AI-201 · Question #232
Universal Containers has multiple Salesforce orgs, each with a unique customer service agent where a verification agent must pass customer identity data to downstream agents handling account modificat
The correct answer is C. Use the Agent API to start the downstream agent's session and pass the verified customer ID as. The AgentForce Inter-Agent Communication and Security Configuration Guide specifies that when sensitive identity data (like a verified customer ID) must be shared between agents, the correct approach is to use the Agent API to initiate the downstream agent's session. The verified
Question
Universal Containers has multiple Salesforce orgs, each with a unique customer service agent where a verification agent must pass customer identity data to downstream agents handling account modifications. The customer ID must remain secure and persistent across agent handoffs without exposure to large language model (LLM) modification. What is the most appropriate configuration?
Options
- AImplement a custom object to temporarily store verification status and have each agent query it
- BStore customer identity information in conversation variables created by the first agent and have
- CUse the Agent API to start the downstream agent's session and pass the verified customer ID as
How the community answered
(26 responses)- A23% (6)
- B12% (3)
- C65% (17)
Explanation
The AgentForce Inter-Agent Communication and Security Configuration Guide specifies that when sensitive identity data (like a verified customer ID) must be shared between agents, the correct approach is to use the Agent API to initiate the downstream agent's session. The verified data should be passed as a read-only context variable, ensuring persistence across sessions while preventing modification by the large language model (LLM). This setup maintains data integrity and security compliance by isolating sensitive variables from the LLM's reasoning layer. Context variables passed via the Agent API are immutable during runtime, ensuring they cannot be altered or exposed in agent-generated responses.
Topics
Community Discussion
No community discussion yet for this question.