Multi-Agent Interoperability

AGENTFORCE-SPEC · 10 questions

• Meridian Veterinary Group's imaging partner runs its own external diagnostic AI model that flags abnormal chest X-rays. Meridian's Service agent needs to pull structured findings from that external model into a referral case, and the Salesforce admins want central control over exactly which tool calls and context are allowed to cross the org boundary. Which mechanism should the agent use to consume that external model as a controlled tool?
• A general-practice clinic's Service agent triages a case that needs cardiology follow-up. Rather than teaching the GP agent all of the specialty hospital's cardiology intake logic, Meridian wants the GP agent to route the case to the specialty hospital's own Agentforce agent, which asks its own follow-up questions, books the specialist slot, and reports completion back. Which mechanism enables this hand-off between the two separate Agentforce agents?
• When Meridian's agent uses MCP to send a referral case summary to the specialty hospital's external triage model, that summary would normally include the pet owner's phone number and home address. Which capability ensures that PII is masked before it leaves Salesforce's boundary in that exchange?
• Meridian's pet-insurance partner has built its own external claims-adjustment AI system, and wants that system to be able to ask Meridian's deployed agent 'what is the status of claim X' on demand, without any Meridian staff mediating the exchange. Which mechanism fits this integration?
• Meridian's pet-owner mobile app is a custom-built native app, not an Experience Cloud site. Product wants the Service agent's conversational experience embedded directly inside that app's chat screen, with the mobile team controlling their own UI while calling into the Agentforce backend for responses. Which mechanism should the mobile team use?
• When the GP clinic's agent hands a referral to the specialty hospital's agent via the agent-to-agent protocol, the specialty agent needs enough conversation history to avoid re-asking the pet owner questions already answered - but the GP clinic doesn't want to expose its entire case record. Which statement correctly describes the hand-off behavior?
• Meridian's pharmacy fulfillment vendor already exposes an MCP server with standardized tools for checking refill eligibility and controlled-substance holds. An architect is deciding between building a brand-new custom Apex invocable action against the vendor's proprietary REST API, or configuring the agent to connect to the vendor's existing MCP server. Which choice, and why?
• The mobile team building against the Agent API needs each pet owner's conversation with the agent to maintain continuity across app restarts, and needs the agent's responses to reflect that specific owner's own data access rather than a single shared identity for every request. Which consideration must the integration handle correctly?
• The specialty hospital's own external research tool wants to securely query Meridian's Agentforce-configured org for read-only referral case status, using a standardized protocol rather than a bespoke point-to-point integration Meridian would have to build and maintain. What should Meridian configure?
• Meridian keeps adding topics and actions to a single Service agent to cover appointment booking, refills, claims, and referrals, and the agent is starting to misclassify what pet owners are asking for. An architect proposes splitting claims handling into its own dedicated agent that the Service agent delegates to when needed. Why does this multi-agent approach, enabled by the agent-to-agent protocol, help?