AI agents are software that can plan and take actions, such as reading tickets, calling APIs or sending messages, often without a human in the loop for each step. Treating them as ordinary apps with shared secrets, or letting them run with a human's full permissions, makes it hard to know what an agent can do and to stop it when it misbehaves. Microsoft Entra Agent ID is Microsoft's approach to giving agents first-class identities in Microsoft Entra, so they can be inventoried, governed and protected like users and workloads. It is a newer capability, so expect its portal screens and names to evolve; focus on the concepts.
Keep reading for free
Create a free StudyToCert account to read the rest of this lesson: 5 more sections, 4 key terms, a real-world example, an exam tip and self-check questions. Every lesson, lab and practice test is free with an account.