Agents are arriving in your tenant from Copilot Studio, Foundry, open-source frameworks and your own code, and each one authenticates and reaches data like any other workload. Most are invisible, over-permissioned and impossible to attribute. So who is your agent, really? It is a non-human identity, and this session treats it as one. We go under the hood of Microsoft Agent 365 and the Entra Agent ID model: the blueprint that holds the credentials and mints the tokens, the agent identity that inherits them and acts, the difference between an agent acting on behalf of a user and acting on its own, and how that same identity behaves across Foundry, Copilot Studio and the platforms you do not control. You leave able to inventory the agents you already have, design blueprints and scope their permissions before you deploy, and budget for agents as identities rather than seats.

Level 300
~ 45 mins, depending on demos.

After this session, participants can:
Inventory the agents already in their tenant and treat each one as a non-human identity.
Design Entra Agent ID blueprints per trust boundary and scope agent permissions before deploying.
Tell on-behalf-of from own-identity access, and budget agents as identities, not seats.