AI-201 · Question #191
Universal Containers wants to allow its service agents to query the current fulfillment status of an order with natural language. There is an existing autolaunched flow to query the Information from…
The correct answer is A. Create a custom Agent action which calls a flow. In Agentforce, the correct approach to expose an existing autolaunched flow as a conversational AI capability is to create a Custom Agent Action that calls that flow. Agent Actions are the bridge between an Agentforce Agent and backend logic - they can invoke flows, Apex, or…
Question
Universal Containers wants to allow its service agents to query the current fulfillment status of an order with natural language. There is an existing autolaunched flow to query the Information from Oracle ERP, which is the system of record for the order fulfillment process. How should an Agentforce Specialist apply the power of conversational AI to this use case?
Options
- ACreate a custom Agent action which calls a flow.
- BConfigure the Integration Flow Standard Action in Agent Builder.
- CCreate a Flex prompt template in Prompt Builder.
How the community answered
(63 responses)- A78% (49)
- B16% (10)
- C6% (4)
Explanation
In Agentforce, the correct approach to expose an existing autolaunched flow as a conversational AI capability is to create a Custom Agent Action that calls that flow. Agent Actions are the bridge between an Agentforce Agent and backend logic - they can invoke flows, Apex, or external APIs. This lets the agent understand natural language intent and trigger the existing Oracle ERP query flow without rebuilding the integration. Option B ('Integration Flow Standard Action') is not a real standard action in Agent Builder. Option C (Flex prompt template) is used to generate text content, not to execute business logic or query external systems.
Topics
Community Discussion
No community discussion yet for this question.