Skip to main content

AI Agents Overview

AI Agents enable intelligent, automated interactions within your application. They can process user messages, trigger tools, and respond with contextually relevant information. For a broader introduction, see the AI Agents section.
Note: Currently, an Agent only responds to Text Messages.

Agent Run Lifecycle and Message Flow

This section explains how a user’s text message to an Agent becomes a structured “run” which emits real-time events and then produces agentic messages for historical retrieval.
  • A user sends a text message to an Agent.
  • The platform starts a run and streams real-time events via the AIAssistantListener.
  • After the run completes, persisted Agentic Messages arrive via the MessageListener.

Real-time Events

Events are received via the onAIAssistantEventReceived method of the AIAssistantListener class in this general order:
  1. Run Start
  2. Zero or more tool call cycles (repeats for each tool invocation):
    • Tool Call Start
    • Tool Call Arguments
    • Tool Call End
    • Tool Call Result
  3. Zero or more card streams (repeats for each card the agent produces):
    • Card Start
    • Card
    • Card End
  4. One or more assistant reply streams:
    • Text Message Start
    • Text Message Content (multiple times; token/char streaming)
    • Text Message End
  5. Run Finished
Notes:
  • Run Start and Run Finished are always emitted.
  • Tool Call events appear only when a backend or frontend tool is invoked. There can be multiple tool calls in a single run.
  • Card events (Card StartCardCard End) appear only when the agent produces a card, and repeat for each card.
  • Text Message events are always emitted and carry the assistant’s reply incrementally.

Event descriptions

  • Run Start: A new run has begun for the user’s message.
  • Tool Call Start: The agent decided to invoke a tool.
  • Tool Call Arguments: Arguments being passed to the tool.
  • Tool Call End: Tool execution completed.
  • Tool Call Result: Tool’s output is available.
  • Card Start: The agent began producing a card; carries a cardId and an executionText loading label.
  • Card: The full card payload for the given cardId is available to render.
  • Card End: The card stream for the given cardId is complete.
  • Text Message Start: The agent started composing a reply.
  • Text Message Content: Streaming content chunks for progressive rendering.
  • Text Message End: The agent reply is complete.
  • Run Finished: The run is finalized; persisted messages will follow.

Card Streaming Events

When an agent produces a card, it is delivered through three streaming events on onAIAssistantEventReceived. Each event is a subclass of AIAssistantBaseEvent — check the concrete type to handle it.

Agentic Messages

These events are received via the MessageListener after the run completes.
  • AIAssistantMessage: The full assistant reply.
  • AIToolResultMessage: The final output of a tool call.
  • AIToolArgumentMessage: The arguments that were passed to a tool.

AIAssistantMessage Elements

Once a run completes, the assistant’s reply is persisted as an AIAssistantMessage. Its content is exposed as an ordered list of blocks via getElements(), letting you render text and cards in the exact order the agent produced them. When getElements() is null or empty, fall back to the plain getText() body. Each AIAssistantElement exposes: