Question
A company has a Microsoft Power Platform environment that contains Microsoft Dataverse data.
You create a Microsoft Copilot Studio agent named Agent1 that processes the Dataverse data.
You discover that Agent1 fails to return relevant or accurate results.
You need to improve the quality and reliability of data grounding.
What should you do?
- A. Retrain Agent1.
- B. Verify and cleanse the Dataverse data. Correct
- C. Use an adaptive card in Agent1.
- D. Add example user inputs to the training data of Agent1.
Explanation
According to Microsoft documentation, ensuring data quality is fundamental for reliable outcomes from AI agents like Agent1. By verifying and cleansing the Dataverse data (Option B), you directly address potential inaccuracies or inconsistencies in the dataset that could lead to poor performance of Agent1.
