Docs

Input / Output

The Input and Output components are required for every Agentic Flow. The Playground is only available when both are present.


Input

The entry point for the flow. Receives the user’s message or trigger payload and passes it downstream.

Use in a flow

  1. Add an Input node to the canvas (typically at the start of the flow).
  2. Connect the Message output to downstream components (for example, an Agent, Prompt, or Tool Calling Agent).
  3. Optionally connect Conversation History if a downstream step needs prior messages.
Input (Message) ──► Agent / Prompt / Processing ──► Output

In the Playground, users type messages in the Text field. When the flow runs via API or channels, the message or trigger payload passes through the same output.

Parameters

ParameterDefaultHiddenDescription
Text—NoThe message to pass as input. Used in the Playground and when no external input is wired.
Conversation History—NoPrior conversation messages to include as context.
Store MessagestrueYesWhether to store the message in chat history.
Sender TypeUserYesIdentifies the sender as User or Language Model.
Sender NameUserYesDisplay name for the sender.
Session ID—YesChat session identifier. Uses the current session if empty.
Files—YesFiles to attach with the message (PDF, DOCX, Excel, PPTX, images, text).
Background Color—YesBackground color for the message icon in chat.
Icon—YesIcon for the message in chat.
Text Color—YesText color for the sender name in chat.

Outputs

OutputDescription
MessageThe user’s input as a message. Connect to downstream components.
Conversation HistoryConversation history as a message. Use when downstream steps need chat context.

Output

The exit point of the flow. Returns the final result to the caller or connected channel.

Use in a flow

  1. Add an Output node to the canvas (typically at the end of the flow).
  2. Connect the final response to Text (from an Agent, LLM, or other component that produces a message).
  3. Run the flow in the Playground or via API to see the result.
Agent / LLM ──► Output (Text)
Input ──► ... ──► Output

Parameters

ParameterDefaultHiddenDescription
Text—NoThe bot response to display. Accepts Message, Data, or DataFrame input.
Store MessagestrueYesWhether to store the message in chat history.
Sender TypeLanguage ModelYesIdentifies the sender as User or Language Model.
Sender NameAIYesDisplay name for the sender.
Session ID—YesChat session identifier.
Background Color—YesBackground color for the message icon.
Icon—YesIcon for the message.
Text Color—YesText color for the sender name.
Channel DeliveryfalseNoWhen enabled, delivers the message to configured outbound channels.
Assume Policy—NoAccess policy for channel delivery and resource access.

When Channel Delivery is enabled, open Controls to configure delivery targets, routing, and LLM settings for outbound channels.

Outputs

OutputDescription
MessageThe formatted response message returned by the flow.