Join me at AI Engineer World's Fair next week in San Francisco! I'll be discussing how to secure agents using OAuth and what we are building at Keycard. The talk is Thursday, June 5 in the security track. See you there!

Interested in Agent Identity? You won't want to miss Jared Hanson at The Lastmile Meetup in SF on Tuesday evening!

Agents broke our auth systems. We’re all pretending they didn’t. I wrote about the shared guilt, duct-taped credentials, and what we’re building Keycard to fix it: linkedin.com/posts/matthewc…

Agents break the fundamentals of traditional IAM systems - overtime, if you build them, as you did a traditional service, they will end up with god-mode privileges -- access to everything, for every user that interacts -- like katamari damacy. Ultimately, we need IAM systems

The recipe for building Trustworthy AI includes a strong auth strategy. We need a new solution to be rebuilt specifically for agents that takes their non-determinism into account and can make decisions based on the current context. You'll want to keep an eye on Keycard 👀