An Agentforce has created a copilot custom action using flow as the reference action type. However, it is not delivering the expected results to the conversation preview, and therefore needs…

Question

Options

• AIn Copilot Builder within the Dynamic Panel, turn on dynamic debugging to show the inputs and
• BCopilot Builder within the Dynamic Panel, confirm selected action and observe the values in Input
• CIn Copilot Builder, verify the utterance entered by the user and review session event logs for

• A
  75% (44)
• B
  15% (9)
• C
  10% (6)

Explanation

When a flow-based custom action in Copilot Builder is not producing the expected results, the most effective diagnostic tool is enabling dynamic debugging in the Dynamic Panel within Copilot Builder. Dynamic debugging captures and displays the exact input values being passed into the action (i.e., what the LLM extracted from the conversation and sent to the flow) as well as the output values the flow returned. This makes it straightforward to pinpoint whether the issue is in how the LLM is interpreting and mapping inputs, in the flow logic itself, or in how the output is being consumed and displayed in the conversation. Without this visibility, troubleshooting requires guesswork.

No community discussion yet for this question.