An AI Agent Got Its User Banned From Resy — Keycard, JPMorgan Chase & AAuth

Um, hi, everyone. Welcome to, um, AI Engineer New York. I'm super excited to be here today. Uh, my name is Allie Howe. I'm a member of technical staff at Keycard. Um, I'm here with some amazing panelists today. We have Ian, CEO of Keycard. We have Michael Davis, um, Global Chief Security Architect at JPMorgan Chase. And we have, we have Dick Hardt, the founder of AAuth and co-creator of OAuth with us on stage today. I'm super

excited to talk to all of them about intent-based authorization. Um, and to set the stage, I wanna bring to light that as more companies are looking to give their agents increased levels of autonomy, they're looking to runtime authorization to help. Runtime auth is the practice of authorizing an agent per tool call rather than having the agent hold broad-standing access that it will eventually misuse. However, is this tool call or not is never a simple question. This is

because many MCP tools and MP-- APIs are coarse-grained, humans struggle to write the perfect policy, and the environment around the agent will change as it runs. Intent can help by providing extra context so that at runtime we can make better authorization decisions about what an agent is allowed or is not allowed to do.

So as to continue, I would like to talk about, um, really dri-dive into why do we need intent-based auth in the first place? Models have dramatically improved. They have bigger context windows. They're able to verify work because model vision capabilities have improved. In many contexts, people are proclaiming that AGI is here. If the models are so good, if AGI is really here today, then why are teams struggling to give their agents more autonomy? Ian, let's start with you.

You're helping many financial enterprises at Keycard. What are you seeing that's getting in the way?

Well, I think broadly speaking, enterprises, especially financial services firms, regulated industries, are almost always security first. It's how they build trust in their business, and maintaining the business continuity is bar first, like, the first priority. Then innovation is second, third, or fourth. I think, like, broadly speaking, in s- in any enterprise, what you see is this, like, hodgepodge of different little islands, of different little identities, of different little systems of, from across all different worlds. And how do you actually tie that together in a way that an agent can navigate through that, ask for

access, and then also ensure that the agent cannot perform, like, a, something that was unintended by the user or the business? And the unfortunate sit-situation is most of our systems today are coarse-grained, right? I don't know, Salesforce is a good example, where for a very long time they had a single scope, which was API on their OAuth, which is, like, in the context of an agent, uh, not very helpful. So that's, that's the broadly the first and foremost part, is that most of the systems they have for security today were designed for a world where humans were making all the decisions and software was very deterministic, not

this newfangled magic box we've invented that basically reasons and tries over and over again to find a solution to a problem.

Dick, how is OAuth part of the problem? How is OAuth getting in the way, and why is it not the right fit for agents?

Well, when people started looking at how do we authorize agents to access something, the tool that was sitting there on the shelf was OAuth. And people grabbed that tool and says, "Here's a tool. This is authorization. It should be able to solve the problem." But OAuth was not designed for this kind of world. It was designed originally for, like, how do I let this website talk to this website? You know, in OAuth 2.0 we added scopes. Before that it was just do anything. Um, but it required you to be pre-registered. It's expecting that there's a

browser involved and a redirect. You know, OAuth has evolved over the years to support some other things, but the agentic world is completely different. We don't know ahead of time what the agent needs to do. We need to go and make that decision over time. Different instances of an agent are gonna need different kinds of things. And, you know, as Ian talked about, the granularity of the scopes that people says, "Well, we already have scopes for OAuth, let's just map those over to agents," is far too coarse-grained for what agents are doing.

Davis, how are you seeing enterprises move towards higher levels of autonomy?

Yeah. I think the key piece is, uh, how do you deal with that coarse-grain problem? And what I've seen the kind of more successful enterprises, they kind of board agents like they onboard developers, right? Start with you don't get full, you know, commit access day one, right? You're actually having to go through and add the levels of capability as they mature, right? And so the definitions that enterprise are coming up with are what is the context that makes this agent safe? And it isn't just usually what the agent says, right? Um, it can, you know, attest to something, but it's other things like the environment

around it and other information that can help you understand levels of autonomy. Very simple example would be where is the sandbox running, right? Is it in the sandbox, right? Those type of things can change the level of autonomy that's allowed.

Absolutely. Yeah. So we mentioned that coarse-grain access problem. And to put that into perspective, um, to give an example, um, with Notion's MCP server, you can say, "Fetch this page," which is, like, the view page, um, tool or get page. But you can't say, "Just get this database on this page." Um, how is runtime authorization based on intent a better model? That's for anyone.

Oh, I'll take a shot at it. So to me, um, this is something that the financial services industry, hopefully maybe we can learn from the background that, you know, banks have gone through. Um, banks moved long ago from authorizing and authenticating humans to authorizing the transaction, right? And when is that transaction occurring? At runtime, right? Um, and so I think that, you know, runtime authorization is we're gonna be able to learn from the kind of the scars of the past that we've had and apply it to this new, new problem. Um, I also think that, uh, you know, one thing

is it's a lot easier to debug something at runtime when you understand the intent, right? I think we've all remember back in the day writing checks, right? But, um, or seen those things on TV now, I guess, is the right thing. Um, but, uh, you know, writing checks, there was a memo field there. Right? That memo field was used to actually tell the intent of what this payment was. But the check itself did have limits, right? The price, the payee, the date, et cetera, right? Uh, I think a lot of those concepts are now being applied and can be applied to help with this runtime.

Intent's sort of one of those, you know, like many words, words are hard. And so, you know, uh, building on, uh, the example here of making a payment of a transaction, right? You know, that's not a scope. That's can I do this one thing in this particular context? Well, this one payment. But I think we need a, an agent we-- to making a decision should it be able to do it, you need all the rest of the context of, well, why are we making this payment? What are all the things that happened before? You know, did we just make the same payment just, like, you know, five

seconds ago and now this is a double payment?

Right.

Right? You know, just because this is right in context does, by itself, doesn't mean it's the right thing within the broader mission. And so, you know, in AAuth, we're working on the concept of a mission that is what do we want the agent to accomplish big picture? And then each of the decisions are made within the context, you know, the intent around what's happening big picture around doing that. And you need granularity at the transaction layer for many of the things to know what exactly is happening, not just I'm

allowed to go and make payments.

Yeah. I think one of the most interesting things, I think, about, like, a practical example, like, to understand, like, why intent's required is if you have two ChatGPT sessions or two Claude sessions, in one session I say, "Hey, help me go do some shopping," in the other session I say, "Hey, help me understand if there-- why there's a bug in production," those, those have very different, like, profiles in terms of, like, a, like, what permissions they should have and also when they should bring you back into the loop. Like, when should the human be involved again? And so at the end of the day, if we don't have intent or some capacity to, like, relay what is the user or the business' intent with

this thing, we actually can't get to, like, autonomy, right? And so a lot of the talks this morning were, "Well, hey, we're gonna run our business on agents. We're gonna do all this stuff." It's like, well, great. What happens the first minute, like, Pocket OS style incident happens where, like, it actually accidentally deletes a production database instead of staging because it has coarse-grained access instead of, instead of long-scoped access? And so we-- what we want as an industry is to leverage this, like, magic box we've created to, like, automate our lives. The current state of the world is that you can do that and take all of the risk, and then you can see all the incidents that

come from it. And so until we actually solve that underlying problem, realizing true autonomy, so being able to operationalize our business and be able to step away as humans and scale that, we have to solve intent first.

Absolutely. And now that we understand why we need intent-based auth, let's talk about what it is practically. What are the primitives? What does it actually look like in practice? Um, Dick hinted at it with the concept of the AAuth mission. Um, so Dick, elaborate on the mission. What is the mission based off of? Is it based off of the user's intent? Is it the agent's intent? Or is it a combination of the two?

Uh, well, the agent, you know, should be working on behalf of the person. And in AAuth, we define a person as either the organization or a human, because it could be operating on either one of those. And so it needs to be acting in the best interest of the person that it's acting on, because that is who's ultimately responsible for what the agent does, right? The agent, agent can't be responsible, right? And, and so the mission is something that the person is giving the agent to do. The agent,

uh, a good agent is gonna go and negotiate with a person to go and talk more about, like, what, what could-- what are the parameters around that? You know, a good example is when you think of back, you know, in the day, which seems like, you know, like, three months ago, when you would want to code something up and you'd create a plan, and then the agent would do the plan. Now you just tell it, and it figures everything out. But that whole concept of what's a plan? What are you trying to do? And you give that to the agent, so then that then is the context around your-- where you're making authorization

decisions later on. And then that mission identifier tracks through everything, so you can go and, you know, audit and be able to see what were all the things that happened and what were the decisions that happened in the context of this one mission, right? Where today, you know, there isn't really a good concept of agent identity or the mission, right? It's just making something and, and things are making decisions without really knowing which expl-- which instance of the agent's doing it or

what's the context of what mission is this involved in, right?

Tell me more about that negotiation phase, because what happens if a user is talking to an instant agent and it talks to the agent and says, "I want you to go read the CEO's email"? That's outside of the scope of that agent, so is that intent rejected from the user?

Uh, should be. Right? So, you know, with a good separation-- and I don't know whether-- I forget whether we're talking about this later, but the separation concerns of the worker, right? There's an agent that's doing the work, and w-we believe there should be a separate agent that's supervising what this one does. And so that you have a separation of concerns where this one can't do any of the work, but it gets to decide what this agent gets to do. And so if the user says, "Oh, I want you to go read the CEO's

email," that's probably gonna get caught in deterministic policies right away, right? Like, that's not a vague thing, right? Reading, reading somebody else's email, we've got good controls for that. Um, but telling the agent to, you know, send the CEO's m-- uh, forward a CEO's email t-to the outside world, that's a little more vague, and that's the kind of thing that ideally comes back to a supervising agent and says, "That's probably a bad idea, and no, you can't do

that."

Absolutely. So I feel like that's another primitive too of intent-based auth is, is policy. Um, Ian, at Keycard, how are you seeing that? When a mission needs to change or a policy needs to update, how can Keycard help keep track of those changes as maybe the mission or policy updates need to be made?

Yeah. I think, like, taking a step back, there's, like-- actually, it was Davis and I were sitting in a room some time ago and, uh Before, like, OAuth and, and some of these other things actually had emerged in the ecosystem, one of the things we actually talked a lot about was consent fatigue. And I think, like, at the minimum, like, we... You always have this, like, how secure do you make a system versus, like, the trade-off of, like, the impact to the human. And so, you know, at Keycard, our broad view on this is you wanna have, like, broad-based deterministic policy that basically says, "This is what must never happen," effectively, right? Or, "These are the things that always require a

human to be involved." And then from there, what you really wanna think about is, okay, cool, well, now that I have that in place, there's a big gap between all of the policy I can write as a human or, or write as an organization, and then what I actually want the policy to be in the specifics of a specific task. And so th- the ne- the real challenge is, how do I, like, layer over those two things, right? 'Cause humans can't write it all. And so there's a version of that that is, like, a user or agent-to-agent interaction, and they have an intent between those two of, like, inter-transactional intent,

and then there's also, like, the business's intent for why they build or adopt an agent. So why did we buy Claude Code? Well, because we wanted to make our developers more successful, or because we wanted to do these different things. And in the context of using Claude Code or whatever, why am I working in this moment with Claude Code? Well, it's actually to fix a bug in staging, right? And those are two different types of intent, and if we can understand those two different things and then convert that some way into, into, uh, like, a bounding box of what those agents can do, you can then basically calculate the intersection of that and say, "Okay,

here's what you can actually do." And then the trick for anyone building these systems is, how do I ensure that I don't bring the user into the loop except when absolutely required? Because it-- that's what's gonna be the adoption curve problem. But that's also the adoption curve problem when it comes to, like, enabling agents to be autonomous in the first place.

That makes sense.

Yeah. I like what you were saying with the intersection. I think that's a unique thing we don't talk about enough within identity and access management, right? Normally, you get access to one thing, right? And so what I've seen successful kind of in this intent-based approach, um, and where I get more excited is you can actually have that, those different intents be from different areas of the organization, right? And so you have the decoupling of these things, and they can kinda live on their own but then come together to form that, you know, decision. And that decision doesn't have to be static, right? So if we use the example of the CEO's email, well, you know, if that

context involves that's the administrative assistant, then yeah, maybe she is supposed to read the email, right? Or maybe just the calendar, right? And so I think when we see and we start thinking about these intersection components, um, we have a totally different way we can start of, you know, expressing policy, but also starting to bring in not just the one side of the equation we always talked about before, which was the app doing something. Now we actually have the ecosystem you can bring in. And so the more I, I see organizations starting to realize that, you know, maintaining that state or that context of these other elements to be able to help

with that intention can completely change the way you're effective at runtime authorization.

And are you seeing this across enterprises today? Most people have mission tracking and policy tracking in place, or is that largely missing today?

No, it's, it's, it's brand new still. Um, and I think, you know, part of the reason why I, I'm excited to talk about it, 'cause I think that it is changing the way to reason through this, right? Even in the most simplistic case, if you're a developer, um, and you are thinking in terms of things like transaction and you have these concepts of intent, um, it makes it easier for you to potentially build the components that'll be composed and used through that intention. Um, and so I think it'll give us more ways to reason through these and communicate, and then ultimately be more interoperable, right? Um, and to me, the last thing that I think is

interesting is the diagnos- diagnostics that you can run on this. Intention is something that flows through many events potentially, right? And I think, uh, th- one of Dick's examples I, I've seen before is, you know, talking about that, like, that, that mission flows through. Um, it could be long-lived. It could be weeks, and intention can still be there. Um, so, uh, it's still very, very early for most enterprises.

Absolutely. And yes, that interoperability is key, and I think that's pretty hard for enterprises because they're j- jumping between different clouds, different environments, different legacy systems, and that policy, that mission has to hold through all of those different hops.

Yeah. A lot, a lot of enterprises still have to deal with the fact that the, the permission says read only, and it's still read write . Right? So, like, you have other problems you have to start dealing with. And so, um, I think that it will help get the, the kinda taxonomy or language a- amongst people to be easier to interoperate, yeah.

Absolutely. One of the reasons why I'm excited about intent-based authorization is because I think it has the ability to be a huge unlock for things like agentic commerce. Um, so let's apply intent-based auth to something real. I think intent-based, based auth adds a lot of value here, and for users it can help them ensure their agents buy the right item with their own personal budget. And for merchants, that means capturing the intent that gives them extra data to understand why a purchase is being made and if this agent should even be trusted to visit their site.

Um, Davis, when we think about agents in the context of financial services and agentic commerce, why is intent-based auth so important?

Um, I think simply it extends the concept maybe not everybody's aware, but some are around, you know, know your customer, right? So I wanna know my customer, know who they are, what they're doing, but I think also we're starting to see, I wanna know my agent, right? So I think that you have a coupling here around the agent itself, um, the intent of the actual user, the intent of the operator, the intent of the processor, right? Et cetera. Um, very... Before now, we couldn't really bring those together, right? Um, it matters of course when it comes to things like commerce because you have additional layers on top of this around, uh,

what was the intention for things like regulatory requirements, et cetera. Um, and this is gonna help, I think, simplify those operations, which means we'll get more access to these agents, you know, doing good work for us.

That makes sense. And another blocker for agentic commerce is the fact that the web wasn't made for agents. Um, Ian, can you tell us how agent identity can help?

Yeah, I think stepping back, we've kinda always had this problem where, like, what do you do with the unregistered client? So, like, I, I show up on eBay, I haven't logged in, I'm using Chrome, eBay doesn't know who I am. How do I do guest checkout? How do I prove I'm a person? How do I, you know... So they can, you know, say, "Yeah, you can bid on the, this pair of socks for $50." And I think if we're all paying attention to what's going on in personal agents, Muse and Instinct and GrokBot and, um, you know, recently this announcement out of Sierra and Decagon and friends around this Personal Agent

Protocol is, like, the fundamental problem we have is, like, how do you have an agent show up to a web- website, be able to interact with the website, know that you actually can trust that agent? So, like, for a long time you had CAPTCHAs on the web. Well, why? It's because we wanna prevent spam. We wanna prevent abuse, so we added CAPTCHAs, and then, like, that's something only a human could solve. So if we have a CAPTCHA, that stops spam, so they can't spam a thing, right? And now we have agents, and they've broken CAPTCHAs. Um, but this has, like, been a traditional problem on the web. In fact, if you think back two to three years Vercel, which is, I think we're all aware of Vercel,

was blocked in Spain. Well, why was Vercel blocked in Spain? Because Vercel shared the same IP addresses for every single host on Vercel, and there was one webs- one host on Vercel, one website on Vercel that they were hosting that was hosting, like, Premier League content. And Spain decided, "Hey, in order for us to stop for that Premier League content being displayed illegally inside Spain, we're gonna block all of Vercel," right? And so in the same way that, like, Vercel has the problem, agents have the same problem, but so much, so much worse. So how do you have unregistered traffic you've never met before show up to your front

door and then decide whether or not you let it in or not? And that's, like, the actual first and foremost fundamental problem we have to solve. It's the same issue with Muse and Instinct, and what they're trying to do is, like, how do we actually create agreeable p- rails that we can all operate on so that as a downstream w- resource, I can decide what, what agents we're gonna allow, who I trust based on who users they are. And then on the other side, I can also know how to talk to those people.

Makes sense. Dick, how is AAuth helping unlock the future of agentic commerce?

Uh, well, the key thing is a, a number of people have been building sort of proprietary closed box systems, right? You know, so, you know, I'm a, a fan of the concept of, uh, uh, personal agent protocol, Poppy. Um, but it doesn't really go far enough, right? It just... It's like, okay, well, now we've got a bit of an agent identity. We just use some of the building blocks, and it's an attractive approach because you're just doing it, but it doesn't solve many of the new things that you need for, uh, an agentic world.

And so a key motivator for people for having standards is that you can plug components from different places, right? So I'm a strong believer that we should have control over what our agents do. At some point, agents can be so much-- doing so much work, there's no way we can have human in the loop approving everything, right? That's just not-- We've already seen that that isn't gonna scale. So that means we need to have a supervising agent that is our supervising agent, that runs our policy and decides how we do things that should

be independent of the agents doing all the work. And if we wanna be able to plug and play those things, we need to be able to have a protocol to separate those. Otherwise, you know, the decision about what the agent can and can't do, what the guardrails, is decided by the agent, by the vendors of the agent around what you can and can't do. And I don't really wanna go and give control to them to decide what I can do, and that all my decisions are based in there. I wanna be able to pull that supervision into another component. And in order to be able

to plug and play pieces, we need to have a protocol that things interoperate.

I would just like add to that. I think, like, right now what we're seeing is, like, we kind of like-- We all want the web to be federated, right? That does-- That, that means, like, re- like, websites or resources on the web can decide what they're allowed to do, but the, the, the standards upon which things operate should be federated, enable us all to interoperate. And I think we're at a moment where things like, you know, we're at a moment where there's a couple large players, and the question for the industry is, are we gonna settle on things that actually bias to the large players and give them, like, concrete block doors? Or are we gonna move to do the thing we've always done, which is build federated protocols? Things like

OIDC, things like, you know, TLS. Those things operated and enabled, like, a broad web, enabled a lot of commerce to occur, enabled a lot of information to flow, enabled all of us to have jobs in a way that because we could be inventive. And so the question I actually ask the broad industry is, okay, this stuff's coming. Which version of the world do we want, one way or the other?

And I'll add, though, I think, um, it's interesting that let's say this all goes perfect, and we've got, you know, agents buying stuff and everybody's kinda happy. What I think will end up happening is we'll start realizing that we have another piece that we have to start working on, which is the human itself. And so one of the things I think when you start having intents being involved is you get what's called psychological ownership, meaning I actually now have a linkage between the human and the outcome of that agent. When you're just kind of, you know, disconnecting it or you, you connected up, uh, an OAuth scope or something like that and a claim and all that, it's kind of magic, and then you don't really know what's going

on. And so I think it'll, it'll-- with intention, it'll be easier for a human to take accountability when things do go wrong. And I think when you're talking about real money being transferred or things like that, you wanna have that human ultimately accountable. I think many people have probably seen the, uh, 1979 IBM manual. It says, uh, you know... And so, like, that, that photo I think is very true in that we can't have the machines be accountable, right? We're gonna have to have the humans linked to it, and intention, I think, is that link.

Yes. And then, yeah, another word for intent is motive- ... like we were, we were talking about last night. Um, and that ability to hold someone accountable, whether it's a person or an agent, I think is really important. And I think intent can also help with that, to be able to understand why did this go wrong? Was it the user's, um, you know, the user was maligned, the agent was maligned? Um, and then using that intent to be able to respond. Um, for each of you, how are you seeing intent provide that benefit and the ability to respond to potentially a maligned user or agent?

Uh, I think it's going back to what I mentioned before about diagnosing, right? So the-- If, if you change the word intent to motive, then you change diagnostics to forensics, right? And I think, um, anybody who's done debugging or had to do forensics of an, uh, AI agent gone rogue, uh, will know that, like, trying to figure out what it was trying to do versus what the intention of the user was, uh, is very hard, right? Um, so having some of that information being propagated and immutable through the system, et cetera, gives you some properties that allow you to more short-circuit your investigation, right? Um, and as those things

become more interoperable, I think we're gonna start seeing companies be able to more quickly kinda scope and identify, well, was this human error? Was this an agent software error? Was this... What was that error? And handle that blast radius appropriately. Uh, we see in the financial system, right, you have different things when you're doing a transaction around, okay, I made this, uh, payment, uh, but it was, you know, incorrect dollar amount or whatnot. You have clear guidelines on how to work with that. We don't have a lot of those when things go wrong right now. So I think intention will help us build those as we get-- go forward.

And I think one area where a recent incident kind of highlights, uh, where intent, um, you can have, like, good intent but still take potentially the wrong action is the Resy incident, um, that happened recently where an Instinct agent went out on behalf of a user and tried to book a restaurant reservation on resy.com. Um, that agent was very eager. It made two hundred API calls an hour, and it ended up getting the user's Resy account banned. Um, Dick, how can AAuth

budgets help in the case where an agent like that is using way too much of a downstream resource, but it still has good intent?

Yeah. Well, this is another example about how just software is completely different now in an agentic world, right? When it was predetermined software, you know, that was a bug if you called two hundred times and you would fix it. Um, where now, well, the agent's like, "Well, I'll just keep trying until I win." Um, and so we saw that as we were, you know, experimenting working with people with AAuth, and we realized, yeah, there's a big problem that agents will learn something and they'll just a- a-abuse the, the system from... They don't think it's

of abuse. They don't know any different. There's been no signal to tell them that, "Oh, I should only use this amount of stuff." And so we added the concept of budgets, where not only do you give a token to the agent that's time-limited as to how long can they do a particular action, but also a budget of how much resource they can do. And so they have access until the, the token's either expired or they've exhausted the budget. And so that way when they come back and, you know, they've exhausted all the budget, the supervision,

you can go and decide, should I give more budget to this agent or not, as opposed to traditional rate limiting, which just cuts it off and then, like, then what do you do, right? And it doesn't know, well, why did I get cut off or anything like that. Where in budget, there's continual feedback to the agent about how much budget was consumed. It has an idea about how much budget it has, and so now it can operate within a budget, right? Like a person would do about, oh, this resource is scarce. I'm gonna be careful about how much I use this.

And how does the brains versus the hands architecture concept come into play here to allow us to, okay, when a ma- a bu-budget is close to being fully reached or is reached, um, how can the brain and hand separation of, of access and the credentials being separate from the agent and the model itself help us be able to stop an agent from using too much of a downstream resource? 'Cause it's getting close and maybe we don't exercise, uh, the ability to give it another credential, for example.

Uh, sorry. I didn't quite follow. The echo in here is horrible, so the-

No worries. That's for anyone. But basically, like, so with the brains and the hands in architecture that we're converging on in an industry, we're basically keeping the credentials and the access from an agent separate from the agent itself. So there's no broad standing access-

Yeah

... that an agent has today, no API keys, which I know is a benefit of AAuth, that AAuth allows agents to run without API keys. How is that helpful in the context of the Resy incident?

The-- When you've got the access to it, um... Sorry, I still don't understand.

Yeah, I, I can jump in.

Yeah. Yeah. Please. Thanks.

I got you. I got you, Dick. So, like, broadly speaking, look, I think if we look back at an incident that I just keep at the top of my mind is, like, Pocket OS, where it found, like, a random key on, on a disk, right? Like, obviously, agents are deeply goal-seeking. So the core of the-- the core of the, the question is, like, okay, well, if we give these, like, agents, we have the brain, which is the model and the LLM, and you have these hands, which is you kind of give them as-- put them in a sandbox, and inside the sandbox are the tools. Um, like, the, the formal idea of the sandbox here that, that's all... that is that, okay, there's n- you can control

what's inside of it. So it can't actually, like, get API access. And then if you have an egress proxy outside the sandbox, that's where you get the heavier authorization boundary. And so not only does it help do translation between systems, right? Which is like that's where AAuth can exist and talk to the outside world or do termination, but also means that, like, the agent, you have, like, a ability to apply authorization at the egress proxy boundary. And so I think at the core of it, that model, which is the predominant model that Anthropic and OpenAI and many other labs are pursuing

today, is, is the model that allows us to both do h- both have the things we want, which is how do we have these things experiment and try stuff out and do silly things, which is the core value, while also having a deterministic layer outside of it that can implement things like AAuth and all the other components we want in our protocols.

I think the decoupling is valuable, right? Going back to, like, mentioned with forensics and being able to separate things. But I do think that we still have a lot to learn on it isn't just one brain, right? And it's very easy actually to build your agent loop, uh, where you put the brain in the loop rather than outside the loop, right? So an example of this would be, you know, people that are leveraging memory systems. Um, they put in some memory and some context that is now used going forward for every agent that is biasing that agent to make a decision to tell the hands, in this case, to go do something it shouldn't do. And so one of the things that I think we

don't talk about enough here is toxic combinations, right? Um, and so when you do separate the hands and the brain and whatnot, you can actually change up, you know, what hands are available, right? So the example that, you know, I've seen be very successful is the removal of tools dynamically based on that actual brain and what it's doing. So the earlier example we gave of reading an email, um, there's nothing that says that, oh, if they're gonna go write an email, I'm gonna disable all, you know, web search tool calls or any other external egress capability tool call-wise until the right email tool has been

complete and that, you know, mission has been done, then I can re-enable them.

Yep.

Right? And so, um, I think that we have to-- we're gonna start becoming more and more, uh, engineering of these different kind of concepts that, um, they are still complicated, they're still growing and, and still nascent, but I think it's a better separation than what we have today.

Yeah, and this is how these things we're talking about, which, you know, seem like geeky OS problems actually then merge back up to, like, real agent engineering problems, which is if you actually understand what you're doing, you know, one of the biggest complaints, less now, but one of the biggest complaints with MCP was context bloat.

Yep.

Like, especially when we had smaller context windows, right? So but intent systems can ensure that the right capabilities are given To the agent at the right time, so they don't spend a bunch of time doing things they shouldn't be doing, right? They, it actually helps them navigate towards the goal state and helps them put them on a more of a paved path. So intent, like, not only unlocks, like, a bunch of security stuff, intent also will result in us spending less tokens because the agent will spend time doing less things that aren't the right pathway, or it'll come up to the point and say, "Hey, I just can't do it." And so what we know about this era is so much of it

is about nudging the agent in the right direction and ensuring it can't do the wrong thing, and that's how you get the outcome you want.

Davis, how are you seeing intent-based auth as part of a larger strategy for production agents? I know when it comes to building, deploying, and operating agents in production, there's many different outcomes teams should be thinking about, such as discovering what's running, what the agent's capabilities are, the ability to validate inputs and outputs-

Right

... constraining an agent, like we talked about, and using the egress proxy and different networking rules. Um, how does all of this fit into play, and what's working inside enterprises today to really be able to ship agents to production?

Yeah. I, I think we're finally... It's helping move the kinda conversation from authentication to authorization, and really, like, how do we do dynamic authorization? How do I validate that authorization? How do I have the human in the loop at the right time? 'Cause I agree with what, uh, Dick was saying earlier, that the human in the loop is somewhat of an anti-pattern in many ways, right? Um, because they can get fatigue, et cetera. But you need to have a way to bring them in when it's important. Those were not engineering discussions before, right? Now they're actually part of the engineering conversation, where engineers are being involved in the

authorization process. They're not just saying, "Oh, I've got my access, I'm good to go." So that actually changes the way we're seeing threat models done. It changes the way we're seeing the full attack surface of applications in general. Um, and so I think you're now looking at this authorization model as a, another kinda set of tools that you can use to reduce not just, um, security issues, but flat-out error rates of your agent, right? Like, I mean, when you have less things the agent can do, it makes better decisions, right? And so fundamentally, we've seen, you know,

real-world cases where the agent loop is just better, faster, stronger because you've actually spent the time on knowing what is the intent they're trying to get? What's the mission that they're trying to accomplish? And then last thing is it, it brings the people together in terms of we now have other different people, the security team, the application team. They're now able to have a conversation that they're using the same language. And a lot of times when it came to identity, it was a completely different language, right? Um, and it was just like, "Get out of my way. What do I have to go do to go ahead and get my, you know, token and I can go forward?" Now they're

seeing that you can actually pair these things and leverage that capability, um, to drive, you know, efficiency of your actual agent outcome.

That makes sense. Ian, how are you applying these concepts to software factories? I know today you released a reference architecture on the secure software factory. How are you applying the concepts of runtime authorization, constraining agents, and all of that to that?

Yeah, I think, like, so there is a, a, a reference architecture we just published on agentbaseline.org. Um, we talked about three different levels of, of factory, one being, like, a human-driven one, one being a workflow-driven one, one being, like, this a-agentic-driven one, which is, like, the thing we all basically wanna get to, which is, like, it's, it's driven by agents. At all points in time, the runtime authorization is a core component of a larger ecosystem that actually enables the, the factory to, like, be able to be pointed in a direction and do the right thing and also get access to the right piece. And it's very--

it looks different than previous things that you would've used, like a secret manager, because it's making very different decisions than previous generations had for managing deterministic software, but it is a core component of enabling the entire thing to work, like when to bring someone into the loop, when what agents could pass what work off to what other agents. You know, how can we have an agent that can have access to production systems and do an auto patch? Um, these are fundamental questions of, like, how do we actually solve how to scale software? Right now we're in a position where, like, we've never been able to generate more software, uh, but we never actually-- but we have a complete bottleneck in

getting into production and ensuring it works. And that's the, the next phase is, like, how do you actually graduate from just using LLM to generate text and software to actually making it capable of deploying it into production, iterating on it, and getting it to a stable state quickly and then responding to instances that arise.

Davis, on a podcast you did with me, we talked about how cybersecurity has something to learn from robotics. Um, in robotics, there's this concept when maybe a robot raises its arm, it thinks, "Is it safe for me to raise my arm? Should I? Am I allowed to do that?" But it also looks at its external environment and says, "What has changed? Is it, is it still safe for me to raise my arm?" Um, when we think about runtime authorizations, what do those decisions need to take into context beyond just intent?

Yeah, I think, um, having a model like this allows us to add in more sensors into our decision. So the robotics example of, you know, an arm moving up or down, um, any of the external factors, it could be are there other objects near it, right? Um, it could be temperature. It could be, well, am I moving and I'm-- don't wanna move my arm while my, you know, the, the rest of the robot's moving, et cetera. So it's usually looking at all different types of things. None of those are deterministic. They're all probabilistic. So there's a range of options, and it picks the best option based on all of

those sensor data at one time. Most authorization decisions in organizations today are still single binary decision, right? And that just doesn't work in the future, right? So being able to pair the intent of what a user's trying to do with the ecosystem that the user's doing it in. That could be where they're doing it from, time of day. But it could be even more advanced things, like for example, should I let, you know, this administrator use Firefox to access this server right now when this server has, you know, high-risk vulnerabilities and their system hasn't been

patched to, right? Now all of a sudden you're bringing in a lot more context into the environment around it. And again, um, that can be through different teams, but more importantly through sensors. And I think we've all kind of seen the value of observability in general. Imagine being able to have this type of context at the span level from an OTEL perspective or something, right? You're looking at a trace, you've got a span, and you actually know what the environment was outside your application at that time, as well as what the user's intention was. Um, that allows you to diagnose things in a completely different way.

Um, and so I think if we can bring in some of those concepts, we'll get

Shorter time, shorter, shorter to live, you know, um, authorization decisions that have much more context than even just a user's intent. It'll be the state of the environment around it.

That makes sense. And forward-looking as we evaluate whether intent-based authorization is working in our environments, one natural place to look will be a log of the agent's actions. Um, what was denied, what was allowed. Um, Ian, why is it important to have your audit log separate from the agent itself, meaning outside of its control?

Yeah, I think this comes back to also just, like, why the enforcement point has to be outside the, like, primary, like, hands and brains of, of an agent, right? You can't trust this thing. And so in the Hugging Face incident, it had a couple of different components of it. I mean, one obviously abused a, a vulnerability we didn't know about in Squid, in Squid proxy. But more importantly, didn't have any observability or monitoring about what was going on. And so this thing was able to go on the open internet through this vulnerability, and there was no, like, place at which recorded the different actions that this agent was taking and for them to monitor. And so independent of, like, whether we're s- applying, like, a, you know, enforcement point to network

traffic that's f- pushing on the internet that is out of reach of the agent to tamper with, or we're using, you know, solving vulnerabilities as they pop up, you know, this, this Hugging Face one is a little unique. Um, we still need to actually have a record of, like, who told this agent to do what thing for what purpose, and is that still true? Um, 'cause ultimately at the end of the day, what we're dealing with agents is we, is, is a liability question. And so this is why I actually don't think we need more regulation around agents. What we just need is our preexisting laws around liability be held, th- to be dealt with, which is if I employ an agent to do some action, who is

liable if that action causes damage, right? It is the person who employs it, which could be an organization or a person or someone that delegated some action to something. That is like, that's the fundamental question we have to deal with, and then al- of course you have to have a, ability to answer that question, which is, "Well, who did it?" And which is where the tamper-resistant audit log comes from.

Perfect. And then to wrap up, I wanted to ask you all a fun question. So there's the concept of the probability of doom or P(doom), where the, uh, AI doomers are saying that AI agents are going to, um, release all sorts of havoc or be, like, the ruin to humanity. Whereas the AI optimists are like, "No, this is really, you know, poised to help us. It's not a genuine threat." Um, for each of you on the p- panel, what is your take on this? Is, you know, runtime authorization based on intent and the other things we talk about like constraining agents, validating inputs,

outputs, a holistic strategy for production agents, is that enough to save us? Is P(doom) real or is it not worth the hype?

You get to start, Dave.

Oh, I get to start this?

Oh, you've got that spicy look on your face.

Uh, uh, well, part of your question is are agents gonna take over? And, uh, I, I think agents being fully autonomous and not really tied to a particular organization is still science fiction. You know, so who knows, right? Like, that's a, that's one direction. Another one is in a responsible organization that's put in the right controls, agents aren't ... You know, we're, we're getting and evolving enough of the tools to make sure that bad things don't happen in a responsible organization, so put in the right controls. And so that leaves two scenarios for where

there's gonna be a potential problem. One of those is in an organization that isn't got its act together, an insider threat could go and unleash an agent to cause havoc, right? And so they've got some special access that other people have. The other one, the one that I'm more concerned about is, you know, it's been shown, you know, the Hugging Face incident, if you watch the, the talk that they gave at Black Hat, right? That was really a call to arms around, you know, here's a situation where we didn't want a

bad thing to happen and a bad thing did happen. What about people that want bad things to happen and have these tools? And that I think is the threat that's the one that's potentially gonna have ... I mean, it's going to happen, and there's gonna be some catastrophes. Hopefully we're prepared enough that those aren't horribly disastrous. But it's gonna be, you know, some, there's gonna be some things that are like massive natural disaster-like scale issues caused by malicious actors,

either kind of intentionally or kind of unintentionally. But it's where people aren't being responsible in their use of these super powerful tools. Yeah. I can't give necessarily a specific probability, right? But what I, I c- I can say is I think I've always been, you know, kind of, uh, surprised and excited when, you know, ingenuity of engineers gets involved in problem-solving. And I think where we're at the stage now, like some of the new capabilities within agents, et cetera, we have real engineers, folks that are here

actually just iterating on the problem, right? And we're starting to see just tremendous improvement in the, you know, in my mind, some of the capabilities that'll be available to change what our future can be. And so to me, I, I have no problem kind of believing the engineers are gonna figure out a solution here.

I mean, maybe I have the hottest take. I mean, like, I can't say it's equal to zero, but I would say it's approaching or asymptotically zero- ... uh, is the probability the world is gonna end. Uh, I think, like, the incentive structure for most people is to continue. Um, and also at the end of the day, like we still have liability frameworks and, you know, I think generally humans are good people, so we don't set out to destroy the world specifically. Um, I also think like broadly speaking, like these agents at the end of the ... I have this sort of hot take I say, which is like they can just be unplugged, but I think it's just true. It's like at the end of the day, like they, they can just un- they're computers, we can unplug them.

Um, and at, so broadly speaking, I, I don't believe in the debate. I, I don't think it's real. I think at the, at the upside of it, I, I kind of believe more, more to what David's position is, is we're iterating very quickly. We're figuring out where these things can work, where they don't, and when they don't work, they create damage and that's what ultimate like sort of, um, the antibody of society is that says, "Hey, maybe we shouldn't do this."

Ah.

Like, this is probably a bad idea.

So I'm, I'm the doomer on the, on the panel.

Yeah. It's unfortunate for, you know, people like the Po- you know, the, the founder of Pocket OS who like h- lost a bunch of data, like, but it's great for the rest of us 'cause we all learn together and, uh, at the end of the day, like that results in people not doing things that don't make a lot of sense, and I think that will continue to be true.

Makes sense. Thank you each for your expertise and your time here on this panel today. And thank you to the audience for listening and we'll catch you next time. Thank you.

Thanks so much.