Skip to content

Workflow Nodes

A Tryll workflow is a graph of nodes, each responsible for one step of the per-turn loop. Eight node types ship in the box; together they cover the common patterns of conversational inference (generation, retrieval, intent classification, instructions, detection, fallback, guardrails).

Nodes are referenced by their NodeType name on the wire protocol:

Node NodeType Exit routes Use for
Generate Generate default Language-model inference. The workhorse.
Instruction Instruction default Attach a named instruction string to the current interaction; rendered by downstream Generate via Mustache.
Retrieve Retrieve found, not_found Vector search over an embedded string storage — the R in RAG.
Classify Intent ClassifyIntent found, not_found Top-1 embedding similarity against a labelled KB; attaches an IntentionComponent for downstream routing.
Intent to Instruction IntentToInstruction default Look up the detected intent in a Map string storage and attach the matching InstructionComponent.
Tool Call ToolCall tool_called, no_tool_called Detect whether the model wants to call an external tool.
Canned Response CannedResponse default Emit a fixed reply from a string storage without calling the model.
Human Message Guardrail HumanMessageGuardrail triggered, not_triggered Regex-match the user message; branch the graph on pattern hits.

Exit-route legend

Every node's reference page lists its named exits. Each exit is a typed string field on the node's params object (e.g. default_exit, triggered_exit). An empty string routes the turn to END (the default); a non-empty string must name another node in the graph. The server rejects graphs where an exit field names a missing node with error 3008 InvalidExitTarget.

Common patterns:

  • Straight line. Generate → default → END. Minimal single-turn agent.
  • Branch on guardrail. Guardrail → triggered → CannedResponse → END; Guardrail → not_triggered → Generate → default → END.
  • Instruction then generate. Instruction → default → Generate. The instruction's text is exposed as {{instruction_<name>}} and {{#instructions}} in the Generate node's Mustache template.
  • Retrieve then generate. Retrieve → found → Generate; Retrieve → not_found → Generate (same target). The not_found path is fine — the projection drops to the user message alone.
  • Tool-call detection. ToolCall → tool_called → END (client handles the tool); ToolCall → no_tool_called → Generate.
  • Intent classification. ClassifyIntent → found → IntentToInstruction → default → Generate; ClassifyIntent → not_found → Generate (general answer, no instruction override). See How to build an intent-driven NPC.

Params

Every node carries a list of (key, value) string pairs (NodeParam). Each node's reference page lists the keys it accepts. Unknown keys are currently silent; standardising on strict validation is planned.

Diagnostics

When the agent is created with enable_diagnostics = true, every node contributes to TurnComplete.debug_info. See agent parameters — diagnostics.