We're having fun talking to everyone at AGNTCon this week about runtime auth for agents. We led a debate on if security is ready for a headless future and gave a talk on how to give agents autonomy, capability, and security. Today is our last day, come say hi and see a demo!

What an amazing week! We spent the first half @aiDotEngineer NYC and the second half in SF for @AISecSummit and AAuth Night. We enjoyed meeting all of you and talking about runtime auth for agents, intent-based auth, and the new software factory reference architecture.

We're hosting Secure Software Factory Show and Tell Oct 13 during @aiDotEngineer NYC with @braintrust, @SocketSecurity, and @Docker Learn how to constrain, observe, and authorize your agents, validate their inputs, and respond when something goes wrong.

AI agents can only be truly autonomous if they have the authority to act and that authority is tightly controlled. At ODSC AI West 2026, @ianlivingstone, Co-Founder & CEO of @KeycardAI, will present “Autonomy Requires Authority: Building Auth for AI Agents.” Ian brings 15+ years of experience across developer tools, security infrastructure, and platform engineering, including previous roles at Snyk and Salesforce. At Keycard, his work focuses on trusted, autonomous agents and the infrastructure needed to let them access tools and services safely. In this session, he’ll explore the shift from static credentials and inherited permissions toward ephemeral access, delegated authority, runtime context, and attributable agent actions. Join Ian at ODSC AI West 2026:

On Tuesday Oct 13th @aiDotEngineer NYC our CEO @ianlivingstone takes the stage with Michael Davis, Global Chief Security Architect at @jpmorgan, @DickHardt Founder of AAuth and co-creator of OAuth, and @vtahowe to discuss intent based auth.

Keycard is going to @aiDotEngineer NYC October 12-14! Here's where to find us: Come see us at our booth (number 15) anytime. Swing by to enter our raffle, see a multi-agent demo using A2A, and chat with our team about agent identity and runtime authorization. Monday Oct 12, 3:30pm-4:30pm: @KimMaida, our Head of DevRel, leads a workshop on secure, durable agents with @temporalio. Tuesday Oct 13, 11:30am-12:20pm: Intent Based Auth panel, featuring @ianlivingstone, CEO of Keycard, Michael Davis, Global Chief Security Architect at @jpmorgan, and @DickHardt, founder of AAuth. @vtahowe moderates. Tuesday Oct 13, 2:30pm-2:50pm: Kamil Potrec Product Lead, runs an expo session on agent auth across gateways and SDKs. Tuesday Oct 13, 5:30-8:30pm: Keycard is hosting Agent Baseline Demo Night with @braintrust, Dick Hardt, and others to explore a reference architecture for building, deploying, and operating production agents. RSVP: We're excited to meet you and hear how you're handling auth for agents.

Really enjoyed talking with @MollySOShea about why we’re entering the systems engineering phase of agents. The raw intelligence is here, but making agents the default in software means figuring out how to make them cheap, reliable, and safe without nuking their ability to reason and solve problems dynamically. That is why we’re building auth for agents at @KeycardAI.

Join us tomorrow night in SF with @temporalio and @MongoDB to learn how to build a durable agent with memory and auth! You’ll learn how to build agent workflows that stay current, recover cleanly, and scale beyond a fragile demo. RSVP:

I've always found Satya a salient thinker, and once again he nails it here. As AI gets more capable, we need to keep pushing to democratize access, increase choice, and build the controls that let us adopt it safely at any scale. We started @KeycardAI because we believe in a future where trusted, autonomous agents are everywhere, and everyone can access them and build them themselves. The problem is that agents break the security models we've relied on for decades because they were built for humans, not millions of non-deterministic machines acting on our behalf. Democratizing that future requires authn/z built for this new world: delegated, task-scoped and revocable access, identity carried through every tool call, a tamper-resistant record of who did what and on whose behalf, and intent-based authorization that can reason about what an agent is trying to do and apply deterministic boundaries dynamically at machine scale. That's the infrastructure we're building at @KeycardAI.

I'm stoked for next week's Builder After Hours: Durable Agents with @MongoDB , @temporalio, and @KeycardAI (9/15, SF). Instead of the usual lineup of separate talks, @MelGoesTech is bringing a fresh take: co-presenting one shared architecture, then diving into each component. RSVP here:

Auth for agents is the biggest remaining gap between cool toy and production grade autonomy. The permission problem is perpetuated by an age of human driven computing where static roles and broad scopes were sufficient - it doesn’t work for agents - permissions have to be task scope and contextual to the progression of the task. We’re solving this @KeycardAI

During the Hugging Face incident agents tampered with their transcripts to cover up their actions. Therefore, the audit log must live outside of the agent's control. In Keycard, every action in a delegation chain is captured as real-time telemetry.