Keycard puts users, developers and companies in control of AI agents with real-time, adaptive permissions and complete transparency.
Joined December 2024
- Tweets276
- Following43
- Followers4.7K
- Likes155
Your best coding agent lives on one developer’s laptop. A software factory is when the whole team can share and learn from it.
Here’s how to get there: keycard.ai/blog/from-agent-s…
Read more about the Secure Software Factory reference architecture, in partnership with @Docker, @SocketSecurity, and others as part of Agent Baseline: agentbaseline.org/reference-…
Our panel on Intent Based Auth @aiDotEngineer NYC is LIVE on YouTube
@ianlivingstone CEO Keycard, Michael Davis Global Chief Security Architect @jpmorgan, and @DickHardt Founder of AAuth discuss why we must have runtime auth for agents based on intent.
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.
Read the Software Factory Reference Architecture
xitter.cf/ianlivingstone/status/…
Today we're publishing the first draft of the Agent Baseline Software Factory Reference Architecture!
An opinionated blueprint for securing increasingly autonomous software factories, built with folks across the community.
It's open for feedback and contributions!
agentbaseline.org/reference-…
An agent's access for a task should be the overlap of what it can do and what the task needs, all inside what the org allows. More on how that works below.
We've spent a lot of time at @KeycardAI thinking about how authentication and authorization need to evolve as agents take on more work.
API keys and OAuth scopes were never designed to account for tasks, delegation between agents, or agents acting on their own.
I wrote about how we're approaching this and what we think needs to change.
keycard.ai/blog/defining-aut…
Then access is enforced as the work happens: short-lived credentials per task, denied by default, and escalated only when policy allows. Task done, access gone.
That context has to come from the trigger and the handoff chain, never from the agent's own description of its task. Otherwise an agent can talk its way into more access.
Who's acting matters as much as what. An incident agent woken by an alert acts as itself. When it hands log analysis to another agent, that agent gets only what that piece of work needs.
Keycard retweeted
Today we're publishing the first draft of the Agent Baseline Software Factory Reference Architecture!
An opinionated blueprint for securing increasingly autonomous software factories, built with folks across the community.
It's open for feedback and contributions!
agentbaseline.org/reference-…
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.
luma.com/keycard-rg1c
Keycard retweeted
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: hubs.ly/Q04yVWNV0
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.
Come for the panel and then join us that evening at Elsie Rooftop for Agent Baseline Demo Night with @SocketSecurity and @braintrust
RSVP: luma.com/keycard-rg1c
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: luma.com/keycard-rg1c
We're excited to meet you and hear how you're handling auth for agents.
Keycard retweeted
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.
Ian Livingstone (@ianlivingstone) CEO of @KeycardAI says the biggest thing standing between today’s AI agents & true autonomy actually isn't intelligence..
“We have apparently AGI, but the real thing that stops us from having autonomous agents that actually work, like a self-driving car, is identity & access.”
“Our systems weren't built for agents that are non-deterministic actors.”
Our CEO @ianlivingstone gave some pretty hot takes at @browserbase's Navigate Conference
Ian says AGI might be here but identity and access is what's preventing agents from being truly autonomous
Ian Livingstone (@ianlivingstone) CEO of @KeycardAI says the biggest thing standing between today’s AI agents & true autonomy actually isn't intelligence..
“We have apparently AGI, but the real thing that stops us from having autonomous agents that actually work, like a self-driving car, is identity & access.”
“Our systems weren't built for agents that are non-deterministic actors.”
We had a great time learning about the infra behind reliable agents with @MongoDB and @temporalio!
We showed how Keycard replaces static secrets with per-agent identities and task-scoped, short-lived credentials, so an agent can only do the thing it was asked to do.
