Keycard

"There's no separation between the control and data planes." @guypod (founder of @tessl_io and @snyksec) That's why prompt injection works, and why you can't secure a skill from inside the model. The fix: put the control plane where the context can't reach it.

The energy at AAuth Night: Moving Beyond OAuth was incredible! @jankytweet shared how ID-JAG makes OAuth better today. @DickHardt introduced AAuth, a new protocol that tracks an agent's mission and runs agents without API keys. Thanks to our panelists and everyone who demo'd and @okta @snyksec @KeycardLabs @cloudsa for their support!

AAuth Night: Moving Beyond OAuth is TONIGHT We have over 500 people registered for our @aiDotEngineer side event! It's a stone's throw from Moscone and doors open at 5:30pm expect DEMOS + PANEL + COMMUNITY

What an honor to emcee the first day of @aiDotEngineer and introduce the Software Factories Track Thank you @swyx & team, and @KeycardLabs for the support. “A year ago @GeoffreyHuntley released the Ralph loop. It captured our attention and sparked our imagination as we watched Ralph loops work autonomously overnight and forge entire products on its own. However, it wasn't perfect and in the early days it came recommended for greenfield work only and it came with the expectation that it would get you about 90% of the way there. Since then we've learned quite a lot about loop engineering and in the last year there's been considerable advancements that make now that largest inflection point for software factories. Model vision has improved allowing them to see and verify work they couldn't before. Agents now have access to far richer tool ecosystems and live data, enabling them to work across real production environments. AI security practices have matured, giving agents the security, autonomy, and capability they need to perform meaningful work. Context windows have gotten larger and agent memory has improved allowing agents in a loop to track what's been done before. Lastly, reasoning models have improved helping the model think through more sophisticated tasks. All of this comes together now. Software factories are no longer a vision for the future. They've become a practical reality. Today's speakers are on the frontier of this shift and helping define this inflection point. They'll help us separate what's real from what's hype, share what actually works, and how to build software factories that produce reliable results, not slop.”

THE GREAT LOOPS DEBATE is on @ianlivingstone and @GeoffreyHuntley take on @dexhorthy and a surprise guest to answer Do loops produce slop? Do we have the AI infra we need today to verify the work and track state? What tasks are right for loops? Main stage 7/2 @aiDotEngineer

Join Snyk and Keycard for an all-you-can-build rooftop party at AI Engineer World's Fair! Next Tuesday, June 30th, we're gathering the boldest builders and security folks in the AI era. Expect vibe coding battles, a live AI red team challenge, and a happy hour to keep it going. See how your build holds up against the people redefining how we build and secure. RSVP before spots run out: lnkd.in/ejnJfnp7

60 verified vulns including auth bypasses. Cost: $1,000 in compute. "They were all off the critical paths, and impact was limited, but they were issues we would have absolutely paid bounties for." @zeeg (CPO, @sentry) on what agents can actually do once you get past the hype.

LLMs hallucinate 12-50% of the time. Agents turn those mistakes into real actions: shipped code, sent emails, dropped databases. Herman Errico (@TrustVanta), creator of AARM (@cloudsa), came on to tell us why you secure agents by blocking the action before it runs. Out now