Rebuilding the web for agents — Liad Yosef, MCP Apps
Read the talk
Rebuilding the web for agents: interfaces, journeys, and discovery
Liad Yosef explains how MCP Apps can bring useful interfaces into assistants—and why making a website usable by agents requires more than publishing another specification file.
From a talk by Liad Yosef
At a glance
Ideas worth remembering
MCP Apps lets a service return interactive UI into a conversation, preserving a human decision step within an otherwise automated task.
Agent readiness extends beyond discovery: an assistant must understand the service, interact with it, authenticate, and complete payment.
Publishing
llms.txtdoes not ensure agents will find it. ORA’s reported journeys make documentation links important, though the talk’s usage percentages are unclear.Test the same intent across multiple agent harnesses. Different paths can reveal missing guidance that a single successful run would conceal.
Resource catalogs and queryable directories address how agents find integrations; they do not by themselves establish successful use of those integrations.
Yosef’s closing goal is to make the existing web accessible to agents, with human accessibility offering useful overlap in how sites communicate meaning.
MCP Apps brings the human decision back into chat
Liad Yosef starts with a practical problem: agents can do more work autonomously, but people still need interfaces for some decisions. Choosing a hotel, inspecting a 3D model, or selecting a seat at a venue requires something richer than a text result. As MCP Apps co-creator and maintainer, and ORA co-founder, Yosef describes MCP Apps as the layer that lets an MCP server return an interactive interface inside a conversation.
The mechanism is to let service providers send pieces of their UI into the assistant’s host application. A hotel service can supply a recognizable booking interface rather than have its product flattened into text or database records. Yosef argues that this preserves the provider’s identity and gives the user a familiar indication of whom they are interacting with. The chat host gains access to services whose underlying work—negotiating hotel deals or helping customers change venue seats—it would otherwise have to reproduce.
This is his last mile of interaction: the agent performs the work leading up to a choice, then supplies the interface through which a person makes that choice. Yosef describes Booking and AllTrails appearing within the same conversation. Their capabilities remain distinct, while the conversation supplies a shared context. MCP Apps therefore addresses a particular gap in automation: how to return control to a human without sending them through an entirely separate application.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
One intent, composed from several services
Yosef’s developing example is planning an anniversary. The conventional workflow means opening several browser tabs and learning how each service expects the same intent to be expressed. Google, Amazon, and Booking each have their own interface and user flow. Two decades of improving those flows have made individual products easier to use, but the person still coordinates the task across them.
His proposed alternative breaks those interfaces into small, useful pieces that a personal assistant can compose. A calendar view establishes that an anniversary is approaching; shopping and hotel services supply the actions needed to plan it. If the assistant knows the user prefers hotels in nature, it can bring back Booking’s map. The claim that he does not need 99% of a dashboard is a way of expressing this mismatch: a complete application contains far more navigation and functionality than one task needs.
The assistant also becomes the place where context connects services. In this example, Booking would not need to build a calendar integration, and Amazon would not need to build an integration with Booking. The assistant carries the user’s context and coordinates the pieces. This is the experience Yosef wants to build toward; the anniversary scenario is a proposed composition, rather than evidence that every part already works together.
That preference also explains his objection to every company adding its own agent-shaped text box. Visiting Amazon’s assistant, then Etsy’s, then Expedia’s still makes the user move between services and repeat their intent. Yosef expects users to prefer their own assistant, which already knows their circumstances. His prediction concerns where a task begins and where its context lives.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Why browser automation leaves the dashboard in the way
Browser and computer-use agents offer an obvious way to automate today’s web. Yosef questions the premise: filters, pagination, sorting controls, and dashboards were designed around human perception and interaction. Making an agent work through them preserves a workflow whose constraints may no longer be useful. His faster-horse analogy targets this choice of workflow, rather than the agent’s ability to operate it.
He describes WebMCP as another approach: a website exposes JavaScript tools that an agent can use, reducing its need to interpret screenshots. This improves how an agent acts within a website. Yosef still questions whether the user should have to visit that website at all. Finding deals while browsing is a helpful co-browsing example; opening a Salesforce dashboard so an assistant can click its buttons preserves the dashboard as the destination.
His evidence for a different entry point is anecdotal but concrete. Friends who connect Jira’s MCP to their IDEs stop visiting Jira’s website. He imagines his mother booking a doctor’s appointment through ChatGPT rather than navigating a clinic’s site. These examples explain the incentive to move tasks into an existing assistant; they do not establish that websites and browsers will disappear. Yosef briefly makes that stronger prediction, then acknowledges that they will not become completely obsolete.
He also points to Sentry’s Designing for Agents discussion as a sign that product teams are reconsidering exclusive reliance on a web application. The design consequence is to make product capabilities available through APIs, so interaction can begin elsewhere. The website can remain useful while losing its role as the mandatory route to the service.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
The nearly headless web changes who experiences the product
The amount of UI needed depends on the task. An agent organizing email might simply report that it has finished. Booking a honeymoon hotel is more likely to require a person to inspect options and choose. Yosef calls the resulting architecture the nearly headless web: agents use services without navigating their full websites, then return selected UI resources when human interaction matters.
This splits product experience into two related concerns. The agent must understand and operate the service; the person must understand and use what the agent brings back. Yosef predicts that 90% will depend on agent experience, but presents no measurement supporting that proportion. The useful design requirement is broader than any one percentage: a service needs to work for its own agent, its customers’ assistants, and people who still visit directly.
Being discoverable is only the first step. After finding a business, an agent still needs to understand what it offers, how to interact with it, how to authenticate, and how to pay without a human navigating checkout. A product can succeed at appearing in an answer and still fail when the assistant tries to complete the task.
Yosef’s analytics decision makes that competitive pressure tangible. His team asked Claude Code to recommend an analytics service. It suggested PostHog; the team preferred Mixpanel because they had used it for a decade. Claude Code continued to recommend PostHog on the grounds that its MCP and API would be easier to integrate, and the team switched. This is an account of one purchasing decision, not a comparative benchmark of the two services. It nevertheless shows how an assistant’s integration preference can outweigh a human team’s accumulated familiarity.
Yosef extends the example into a warning about repeated friction: an agent that has to launch a browser to use a service may remember that cost and choose another service later. The talk does not demonstrate that behavior across agents. It identifies a plausible product risk, especially when an assistant is making the recommendation and carrying out the integration.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Published guidance only helps if agents find it
At ORA, Yosef’s team began with readiness benchmarks: scan a website, evaluate protocols and best practices, return a score and agent feedback, and compare products on a leaderboard. A surprising observation challenged the usefulness of checking for a file alone. Almost fifty percent of the websites they tested published llms.txt, yet agents generally went to the documentation page and then the homepage.
Yosef’s numerical account of usage is internally unclear: he first says none of the agents used llms.txt, then refers to forty percent that did, without establishing the denominator. The narrower observation is that agents reaching the file did so because the documentation pointed them to it. Publishing guidance and making it discoverable along the agent’s actual path are separate pieces of work.
He also argues that tool-writing conventions change as models improve. His example contrasts a three-paragraph MCP description with three lines, suggesting that less explanation may become sufficient. The talk supplies no comparison establishing when either length works best. His practical response is to observe what agents need on real tasks, rather than assume that a fixed description format will remain effective.
ORA’s Journey turns that response into an experiment: choose a website, an intent, and an agent, then watch the path the agent takes while trying to accomplish the task. Yosef says the team ran these journeys tens of thousands of times. The path exposes what the agent looks for and where it goes, making it possible to investigate why a published resource such as auth.md is overlooked.
Comparing multiple harnesses is central to this method. The harness is the environment through which the agent pursues the task; different environments can produce different journeys even on the same website with the same intent. Yosef compares Claude Code, ChatGPT, and another harness, and says ChatGPT finds results better in the illustrated case. That example does not establish a general ranking. It shows why one successful journey cannot stand in for readiness across assistants.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Discovery has to find usable resources
After studying how agents use a service, Yosef turns to how they find it. Search accompanied the web, app stores accompanied mobile, and feeds accompanied social platforms. For agents, the object of discovery may be an MCP server or an openapi.json description rather than a page. His hypothetical comparison between Airbnb and Booking.com makes the distinction useful: one could offer the better MCP integration while the other offers the better API. Choosing a service requires knowing which resource fits the task.
He sees different limitations in existing discovery approaches. Conventional web search ranks material shaped for human search. Registries tied to a particular assistant are closed and require providers to submit their applications. A central MCP registry raises questions about curation, governance, and which resources qualify for inclusion. These are separate problems: finding a page, joining a platform’s catalog, and governing a shared directory do not automatically produce the same result.
Yosef describes two emerging conventions that address different parts of discovery. aicatalog.json describes how a website exposes its agent-facing resources. Agentic Resource Discovery, or ARD, describes how a directory exposes itself to agents. One helps an agent learn what a provider offers; the other helps it query a collection of providers. The talk presents these as emerging standards, without establishing their adoption or resolving the governance questions he has just raised.
ORA.directory applies that model to domains the team has scanned. Yosef describes generating a catalog for monday.com that identifies its MCP and API servers. Directory entries identify available resources and how to access them, with Vercel as another example. The directory is presented as ARD-compliant. Its purpose is to give agents queryable descriptions of usable connections; the catalog itself does not demonstrate that authentication, payment, or task completion will succeed.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Make the existing web accessible to agents
Yosef ends by connecting agent readiness with human accessibility. His analogy is to users with vision disabilities: agents relying on nonvisual information need signals that explain how a website works, rather than depending on its visual presentation. Human accessibility work can therefore help agents as well. The analogy concerns how meaning becomes available without sight; it does not mean that every agent lacks visual capabilities or that agent success proves a website meets human accessibility needs.
That changes the emphasis of his closing proposal. MCP Apps supplies a way to bring human-facing interaction back into an agent-led task. Journey investigates how agents actually move through services. Directory supplies a route to their resources. Together, these support his stated goal of making the existing web accessible to agents: expose capabilities they can use, help them find those capabilities, and retain useful interfaces for the moments when people need to choose.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Read the complete timestamped transcript
- 0:12
Hi, everyone. Uh, hello, hello. So we're gonna talk a little bit about the agentic web, and more spe-specifically, what it means and how do we make the web ready for agents. Um, one disclaimer, um, I built this talk yesterday, so it might be outdated because, uh, things are moving really, really fast in this, uh, in this space. And, um, I think I need to introduce myself just to, um, to get some context. So I'm the co-creator and maintainer of a spec called MCP Apps. MCP Apps, that's the underlying
- 0:42
spec be-behind, uh, ChatGPT apps, Claude apps, Copilot, GitHub. Every chat-based app that you saw... that you see is based on the spec MCP Apps in the MCP committee. I'm also the co-founder of a company called ORA, where we research the agentic human interactions, and I built and led the agentic storefronts in Shopify. So the topic of agentic web is really close to my heart. Um, and a lit- a little bit of primer about MCP Apps, if you're not
- 1:12
familiar. Um, MCP Apps are actually... This is actually the spec that paved the way to agentic web. So MCP Apps were, were released as a spec and as, as a standard few months ago, um, with the support of, uh, Claude first as the first client, and then all clients followed. And if you play with any chat-based app and you pulled any, uh, visualization and interaction UI layer from an MCP server, you probably used MCP Apps. And the good thing about MCP Apps is
- 1:42
that everybody wins because if the servers or the providers can send UI chunks into the chats, then the apps gain their brand and identity. They get, they get to keep their UI and not being reduced to a database or just text-based, uh, information. The users gain the trust and familiarity because if you, uh, ask ChatGPT, "Hey, book some hotels for me," and you see Booking.com, then you know it's Booking.com, right? You know who you're
- 2:11
interacting with. And the host of the, the chats gain, uh, access to the world of capabilities. Um, you know, a few months ago, people ask, "Yeah, why won't, uh, OpenAI just build everything out of scratch?" But OpenAI will not negotiate, uh, deals with hotels or support, uh, users that want to change seat in a venue. Um, we need those services, and MCP Apps actually solve for this, uh, for this last mile of interaction.
- 2:41
Yeah. So, um, uh, this is the, this is the benefit, uh, that we get, and MCP Apps solved our last mile of interaction, right? So what does it mean, the last mile? Last mile is, as agents become better, as models become better, they can do things more autonomously. But we are still in the end of the chain as humans. We still need to be able to choose the hotel or to view a, a 3D model or to choose a seat at, at the venue, all those
- 3:11
last mile of interaction, and that can change. And, um, this is an example from, uh, um... Oh, sorry. Yeah. So this is from, like, uh, Claude, um, API on MCP Apps. This is how it looks like, right? So when you, um, when you're embedding apps inside chats, you get this unified experience of how UI feels inside the same context of a chat. And as you can see, in the same conversation, you get data from Booking, you get data from AllTrails, you can get data from
- 3:41
everything you, um, uh, you want to interact with, right? So this is, this is already happening. MCP Apps is already s- wi-widely supported across every, uh, chat agent, except Gemini, but that's coming. Um, and this is already hap-happening. And the interesting part is that it brings us to what we call the agentic web. So what, what is the agentic web? The agentic web is not a web of agents. Uh, it's not the web as we know it today. It's a, it's a shift.
- 4:11
It's a change. It's a, a changing in the way that we see websites and the way that we see browsers. Because up until now, we spent 20 years, two decades, perfecting this experience, meaning that if I want to somehow, um, do a project or fulfill a task or plan an anniversary, I have to open tabs in my browser, and I have to go through these tabs, and I have to convey my intent differently to each of those services, right?
- 4:41
Meaning that if I just want to plan an anniversary, then I need to learn Google's UI and Amazon's UI and Booking UI and the other Booking UI and the other Amazon UI, all that just to convey the same intent to those interfaces. And every company perfected this user flow. But we don't need to do it anymore, right? We can just take these interfaces and break them into atoms because we don't need... I don't need 99% of Booking's dashboard. I
- 5:11
don't need 99% of Air- Airbnb's dashboard. I definitely don't need Jira's dashboard. But I do want to convey my intent to those services, so why can't I let my personal assistant use that? So if I have a personal assistant, I can just take these atoms, and it composes these atoms and say, "Yeah, I see that you have an anniversary coming. This is, this is the view from Google that says that you have an anniversary coming, so I can book... I can, I can buy things for you. I can book your hotel." Now, Claude
- 5:41
knows me, so it, he knows that I prefer to book hotels in, uh, uh, in the nature, right? So it knows to pull the map from Booking. I don't need to think about it. And what Booking and Amazon and Google benefits from this is that they have this integration layer that they don't, they don't need to develop 'cause Claude has the context, um, for me, right? So Booking doesn't need to develop integration with my calendar. Amazon doesn't need to develop integration with Booking. So it's a win-win-win. This is the view that we're, uh, aiming for, and this is
- 6:11
very different from what the things are going, which is this, which is basically browsing into different services just to stare at different text boxes that ask what I want to do there. But no one is going to do that. In fu- in, in a year, no one is going to, um, browse through Amazon's agents and, and Etsy's agents and Expedia's a- agent. I don't wanna do that. I have my own personal assistant. I don't want, I don't want to use your agent. I wanna use my agent. Okay?
- 6:42
Now, if we think about it, it means that websites as the source of truth are something that's gonna go away, because why would I need the website? Why would I need to open the tab? Why would I need the information that the website is working really hard to convey to me? And the immediate response to that is that, yeah, we have browser agents. We have computer use agents. We have very smart agents or assistant that can browse the web for us, but that doesn't make sense because that, that's, that's a faster,
- 7:12
horse solution. Why would I let an agent that doesn't know anything about the human perception limitations work with, uh, filters and paginations and sorting and all of those UIs that we spent decades perfecting for us, um, just for it to fulfill its task? So Google has, uh, um... Google is very bullish on the other end of the spectrum, which is co-browsing and, and websites, and they have a protocol called, or standard called WebMCP. WebMCP says, okay, instead of the agent
- 7:42
taking screenshots of the websites and trying to figure out what's happening, let's have the website expose some tools in the website, JavaScript tools, and the agent will work with it. And you can see here an example of Gemini and Chrome that, um, buys stuff for me or, uh, finds, uh, deals for me as I browse the web, which is very nice, but it's very simple. What happens if we push Salesforce dashboard to Gemini on Chrome? Why would I want that? Why would I want to browse to Salesforce dashboard with Gemini
- 8:12
to click buttons for me in a dashboard that I don't even want to use? I mean, this is definitely not what we want. And the shift is that assistants are becoming our entry point to the web, right? We see it everywhere. Every major lab wants its app to be the everything app, and the shift is happening. And friends of mine that connect Jira's MCP to their IDEs, they don't go to Jira's website anymore, right? And my mother uses
- 8:42
ChatGPT for everything. If she could book a doctor's appointment using ChatGPT, she won't go to that clinic's websites anymore, and you have a long tail of websites that no one is going to see because it's much easier for me to connect to them using my personal assistant. So websites will become obsolete, browsers will become obsolete, and personal assistant will become our only gate to the web. And I know what it sounds like. It sounds like old men yelling at a lit- literal cloud, right? I mean, um, yeah, they're not gonna go completely obsolete, but we see
- 9:12
it with the younger generation today. My [REDACTED] goes to ChatGPT. He doesn't go to Google when he, when he wants to search for stuff. I was, uh, I was traveling to Georgia, the country in Eastern Europe, and there was an older lady there that asked me to take a picture of her, like [REDACTED], and on her phone she had three apps: WhatsApp, Camera, and ChatGPT. That's it. The shift is happening. Um, and very smart people like David Cramer from Sentry said a year ago, "I will take this bet
- 9:43
against anyone who thinks websites are going to be obsolete in 25 years." That was one year ago. Few days ago, David Cramer p- published Designing for Agents, which says, "We have to recognize that interaction with products at Sentry will no longer be exclusively through our web application, and we have to design for API first as a surface." So everything is going headless. Salesforce recently went headless, which is very important because Salesforce's main differentiator from its competitors is its UX. It's the way that it conveys
- 10:13
everything to the user. But it went headless. Cloudflare went headless. Sentry went headless. Um, this is a, a tweet by a Cloudflare CEO, uh, saying that agents traffic surpassed, uh, human traffic in the web. And we have this spectrum of interaction because if, if my agent is autonomous, I don't need this last mile of UI, right? If I have an OpenClau, I just send... and I just say, "Yeah, organize my emails." It comes back, said, "Done." Good. But if I want to book a hotel for my honeymoon, I probably need this last mile of interaction, so we call it the nearly
- 10:43
headless web, right? Uh, it's not completely headless. Um, the agents will interact with your web head- with your, um, website headlessly, but then it will bring back these UI resources for you. So user experience as we know it is being split. Now it's the agent experience of your website, plus how a user experiences the agent that experiences your website. But 90% is gonna rely on agent experiences, m- which means your website needs to be agent ready
- 11:13
for everything. It needs to be agent ready for your agent. If I'm booking, I need to make bookings that are ready for bookings agent. I need to make it ready for my customer's ChatGPT or my customer's OpenClau, and I need, I need to be ready for my human customer who doesn't have an agent but still wants to browse to booking.com, right? So I need to, to be agent ready, and what we fi- found out is that agent ready means a lot of things. So we heard a lot about AEO, SEO, GEO, how to get discovered. But discovered, discovery is
- 11:43
only the first, the first step, because once an agent knows about you, it still needs to know what you are and how to interact with you, and how to, uh, authenticate to you, and how to headlessly pay you, right? And actually, when, when we built, uh... It's an anecdote, but when we built, uh, analytics for our product, we asked Claude Code, "What's the best analytics service?" And it recommended PostHog, which is an analytics service. And we said, "No, we prefer Mixpanel," because we know Mixpanel. We worked with Mixpanel for a decade. We know how to work with it. And Claude Code insisted on PostHog because it said, "PostHog has better
- 12:13
MCP and API, and I can integrate to it better." So we don't have brand loyalty, right? We went with PostHog if that's Cl- what Claude Code recommend, but it made us think about Mixpanel, and Mixpanel spent a decade perfecting their UX and developer experience. We just left it just because Claude Code prefers PostHog, and it will always happen. Hermes, for example, if it uses your product, and it needs to spin up a browser to use your product, it will remember that, and next time it won't go to your product anymore, right? So at ORA, which is an agentic web research lab,
- 12:44
we started researching. Uh, we raised some ca- raised some capital, and we started researching what does it mean for the web to be ready for agents. And we have these, um, readiness benchmarks, which is interesting. So you can run... It's free. You can go to ora.ai. You can run any website. You get this score and benchmark according to a lot of protocols and best practices, and you have agentic feedback, so the agent actually returns the feedback about your, uh, your website. And we have
- 13:14
this leaderboard of how companies and products rank according to this benchmark, and we started mapping the web, and everything was nice. But we hit one insight or one, uh, unexpected result. We found out, uh, anyone here heard about llms.txt? llms.txt, that's like the de facto standard to be agent ready. You say, "Yeah, if your, if your website publish an llms.txt, agent know how to interact
- 13:44
with you." Um, and you have auth.md and pricing.md and X-402 and a lot of standards. And we found out that almost fifty percent of the website that we tested, that we ran, published llms.txt. But none of the agents that we ran on this website actually used llms.txt. Actually, almost all the agents went straight to the docs page, and then the homepage, and the forty percent that did use llms.txt used it only because the docs pointed out that there's a file called
- 14:13
llms.txt that they need to, to use. So then it hit us. We said, "It doesn't make a lot of sense for us as humans to define to agents what they need." No one is doing it anymore. Even OpenAI, they don't publish best practices for tools anymore because they say that every time they publish best practices, the models become better, and these practices become obsolete. Six months ago, the best practice for an MCP server was, yeah, uh, have three-paragraph description so agents will know how to interact with you, and now three lines are
- 14:43
enough. So best practices become obsolete. We need the agents to define what the agents need, right? We need agents' feedback on this website, so we built ORA's Journey. And ORA's Journey, that's a really cool... That's also free. You can go to journey.ora.ai, and you can run on any website, any intent, with any agent, and see the path of the agent as it tries to interact with the website. So for example, etia.com. Choose Claude, Claude Code,
- 15:14
and we run it on the website, and you can see in real time how the agent goes and what it tries to look for in the website. And we, we did it tens of thousands of times just to understand what agents really look for when they look... whe-when, when they try to interact with, with websites. And the cool thing is not running just one harness. It's running multiple harnesses. You see here Claude Code and Eve, which is, uh, Vercel's harness, um, and ChatGPT on the same
- 15:44
website with the same intent. Okay, so this is Claude Code. This is Haiku. This is Eve. See how different the agent journey looks like, and this is ChatGPT. So ChatGPT could, could find results better. See, you can just see the, the, the journey across, across the website, and we need to understand why. We need to understand why does it happen, why websites publish auth.md files, but agent don't look for auth.md files, and what do they look for? So in ORA,
- 16:14
um, you can actually, uh, go to any business, business question. So for any domain you have, like, business goals or, or questions, and you can see the paths that the agents are taking. And the, uh, interesting part of it is that, okay, now we know how agents interact with website. What's the next big, big milestone for ag- the agentic web? And for those of you who, uh, heard the, the previous talk, um, it's discovery, right? But it's not the discovery that we think of.
- 16:44
It's not a SEO. It's not GEO. It's not AEO. Because we have to remember that every rev- revolution came with its discovery layer, right? The web revolution came with search. Um, mobile came with app stores. Social came with feeds. What is the discovery layer for agentic resources? What is the discovery layer for MCPs? What is the discovery layer for openapi.json? What do we even look for? I mean, maybe Airbnb has a better MCP than, than Booking.com, but Booking.com has better API than Airbnb. So how do we do it?
- 17:15
Um, web search, classic web search, it's not enough because, um, it ba- it's based on human SEO and human, uh, PageRank, and it's not flexible enough. Custom registries, like per agent or per chats, they're not enough because they're closed, and they're, uh, um... and, and they require every app to sub- to submit itself to these regi- registries. And a central registry, like an MCP registry, that's not enough because who will do the curation? What's the governance model? How do we decide
- 17:45
which resource comes to that registry? There are eme- emerging standards around it. There's an aicatalog.json, which is a standard by Anthropic, OpenAI, Google, MCP, and A2A, which standardizes how a website exposes itself to agents. And there's the Agentic Resource Discovery standard, which is by all these companies and more, which is basically standardize how, uh, a discovery layer or, or a directory, uh, expose itself to agents. So we built ORA.directory, right?
- 18:15
Because we're a research lab for the agentic web, so we built this. And in ORA.directory, we take all the domains that we scanned or scanned ourselves, and we put it in a directory that agents can actually query, right? Um, we expose the aicatalog.json files, so you can see here, for example, for monday.com. You can see that we generate this JSON file that basically tells agents, "Yeah, this is the MCP server for Monday, this is the API server for monday.com," and you can just... The agent can just query that,
- 18:46
right? So for every domain, it can just goes to, go to aicatalog.json, and we expose the registry, the directory itself. So for every entry on the directory, we can, uh, we can tell the agent, "Yeah," for example, Vercel, "These are the agentic resources, um, and this is, and this is how you access them." And obviously, this directory is fully ARD or Agentic Resource Discovery compliant, so any agent can just query that directory with any, with any query, right? So this is, uh,
- 19:16
this is ORA.directory, uh, if you wanna take a look. All of it is part of the ORA multiverse: Journey, Directory, and the Ranker. And we found out some very other interesting insights. For example, being agent ready and being human accessible is very similar because LLMs, when they come to a website, they're like, um, users or people with vision disabilities. They don't see your website. They need other signals to understand how to work with your website, and making your website human accessible helps agent accessibility and vice,
- 19:46
vice versa. So to wrap up, these are MCP Apps. This is what I've been working on in the past few months, and this was the last piece for the agentic web. This actually brought the agentic web. And now agents start to roam the web, and agents need different things. They need different roads. They need different infras. But we don't want to rebuild the web for agents. We, we want to make the web agent accessible. So let's just make sure the web is prepared for when agents are coming.
- 20:19
Thank you very much.