Workflow Nodes
Configure the available nodes in Clouisle workflows by category
The workflow editor currently registers the following nodes. The exact input and output fields of a node are determined by the editor configuration and the node reference.
| Category | Nodes |
|---|---|
| Start and Output | User Input, Trigger, Output, Note |
| Models and Apps | LLM, Agent, Media Generation, Question Classification, Parameter Extraction |
| Knowledge and Extensions | Knowledge Base Retrieval, Tools, MCP/Custom Capabilities, Sub-workflow |
| Logic | Conditional Branch, Iteration, Loop and its start/exit nodes |
| Transformation | Code Execution, Template Transformation, Variable Assignment, Variable Aggregation, File to URL |
Principles for Choosing Nodes
- Use LLM when chat model reasoning is needed; use Agent when you need to reuse complete Agent behavior.
- Use Knowledge Base Retrieval when you need to answer based on a knowledge base, then map the results to an LLM or output.
- Use Tools when you need to call existing HTTP/MCP/code capabilities; do not duplicate stored credentials in workflows.
- Use Iteration to process each array item; use Loop to repeat until a condition is met.
- Use Sub-workflow to isolate reusable flows, configuring input/output mappings and failure strategies.
Node-level Failures
Each executed node records inputs, outputs, model, Tokens, duration, retry count, error type, and error message. HTTP, code, MCP, and media nodes should configure an acceptable timeout; avoid unconditional repeated calls to side-effect interfaces that cannot be retried.
How is this guide?