LLM Chaining examples
Configured with Agent, Chain LLM, HTTP Request, Anthropic Chat Model, and additional nodes. Review the connections and setup before adapting this template.
Node categories in this workflow
- Trigger
- Web / API
- Transform
- AI & models
- Data store
- Routing
Icons describe general node roles, inferred from node types. Inspect the parameters for the configured action.
Drag to pan; use + and − to zoom. Reconstructed from the exported node positions; nothing runs here. Dashed lines represent non-main connections. Full node names and notes appear below.
How it works
The exported workflow contains the following configured nodes. Their connections are shown above; inspect the JSON for the complete logic, expressions, and external actions.
| Node | Category | Type | Operation |
|---|---|---|---|
| When clicking ‘Test workflow’ | Trigger | Manual Trigger | See node parameters |
| HTTP Request | Web / API | HTTP Request | See node parameters |
| Markdown | Transform | Markdown | See node parameters |
| Anthropic Chat Model | AI & models | Anthropic Chat Model | See node parameters |
| Anthropic Chat Model1 | AI & models | Anthropic Chat Model | See node parameters |
| Anthropic Chat Model2 | AI & models | Anthropic Chat Model | See node parameters |
| Anthropic Chat Model3 | AI & models | Anthropic Chat Model | See node parameters |
| Merge | Transform | Merge | See node parameters |
| Simple Memory | Data store | Memory Buffer Window | See node parameters |
| Clean memory | Data store | Memory Manager | See node parameters |
| Initial prompts | Transform | Edit Fields | See node parameters |
| Split Out | Transform | Split Out | See node parameters |
| Reshape | Transform | Edit Fields | See node parameters |
| Anthropic Chat Model4 | AI & models | Anthropic Chat Model | See node parameters |
| Merge2 | Transform | Merge | See node parameters |
| Basic LLM Chain4 | AI & models | Chain LLM | See node parameters |
| Split Out1 | Transform | Split Out | See node parameters |
| Anthropic Chat Model5 | AI & models | Anthropic Chat Model | See node parameters |
| Webhook | Trigger | Webhook | See node parameters |
| CONNECT ME | Routing | No Op | See node parameters |
| CONNECT ME1 | Routing | No Op | See node parameters |
| CONNECT ME2 | Routing | No Op | See node parameters |
| Initial prompts1 | Transform | Edit Fields | See node parameters |
| LLM Chain - Step 1 | AI & models | Chain LLM | See node parameters |
| LLM Chain - Step 2 | AI & models | Chain LLM | See node parameters |
| LLM Chain - Step 3 | AI & models | Chain LLM | See node parameters |
| LLM Chain - Step 4 | AI & models | Chain LLM | See node parameters |
| All LLM steps here - sequentially | AI & models | Agent | See node parameters |
| LLM steps - parallel | Web / API | HTTP Request | POST |
| Merge output with initial prompts | Transform | Merge | See node parameters |
| Merge output with initial prompts1 | Transform | Merge | See node parameters |
Setup
- Download the JSON and import it into an isolated n8n instance. Leave the workflow inactive.
- Connect your own credentials through n8n’s credential store. Replace
REPLACE_WITH_*values with your resource identifiers. - Inspect API destinations, Code nodes, database queries, file paths, and outbound actions.
- Run with synthetic data and harmless destinations. Enable triggers only after checking the actual outputs.
Requirements
An n8n instance with the listed node types and compatible versions. Service-connected workflows may require accounts, credentials, or paid APIs.
Credential types declared in the source
anthropicApi
Workflow notes
Connect to one of the blue sections -->
Connect to one of the blue sections -->
This can be anything:
- Chat input
- Trigger from external system
- CRON-scheduled event
Make sure URL matches
Make sure URL matches
⚠️ Cloud users!
Replace {{ $env.WEBHOOK_URL }}
with your n8n instance URL
1 - Naive Chaining
1 - Naive Chaining
PROs:
- Easy to setup
- Beginner-friendly
CONs
- Not scalable
- Hard to maintain long chains
- SLOOOW!
2 - Iterative Agent Processing
2 - Iterative Agent Processing
PROs:
- Scalable
- All inputs & outputs in a single node
- Supports Agent memory
CONs
- Still Slow!
3 - Parallel Processing
3 - Parallel Processing
PROs:
- Scalable
- All inputs & outputs in a single place
- FAST!
CONs
- Independent requests (no Agent memory)
LLM Chaining examples
LLM Chaining examples
Purpose and structure
This folder contains the LLM Chaining examples workflow. Its executable nodes use agent, chainLlm, httpRequest, lmChatAnthropic, manualTrigger, markdown, memoryBufferWindow, memoryManager, merge, noOp, set, splitOut, webhook. The table and connection map below are derived from the JSON, not an inferred guarantee of behavior.
Setup
Import inactive. Configure your own credentials and replace REPLACE_WITH_* values. Review external destinations and Code nodes before running.
Entry points
When clicking ‘Test workflow’, Webhook
Verification
Sanitized source candidate; not runtime-tested. This overview is generated from node metadata. Read the folder README for the connection map, credential types, and license.
Attribution
https://github.com/Zie619/n8n-workflows/blob/94007c1445d9258a7da116646b79473e7c7c3282/workflows/Splitout/0958_Splitout_Webhook_Automation_Webhook.json MIT; preserve source notices.
Canvas section labels
These name areas of the original canvas; they do not include explanatory instructions.
- An array of prompts here
- Array of prompts here