← Microsoft Certified: Power Platform Fundamentals
AZURE · objective · 23% of the exam
Describe features and capabilities of agents in Microsoft Copilot Studio
Exam objectives are the official skill domains Microsoft Certified: Power Platform Fundamentals tests. Below are the official AZURE docs our questions on this objective cite — review them, then practise.
Sign in to track your progress on this objective.
Official references for this objective
-
Microsoft — Apply generative orchestration capabilities - Microsoft Copilot Studio | Microsoft Learn
In generative mode, the agent generates questions on its own instead of requiring you to manually add question nodes to prompt for missing information.
-
Microsoft — Available knowledge sources for agents - Microsoft Copilot Studio (GitHub Copilot) | Microsoft Learn
Confluence (Advanced) Connect to Confluence workspaces to let the agent reference team documentation and knowledge base articles.
-
Microsoft — Connect to custom knowledge sources - Microsoft Copilot Studio | Microsoft Learn
System.SearchResults : Where the topic stores formatted knowledge snippets.
-
Microsoft — FAQ for generative orchestration - Microsoft Copilot Studio | Microsoft Learn
Admins can restrict which tools and agents are available. Makers can require user confirmation before executing tools that modify data.
-
Microsoft — Files the agent creates (preview) - Microsoft Copilot Studio (GitHub Copilot) | Microsoft Learn
The file isn't surfaced in the response. The turn continues, and the agent typically explains why the file wasn't produced.
-
Microsoft — Tools overview for agents - Microsoft Copilot Studio (GitHub Copilot) | Microsoft Learn
Look up real-time data from external systems, such as Customer Relationship Management (CRM), IT Service Management (ITSM), and databases Take actions on your behalf, such
-
Microsoft — Use public websites to improve generative answers - Microsoft Copilot Studio | Microsoft Learn
All content is checked twice: first during user input and again when the agent is about to respond. If the system finds harmful, offensive, or