Coral Cloud Resorts (CCR) sees the agent forgot the dietary/activity preferences gathered earlier. They need those preferences to persist throughout the session. What should CCR implement?

The correct answer is C. Create a context variable to capture/store customer preferences as action outputs. Context variables in Agentforce are session-scoped variables that persist for the lifetime of a single conversation. They can be populated from action outputs (e.g., after an action collects dietary preferences, the result is stored in a context variable) and then referenced by…

AI Features for Service (e.g., Einstein Bots, Next Best Action)

Question

Options

AConfigure custom variables to capture/store customer preferences from action outputs.
BRely on natural conversation memory and instruct the agent to look back.
CCreate a context variable to capture/store customer preferences as action outputs.

How the community answered

(54 responses)

A
6% (3)
B
11% (6)
C
83% (45)

Explanation

Context variables in Agentforce are session-scoped variables that persist for the lifetime of a single conversation. They can be populated from action outputs (e.g., after an action collects dietary preferences, the result is stored in a context variable) and then referenced by subsequent actions in the same session. This is the correct mechanism for session-level memory. Choice A describes 'custom variables,' which is not the standard Agentforce construct for this purpose. Choice B (relying on the LLM's natural conversation memory) is unreliable and not a supported design pattern for critical data-the LLM's context window is not guaranteed to retain earlier inputs as the conversation grows.

Topics

#Einstein Bots#Context Variables#Session Management#Conversational AI

Community Discussion

No community discussion yet for this question.

Full AI-201 Practice