Skip to main content
The workflow builder tools let AI assistants create, edit, and restructure workflows step-by-step. Each tool validates independently, so errors are caught early — your assistant gets a clear error and can self-correct.

Typical build flow

1

Discover nodes

Call list_node_types to see available node types and their ports.
2

Scaffold a workflow

Call create_workflow to create a workflow with Request and Response nodes.
3

Add processing nodes

Call add_node for each model (image generator, LLM, etc.).
4

Wire it together

Call connect_nodes to wire outputs to inputs — type-checked automatically.

Editing an existing workflow

Already built a workflow and need to tweak it? Use these tools:
  • update_node — change input values on an existing node
  • delete_node — remove a node; all connected edges are cleaned up automatically
  • disconnect_nodes — remove a single edge (by edge ID or source/target pair)
  • add_node + connect_nodes — rewire the workflow

Examples

Four common patterns. Switch tabs to see each one.
Generate an image with Flux, then describe it with a vision LLM.

Port names returned by add_node and list_node_types use the in: / out: prefix format expected by connect_nodes. The connect_nodes tool validates type compatibility (e.g. image→image), prevents cycles, and enforces single-input rules. Use disconnect_nodes to remove a connection, or delete_node to remove a node along with all its connections.