Before activating a custom copilot action, An Agentforce would like is to understand multiple real-world user utterances to ensure the action being selected appropriately.
Which tool should the Agentforce Specialist recommend?
Model Playground (specifically within the context of Generative AI and Copilot in Salesforce) allows you to test and refine the behavior of your AI models and, by extension, how your copilot actions interpret and respond to different user inputs (utterances). It ' s a sandbox environment where you can:
Input various user utterances.
See how the underlying Large Language Model (LLM) and the copilot ' s reasoning engine classify those utterances.
Observe which actions are triggered by those utterances.
Adjust the action instructions and examples to improve the copilot ' s understanding and ensure the correct action is chosen for specific user requests. This iterative testing is crucial for ensuring the action performs as expected in real-world scenarios.
Contribute your Thoughts:
Chosen Answer:
This is a voting comment (?). You can switch to a simple comment. It is better to Upvote an existing comment if you don't have anything to add.
Submit