Skip to main content
Subagent node is used to have a conversation with the user while allowing the agent to call tools / functions during the conversation. Use it when the agent should decide whether and when to use a tool / function based on the conversation context. If you only need dialogue without tool calling, use a Conversation Node.

​
How It Works

When a subagent node has tools / functions attached, the LLM receives both the node instruction and the list of available tools / functions. During the conversation, the LLM determines when a tool / function should be called based on context, extracts the required parameters, and invokes it while maintaining the dialogue with the user.
  • Multiple tools / functions can be added to a single subagent node
  • The agent can continue talking while a tool / function executes
  • Tool / function results are available to the LLM for generating follow-up responses

​
Write Instruction

Subagent nodes only support Prompt instructions. Unlike a conversation node, Static Sentence is not supported. Write the instruction to define the task, what information the agent should gather, and when it should use the available tools / functions. For example:

​
Subagent Node vs Function Node

Subagent nodes and function nodes serve different purposes: Use function nodes when you want guaranteed execution every time the flow reaches that step. Use subagent nodes when the agent should decide whether and when to call a tool / function based on what the user says.

​
Add Tools / Functions

1

Select a subagent node

Click on a subagent node to open its settings panel on the right side.
2

Add a tool / function

In the settings panel, find the Tools section and click + Add.Select the tool / function type from the dropdown menu.
3

Configure the tool / function

Configure the tool / function based on its type. See the Available Tool / Function Types table below for configuration details for each type.
4

Update the node instruction

Update the node prompt to guide the LLM on when to use the tool / function.

​
Available Tool / Function Types

​
Execution Speech Settings

Each tool / function has settings that control what the agent says while it is running and after it completes.

​
Speak During Execution

When enabled, the agent says a message while the tool / function is executing, for example One moment, let me check that for you. This is recommended when the tool / function takes over 1 second, including network latency, so the agent remains responsive. You can configure how the message is generated:
  • Prompt: The LLM dynamically generates what to say based on a description you provide.
  • Static Sentence: The agent speaks the exact text you provide.

​
Speak After Execution

When enabled, the agent calls the LLM after the tool / function returns a result so it can speak about the outcome to the user. Turn this off if you want to run it silently.
  • Speak During Execution is available on: Custom Function, Code Tool, End Call, Transfer Call, Transfer Agent, and MCP Tool.
  • Speak After Execution is available on: Custom Function, Code Tool, and MCP Tool.

​
When Can Transition Happen

  • when user is done speaking
  • when Skip Response is enabled and agent finishes speaking
Tool / function execution happens within the subagent node, so the node can stay active across multiple turns and tool / function calls before it transitions.

​
Node Settings

  • Tools: attach the tools / functions this subagent can use during the conversation.
  • Skip Response: when enabled, the transition will only have one edge that you can connect, and when agent is done talking, it will transition to the next node via that specific edge.
  • Knowledge Base: configure node-level knowledge bases to combine topic-specific knowledge with the agent-level knowledge base. Read more at Knowledge Base.
  • Global Node: read more at Global Node
  • Block Interruptions: when enabled, the agent will not be interrupted by user when speaking.
  • LLM: choose a different model for this particular node. Will be used for response generation, tool / function selection, and tool / function argument generation.
  • Fine-tuning Examples: Can finetune conversation response, and transition. Read more at Finetune Examples

​
Best Practices

  • Be explicit in your node instruction. Tell the agent when each tool / function should be used.
  • Use function nodes for guaranteed execution. If a tool / function must always run at a certain point in the flow, use a function node instead.
  • Avoid adding too many tools / functions to one subagent node. If you have many tools / functions, consider splitting them across multiple subagent nodes.