An AI Future Without the Lock-In — Remy Guercio, Tailscale

Well, hi, folks. Uh, thanks for joining me here for the last talk on this stage, uh, of the, uh, AI Engineer World's Fair this year. So, um, yeah, thank you for joining me. My name's Remy. I am on the strategic projects team at Tailscale. Uh, and more specifically, I actually work on our AI gateway, Aperture. And today I wanna talk a little bit about, you know, what it means or, you know, what it's gonna take, uh, to have a AI future without the lock-in. I

think a lot of the lock-in that we've seen, uh, over the last twelve months. And yeah, so if we take a look real quick at the, you know, the last twelve months, you know, I think it can really be, you know, described quite a bit by, uh, the phrase token maxing. And I, I don't mean that in the kind of, you know, negative sense that you might kind of hear outside of the, you know, kinda AI enthusiast circle. I mean that in the sort of, you know, it's been a year of trying to figure out, you know, what we can do with million token context windows,

uh, with the ability to get context from anywhere, right? Not just, you know, MCP being everywhere, but, you know, also having coding tools, right, that are great at finding context, using the CLI, bringing that context into the model, uh, bringing it, you know, bringing it into, you know, everything that you need and, and, and going from there, right? It's, it's been pretty cool, right? I mean, we've gotten-- It's really made truly agentic coding possible, having all of this, right? So yeah, it's, I mean, it's, it's quite cool and, you know, we're gonna see, uh, not just agentic

coding but, you know, other agentic use cases where it continue to take off, uh, as we, as we do this. So, um, you know, token maxing is cool, but right, it has, it has problems, right? Ob-- There's obvious problems, right? It's very expensive, right? It's, it's, it's an extremely expensive endeavor. Uh, you know, I think the last twelve months are, you know, have maybe been marked by, "Hey, we have, you know, unlimited AI budget." Uh, and that's changed here in the last few months, uh, in

terms of, you know, what it, what it means to, you know, what it means to use AI. Um, it also-- I mean, you know, it's expensive, like, just generally if you're doing it, you know right. But it also, it does incentivize what I would call, like, wasted tokens by default. I mean, I, I work on an AI gateway. Uh, we use our AI gateway. I get to see all of the usage from the AI gateway. You would not believe the number of sessions that are hundreds or thousands of messages long where nobody clears the context. They just kinda keep going. I mean, it's helpful sometimes, but, you know, it's,

it's, it's pretty surprising. You will have, you know, tens of millions of tokens of a session, uh, where it's-- the cache is basically max out, maxed out the entire time. Uh, it gets really expensive. Um, and the other thing is, right, so, you know, this has been an exciting time, right? People are doing new things, building new things, uh, but this has led to, you know, in many cases, very vertically integrated tool chains. Uh, Claude Code is obviously, you know, a big one. Codex, right? Everybody's kinda building up their, you know, for all the way from the model, you know, all the way, all the way out of the top, uh,

you know, building their, uh, you know, building their agents, building their tool chains. So, um, right, there's a lot of problems there. And so, you know, my question, right, in terms of this is, uh, you know, how do we address these problems? In particular, how do we address the lock-in and, you know, how do we actually improve, uh, how we use AI such that, you know, we can use it for things that aren't just, you know, kind of essentially frontier task or where we're just kind of wasting, wasting money, wasting tokens, uh, you know, that sort of thing. Um, but first I wanna talk about how not

to address the problem. Uh, and this is a super, super common thing. So, uh, over the last six months, we've been talking to-- I've literally been talking to hundreds and hundreds of folks about their AI spend, their AI usage, right? That's the kind of benefit of working on an AI gateway. Folks come to you, they're like, "I don't know what's going on. I know we're using a lot of AI. I get, you know, uh, I get an Anthropic bill every day. Uh, I get a Codex bill every day." Um, uh, so you know, I-- it's not just that, you know. I see it all the time. So you

know, what do I do? They usually come with one kind of solution in mind, uh, and that is, "Oh, we're just gonna, like, uh, everybody seems to be using Claude Code right now, so we're just gonna, like, consolidate on a single vendor. Maybe two vendors, right? Maybe two vendors." So that's, uh, they're like, "I need to get a handle on this. How do I get a handle on this? How do I get, you know... Oh, oh, okay, yeah, I will say everybody's gonna use this, right? We're just gonna use this thing." Um, that is not, not a great idea. Uh, you know, I-- might seem obvious sitting here that it's maybe not a great idea, but you know, when you're in that

panic zone of, "We've spent a lot of money, and we don't know how exactly," uh, and we, you know, finance is talking to you, IT is being like, "What are you doing?" Uh, um, you know, like, we said to, you know, use AI, but maybe not use that much AI. Uh, and you know, it, it's a pretty natural response to go, "Okay, I'm gonna consolidate everything down, right? Okay, well, I'm gonna, I'm gonna have a control on it. I'm gonna have, you know, I'm gonna have control on this, uh, control of this." Um, and you know, I think this is kind of peeking at what we're gonna see the next twelve months and what people are actually trying

to do. Uh, at least at the, you know, kind of frontier is, uh, what I would like to call ROI maxing, right? We're not gonna be token maxing. We're gonna be ROI maxing. Uh, and you know, it's, it's really just a necessity, right? It's not, uh, um... And I don't mean that-- When I say ROI maxing, I don't just mean cutting costs, right? I mean actually proving some sort of value, uh, to the thing that you're doing. Uh, and not only that, but also kind of opening things up, right? So if the only thing you have is, like, two frontier models

and their entire stacked ecosystem, that's a certain cost level where you, you-- it just makes things un- certain things untenable, right? You can't actually expand AI usage into the company if that's the only way you can use AI. Um, and so, you know, when we think about ROI maxing, we first need to kinda think about, like, what are the components- Of an internal AI deployment. I'm not talking about, like, a, "Hey, we've built this new AI feature in our app." I mean, you know, internal, internal to your organization. And so, you know, there's four things, right? There's the LLM or LLMs, right, there's that

layer. Uh, there's sort of the data connector layer. I mean, this is MCP for a lot of people, but in reality it's, you know, CLI or APIs, or really just any way that you get data. Uh, could be reading a file, right, into your, uh, into your agentic system. Uh, there's the interface. I think people kind of forget about this sometimes, but you know it's started with the chat interface. We got 2Es. You know, we kinda got a, uh, we got, you know, IDEs with chat. We got, you know, kind of a whiplash back from 2Es into, you know, I'm gonna do it on my ... go to my phone, uh, you know, to

oh, now the, you know, the hot thing is, you know, Claude Tag, and like, I'm gonna use, you know, I'm gonna use... We're just gonna interface with agents via Slack, right? So, uh, um, you know, it's another core component, and it is a component that you can break out. Uh, and then the last one is sandboxes/just the environment in which the agent runs, right? So those are your four kind of, uh, you know, four components really. Uh, and to be ROI maxing, uh, means to be maxing your, you know, every opportunity that you have, uh, for choice, to make a choice at one of those

layers, right? You don't have to necessarily have a unique thing at, you know, oh, I've made my bespoke special choice at every one of those layers, but it's really important to be able to make a choice at any given layer that you need at any given time. Uh, and it might be different for different teams or different folks, right? It's, you know, it, it can be pretty different across the organization. I don't totally imagine, like, an entire engineering team just coding via, you know, Slack thread. It might be fun, but I don't totally imagine that, right? Uh, um, but, you know, the entire marketing team

might be working entirely, uh, you know, in a Slack thread asking data questions, doing other things like that. So it's really important to, you know, to be able to, uh, kind of separate these things. And right, so I, I work at Tailscale, right? I work on an AI gateway. Uh, you know, maybe no surprise that I'm here to talk a little bit about why an AI gateway, uh, will help you do that, can help you do that. And I don't just mean necessarily using our AI gateway. I think it's nice, but, you know, just any AI gateway is the, um, you know, is important for this. Uh, so our AI gate- AI gateway is, uh, called Aperture,

and, um, what it does, uh, is, right, it's maybe no surprise here, right? But it lets you-- It sits in between your agents and that interface of that agent, uh, and, you know, all of your endpoints, uh, as wel- both, like, LLM endpoints as... and data, you know, kind of MCP endpoints, API endpoints, anything that you have, uh, it sits in the middle and lets you both control and monitor what's happening from a-- That can be from a, like, security perspective. That can be from a cost perspective. That can be from a, which we do a lot,

"I wanna learn about what somebody is doing or what an agent is doing" perspective. It's actually really cool when you have logs, uh, and you can tell your agent to, "Hey, uh, I... It... Maybe it ran out." It kind of just kind of, you know, oh, it, it didn't reach an answer. It just kind of spiraled out of control. Uh, maybe happens less now. Definitely used to happen quite a bit. Happens with, you know, maybe cheaper models more often too. Uh, they're usually not great at stopping themselves, uh, but they are great at analyzing where they went wrong after the fact. And so when you have

something like an AI gateway, it's really easy to point it back at what you were doing and say, "What happened?" "Why did this not, why did this not, you know, work the way I was expecting it to?" Uh, and so, you know, if you've used an AI gateway, how many people, like, have an AI gateway, have deployed an AI gateway, use an AI? Yeah. So if you've used one before, you're probably used to, "Okay, so I've put all my keys on this gateway. Now I need to go create synthetic keys for everything that I have," right? So it's like, okay, I've traded some keys for a bunch of other keys. Uh, we get to

do something a little special. So Aperture is built on Tailscale, and if you're not familiar with Tailscale, Tailscale is an identity-based mesh network. It's built on WireGuard. Uh, and what you get to do with Tailscale is, uh, every connection that is made over a tailnet, so it's a Tailscale network. Uh, you know, you install the tailnet agent everywhere that you need. It can be containers, laptops, GPU servers, doesn't matter. Um, you install it everywhere, and every connection that's now made over that tailnet,

uh, comes with the identity of the machine or the user on the other side. So that can be a tag, right? So that can be like, "Hey, this is a machine ID. This is a PR review bot," right? Uh, and then it would get a separate node ID underneath. This is the instantiation of that PR review bot, right? So you can do that, or it can be the user, right? So it's just me using Claude Code on my laptop. Uh, that can come with it as well. Uh, in addition to if you're using something like Entra or Okta, uh, we can actually sync all the groups in, uh, so you can see the group that that person is associated with. So something on the

other side is able to see all of that. We have this really cool library. It's called tsnet. It's an open source library. You can use it to build these sorts of apps. That is what we use to build Aperture. That is what is actually happening here. So it is able to see the, uh, it is able to see the identity of that user or that agent on the other side of the thing or the other side of the connection. And so, you know, again, just reminder, components of a, you know, an internal, you know, AI deployment, uh, right? So there's the LLM side of things. There's the data side of things, the interface side of things, and the

actual sandboxes, uh, sandbox and environment in which things run, uh, side of things. So, um, when it comes to using Aperture, uh, you know, as far as LLMs go, this is pretty similar, I think, to, you know, what you might expect from other, other AI gateways. Except now, you know, here I have a, you know, a configured gateway. Uh, it's got Anthropic, OpenAI, Vercel. You know, it's got even Anthropic OAuth, uh, you know, Bedrock Codecs, everything, uh, that you can imagine. I put all those keys on that gateway, and then now

when I wanna actually connect to that LLM provider as an agent or a user, there's no-- I don't have-- There's-- If I had this expanded, there's, there's no extra screen for create these API keys, create these identities, create this. Once I connect to the-- Once I actually connect to the gateway, it knows who I am. It knows what I am. And it's like, "Oh, you have access to these models, this provider," right? You can use GLM 5.2. Uh, you get this budget with GLM 5.2, right? You get unlimited budget with a cheap model, and you get an extremely narrow budget with

a frontier model, right? Those sorts of things. Uh, there's no extra setting here. It's just add your, add your API key and go. So again, we've taken all the LLM layer, and we've put it into a, you know, put it into one place that you can then, you know, kind of expand out within your organization again. Doesn't matter if you're trying to switch models or providers, you can do that. Uh, the next thing is the data side of things. So, uh, in addition to, you know, being an, an LLM gateway, and this is actually why I said AI gateway at the beginning. So I know that seems kinda nebulous,

uh, but I've actually, I very specifically chose that term because we're both an LLM gateway and an MCP gateway, and we even do auth, like, uh, injection for just standard APIs and re-expose those as MCPs too. So, uh, you know, kind of intentionally choosing the broader term here. Um, but with this, as you can see here, uh, in Aperture as an admin, you can go in and configure whatever MCP servers you want. We have kind of built in ones where we've, you know, checked them out, made sure they're easy to, easy to work with, all those sort of things. If you've ever

deployed an MCP or used MCPs within your organization, you'll know that, uh, there's a standard, but everybody follows a different version of that standard. Uh, you know, you can tell exactly when an MCP server was built by exactly how they decided to do auth. Uh, yeah, it's a, it's a great, uh, you know, kind of archeology lesson, uh, when you go through, when you go through setting up MCP servers. But we try to make that a very simple process here, right? We've kind of gone through this. Uh, so you as an admin can say, "Hey, I've configured these. These are the ones that are allowed." You can use that

same identity information to say, "Hey, the marketing team, you know, they get access to Google Calendar and Gmail, but the engineering team will also get access to GitHub," right? Uh, you can even say things like, "Oh, the engineering-- you know, this side of the engineering team gets access, write access to GitHub or read-only access to GitHub." You can do all, all sorts of things here. And what's really nice, and again talking about decoupling, is all of the authentication happens here. So if you have folks that wanna use Cursor or they wanna use Claude

Code or they wanna use Codex or they wanna use some special agent framework that they're-- You know, some new hot thing that they've, you know, they've discovered or built or whatever, uh, all they have to do is hit that endpoint, and if they're on the tailnet, everything's authenticated as them or as whatever the agent or as whatever, you know, the tag device is. Uh, there's no like, "Oh, I have to go reauth into everything and then reauth into everything and then reauth into this new tool." Uh, we make the switching cost, right, of like actually trying out tools and trying different workflows and different experiences a lot, a lot easier with

this sort of thing. It's all those little points of friction, uh, that lead to use cases where like, you know, people just don't try new use cases. They don't try to, uh, you know, "Oh, maybe I should experiment. Maybe I can make this cheaper. Maybe I can make this faster." Um, you know, next thing, talking about the interface. So, uh, with Aperture, we actually have a built-in chat UI. Surprise. Uh, you know, everybody seems to have a chat UI. We have a built-in ch- built-in chat UI. Um, however, it is built on top of APIs that you can also leverage yourself. Uh, so our whole goal

with Aperture is to actually provide you with the same sort of, you know, tools and interfaces and-- or tools to build interfaces that we can. So whether or not you wanna build a Slack bot or you wanna build a chat UI or you wanna build, you know, some new thing that nobody's thought of, some mobile app kinda thing, you know, voice only interface, right? Uh, you can, you can do that. The whole point is you're gonna be able to do that with Aperture. We wanna support all of those din-- different individual, uh, use cases. But again, you can see it has connectors. Those are all, again, set up through Aperture itself. They're not set up in the

chat UI. You're just getting them, uh, by way, by way of Aperture. Uh, and then the last thing-- So this is, uh, you know-- So we talked about interfaces, you know, a little bit. It's, you know, it's-- Again, it's very important, uh, that you be able to kinda use all of that. Uh, actually one other thing that's coming very soon here is, um, uh, if you've ever s-- I don't know if anybody's ever tried to set up like Open WebUI or, you know, or like Libre-- Like, or any of the-- Like, kind of like any of the like, "Oh, I'm gonna set up like a, hey, this like, you know, this interface or this interface." Uh, one big

thing is you always lose identity information and then suddenly all of the, you know, everything's coming from the UI, right? Everything's kinda like, "Oh, everything's just coming from the system." Uh, we're actually gonna be adding a full like pass-through auth, uh, so you'll be able to actually see all of the like user identities and machine identities if for some reason they're using whatever interface that you have. Uh, you're just gonna be able to set it up so that you can pass through the auth and you still get all of the same visibility that you're kind of expecting from a, from an AI gateway as well. Um, and then, yeah, the last thing is, right, this is actually the-- I think the area

in which, um, folks are doing pretty good. There's actually a lot of choice already. People are trying to do this. Uh, I think that's because, uh, the definition of a sandbox, I'm sure I could poll everybody here and would have a different-- everybody would have a different definition of exactly what a sandbox is, uh, or what they need from a sandbox or what they want from a sandbox. Uh, and so, you know, there's-- we're kind of in that let a thousand flowers bloom phase of, you know, there's a sandbox provider for every sort of whim and need and, you know, and want out there.

Um, but, uh, you know, and folks are doing a pretty good job of integrating them. But again, it's a really important thing. We're actually gonna be adding kind of an orchestration layer as well for sandboxes to a gateway. Uh, again, trying to use that term AI gateway very loosely, intentionally very loosely because in order to, again, kind of make the best choices for all of the different endpoints that your, you know, environments, LLMs, data connectors, all that sort of thing, uh, you really do need, uh, to kinda have a place to sort of see them all, uh, and then a place that brings them all together such that you can then

use any other one. So right, kind of a-- almost a universal translation layer in a way. Um, but yeah. So that's, that's mostly that. And, you know, like I said or as a reminder here, uh, is, you know, ROI maxing really is all about maximizing choice, uh, to prevent lock-in, right? So, you know, even if you don't use Aperture, I do highly recommend you start considering an AI gateway. You look at an AI gateway. It's, it's good just beyond like actual, you know, oh, you know, I don't have to, you know, uh, have three different providers

configured or switch between them this way. You know, uh, it's good beyond that, right? It's great for just, you know, understanding what agents are doing, even if it's just you as an individual. We have so many people who are just as an individual, they have their usage behind an AI gateway just to have an idea as to what their agents are doing because, you know, if you're running, uh, very commonly, uh, is people are running something like OpenClaw with-- on Tailscale and it's on their tailnet and they-- and it's just running in the background and they're like, "Oh my goodness. It, it did something. I'm not sure what it

did. It did something it was not supposed to do." With something like an AI gateway, you can actually go back and you can see and you can look and you can actually diagnose where it went wrong, what happened. Um, so, you know, it's, it's not just lock-in, right? It's actually just experimentation and understanding as a whole, uh, is, you know, is very important to use something, uh, like a, like an AI or LLM gateway. So, um, that's it, uh, for my talk. Just short and sweet. Uh, thank you very much for attending. I know this is the, the last talk in here of the day, so, uh, I hope everybody's had a

really great conference. I know I love the AI Engineer World's Fair, uh, and I hope you do too. So thank you.