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
- Conversational agent
- Voice agent
- Coded agent
- Third-party agent
- Build with BPMN
- Operating
- Monitoring
- Optimizing
- Reference information
Third-party agent
Call an AI agent that runs on another platform, such as Databricks, Google Vertex, Microsoft Azure AI Foundry, Salesforce Agentforce, or Snowflake Cortex.
Third-party agent lets a workflow call an AI agent that runs on another platform. The workflow sends the agent a task, and continues with its answer.
Add a third-party agent
- Select + on the handle of the node it follows, then select Agent > Third-party agent.
- Pick the agent's action. The list is grouped by platform, for example:
- Databricks Agent: Query a Serving Endpoint
- Google Vertex: Execute Google Vertex Agent
- Microsoft Azure AI Foundry: Invoke Agent, Execute the Thread
- Salesforce Agentforce & Flows: Execute Salesforce Agent
- Snowflake Cortex: Interact Agent, Run Agent Without an Agent Object
- In the properties panel, select a connection to that platform, or create one. Connector nodes describes connections.
Each platform's action has its own fields. The connector's documentation describes them. For example, About the Agent 2 Agent connector describes how to call any agent that supports Agent2Agent (A2A), an open protocol for communication between AI agents.
Next steps
- Autonomous agent: build an agent on the canvas instead.
- Coded agent: call an agent that a developer wrote in code.