AGNTCon + MCPCon Europe 2026

Enterprises understand human identity fairly well. You could argue they are decent at service accounts. But what about an AI agent? Is it either of these?

Agents are driven by intent, discover/invoke tools, make decisions, and interact with other resources (APIs, databases, other agents, etc). Enterprises will care about "Who is this agent?", "What is it allowed to do?", "What has it done?" and of course "Can we revoke its authority?"

In this talk we'll break down what actually makes up an agent's identity. We'll look at authentication, delegated authority, provenance, trust establishment, and accountability. We'll also examine where technologies like OAuth, OpenID Connect, SPIFFE, and emerging efforts such as AAuth fit into the picture.

You'll leave with a practical framework for thinking about agent identity, which problems have already been solved, and which ones we're still figuring out.