Session

Trust Protocols for Agentic Interactions: A Practical Architectural Guide

AI agents increasingly invoke APIs, browse websites, and complete transactions across organisational boundaries. Service providers need evidence about the requester, its operator, and the assurances that support a given level of access.

This session provides a practical overview of open standards for agentic trust. We examine Web Bot Auth and HTTP Message Signatures for request integrity and agent authentication; SD-JWT for selectively disclosing credential claims; Verifiable Credentials and DIDs for portable, verifiable assertions; Bitstring Status Lists for credential status; and JOSE for signed and encrypted token formats. We also introduce TSAI as a protocol that profiles these building blocks for the exchange of agent trust signals.

Using an agent-to-service interaction as a running example, we trace the protocol flow from request authentication through credential presentation, status verification, selective disclosure, and application policy evaluation. The session explains the trust decision each component supports and the implementation choices available to agent operators, trust authorities, and service providers.

Alexander Günsche

Senior Solutions Architect at AWS

Aachen, Germany

Actions

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