Session
Beyond Authentication: Implementing Trust Systems for the Agentic Web
AI agents increasingly access websites, APIs, and business workflows on behalf of users and organisations. For a service provider, authenticating a request is only the first security decision. It must also assess who operates the agent, whether relevant claims remain valid, how the agent has behaved, and which evidence supports the requested access.
This session examines the protocol landscape for implementing those trust decisions. We cover Web Bot Auth and HTTP Message Signatures for request integrity; JOSE and SD-JWT for signed credentials and selective disclosure; W3C Verifiable Credentials and DIDs for portable assertions; Bitstring Status Lists for efficient credential-status checks; and TSAI for exchanging agent trust signals.
The session explains how these protocols support an agentic security architecture, from agent authentication and credential presentation to status verification and application-policy evaluation. Attendees will leave with a practical model for selecting and applying open standards to secure agentic systems.
Alexander Günsche
Senior Solutions Architect at AWS
Aachen, Germany
Links
Please note that Sessionize is not responsible for the accuracy or validity of the data provided by speakers. If you suspect this profile to be fake or spam, please let us know.
Jump to top