maestro
latest
false
Maestro Orchestrate user guide
- Introduction
- Getting started
- Build on any canvas
- Build with Case
- Reference
- Defining case keys (system vs. external)
- Establishing task I/O and write-back contracts
- Modeling primary and secondary stages
- Triggering a case from Data Fabric
- Implementing stage-level personas and permissions
- Setting SLAs and automated escalation rules
- Configuring a rework loop (re-entry)
- Configuring and testing the Case Manager Agent (preview)
- Build with Flow
- Build with BPMN
- Operating
- Monitoring
- Optimizing
- Reference information
Conversational tools
Chat nodes for modeling conversational experiences on the canvas, covering routing control, conversational AI turns, and deterministic messages.
The Chat nodes build a conversational workflow. Once deployed, it reaches end-users through every chat channel supported for conversational agents, iFrame embeds, Assistant, Microsoft Teams, Slack, and custom surfaces built with the UiPath TypeScript SDK. Monitor its performance, metrics, and user feedback through chat agent observability.
Available nodes
| Node | What it does |
|---|---|
| Conversation Trigger | Marks the workflow as conversational and starts it when a user initiates a chat on any channel. |
| Wait for Message | Suspends until the user sends a message, then outputs the latest conversation context (chat history) for downstream nodes to consume. |
| Conversational Agent | Runs a single chat agent turn. Streams its responses and takes actions through tool-calls. |
| Send Message | Writes an arbitrary message to the conversation. Use for fixed replies, routing messages, and emitting data from other nodes to the chat. |
| Get Conversation Context | Reads the current conversation history and metadata without suspending the workflow. Generally not needed, but can be used when a downstream node needs to inspect latest chat messages without waiting for new input. |
Capability examples
Combine the conversational nodes with the rest of the nodes in the Add node panel to unlock a variety of capabilities, such as:
- Deterministic branching: route to different node paths based on message content or agent output.
- Agent hand-off: pass the conversation between multiple conversational agents, each with its own prompt and tools.
- Parallel branches: launch any other workflow branches in parallel - such as human approval tasks - while the conversation continues seamlessly to the user.
- Chat termination: end the conversation when a goal is reached.
- Zero-agent conversations: build a fully deterministic chat experience with no large language model (LLM) turns at all.
End-to-end walkthrough
Visit build a chat agent workflow for a step-by-step example that combines the chat nodes into an agent-handoff routing pattern.
Next steps
- Chat conversational agents: surface overview in the Agents user guide.
- Chat deployment: deploy a chat workflow and make it available in Assistant, Microsoft Teams, Slack, a web page, or your own app.