebhookStarts it
  10. 10CONNECT MENo OpLogic
  11. 11CONNECT ME1No OpLogic
  12. 12CONNECT ME2No OpLogic
  13. 13HTTP RequestHttp RequestService
  14. 14LLM Chain - Step 1Chain LlmModel
  15. 15LLM Chain - Step 2Chain LlmModel
  16. 16LLM Chain - Step 3Chain LlmModel
  17. 17LLM Chain - Step 4Chain LlmModel
  18. 18All LLM steps here - sequentiallyAgentModel
  19. 19Clean memoryMemory ManagerModel
  20. 20Basic LLM Chain4Chain LlmModel
  21. 21MergeMergeLogic
  22. 22Initial prompts1SetLogic
  23. 23Merge2MergeLogic
  24. 24MarkdownMarkdownLogic
  25. 25Merge output with initial prompts1MergeLogic
  26. 26Initial promptsSetLogic
  27. 27Split Out1Split OutLogic
  28. 28LLM steps - parallelHttp RequestService
  29. 29Merge output with initial promptsMergeLogic
  30. 30ReshapeSetLogic
  31. 31Split OutSplit OutLogic

How it's built

Starts on
Another system calling it
Steps
31
Size
Large: read it before trusting it with anything live
Connects to
Nothing by connector; it calls services over plain HTTP
Model
Claude
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 Claude. 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 Claude. 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 31 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 31 steps before you point it at anything that matters.