AI Engineer Europe 2026
Agents for Everything Else — swyx
Read the talk
Agents for Everything Else
Running an AI conference with agents changes more than website development: it shortens design feedback loops, moves schedule management into code, and reshapes who uses software.
From a talk by Shawn "swyx" Wang
How does a tiny team run an AI conference?
How much of running an AI conference can the organizers hand to AI? At AI Engineer’s first London event, Shawn “swyx” Wang approaches that question through the work of his own team. The opportunity extends beyond writing software: it includes the coordination, setup, and routine knowledge work that determine how much a small organization can accomplish.
His successive AI Engineer keynotes trace the path toward that question. The first, three years earlier, concerned productivity gains from using AI. The next encouraged greater use as costs fell. Swyx describes a roughly 100-fold decline in AI costs every 12–18 months as his working heuristic, rather than a guaranteed rate for every workload.
The third theme was tiny teams: teams whose revenue, measured in millions, exceeds their employee count. The accompanying Tiny Teams Playbook, developed around a World’s Fair track, uses the more specific measure of annual recurring revenue. The attraction is organizational, not just entrepreneurial. A large company can contain tiny teams; the idea does not require finding a lone founder who builds a billion-dollar business.
Swyx reports that AI Engineer, led by Ben Li and himself, has nine full-time people and runs a business exceeding $9 million. He describes that figure as business size, not ARR. The workflow changes since the organization began two years earlier become his practical example of adopting AI wholeheartedly—complete with physical “AGI pills” given to attendees. His joke is that everyone can now prescribe one to a coworker who remains unconvinced.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
The website begins with a setup problem
The original conference stack was stable and largely non-AI: Figma, React, Supabase, Tito, Google Sheets, and Sessionize. Joining Cognition gave swyx access to coding agents at work, and free access helped prompt serious experimentation. He added Devin to the company’s Slack and began showing colleagues how to request changes to the website.
Then the designer brought him a Figma page. The expected implementation cycle was measured in weeks—perhaps one, two, or four. Swyx brought Devin into the conversation, but first faced a prerequisite: connecting it to Figma. He delegated that setup to Claude Cowork. Before the coding agent could do the visible work, another agent helped remove the work blocking it.
An agent’s value includes the prerequisites it removes. Dependency installation and broken Python environments are concrete examples of this “yak shaving”: each intended action exposes another task that must happen first. Counting only autonomous task completion misses both the depth of that prerequisite chain and the benefit of handling work in parallel.
Once the connection was in place, swyx reports that Devin produced a functioning website matching the Figma design pixel for pixel. He does not give an elapsed implementation time. Seeing the result himself changed his confidence in the tool, and the designer was happy with it. Swyx identifies the result as the conference website live at the time of the talk.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
A shorter feedback loop changes what people attempt
The initial success turned into ongoing collaboration. Swyx points to 207 replies in one Slack thread as evidence of growing use. He would start work before going to bed; the designer, based in Indonesia, would wake up and continue with Devin. The designer began sending red-line annotations, communicating changes visually in the same way he might with a human developer. Swyx compares this with Steve Ruiz’s tldraw examples, but says he had neither taught the designer the technique nor supplied an instruction manual. For a mostly nontechnical team, that independent adoption mattered.
The team also began making things it would normally leave undone. Swyx added a website Easter egg that appears when a visitor on an ultrawide display moves the pointer over the highlights. Then he fed Devin a viral tweet whose design aesthetic he liked, simply to see what it would produce. That experiment grew into a thread with 127 replies. He had initially wanted to avoid spending the designer’s time on a throwaway idea, but the designer joined anyway.
The reason was enjoyment. The wait between an idea and a visible result had largely disappeared: the designer no longer had to block on swyx or a contract developer to try something. Animations, polish, and playful experiments became work the team could initiate directly. The productivity gain showed up in human initiative, not just generated code. This is the shift swyx calls agents for everything else.
Figma-to-website and tweet-to-website were useful successes in their own right. Together, they also changed the next question from whether the agent could help to where else the team could use it.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Make conference data something the agent can maintain
A conference is also a large data-management problem. Swyx describes coordinating 130 speakers, a couple dozen sponsors, and attendees with varied needs. Much of that work resembles maintaining a content management system: collect information, reconcile changes, and keep the published schedule current. The team had experimented with Sanity, but swyx found a more useful arrangement by supplying spreadsheets to Devin and moving the source of truth into code.
With the schedule represented in code, a coding agent could maintain it. Swyx says Devin managed the entire schedule, while emphasizing that another coding agent could fill the same role. His example is a speaker-change email from Marta. Instead of translating the email into a manually edited CMS entry, he could forward it—or paste a screenshot—and ask Devin to handle the change. The incoming message supplied the task context; the agent worked against the schedule’s existing source of truth.
Swyx describes a nine-person team managing a conference of roughly 1,000 people. That is his account of operational scale, not an audited attendance count. He then projects handling 6,000 people in San Francisco that summer without increasing the team size. His confidence depends on sufficient onboarding and established workflows: the throughput comes after the agent has been integrated into how the organization works.
The same approach extends to ETL, the extraction, transformation, and loading of data between systems. An external vendor holds information missing from the central source of truth. The task is to obtain the vendor’s API key, synchronize its data, and reconcile the information into that shared source. This is routine integration work, but it is also part of the conference operation that an agent can take on.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Finding a lobster in London
The next example leaves software maintenance entirely. A viral post showing a claw beside the Wall Street bull inspired swyx to put a similar prop in front of the conference. He asked Devin: “Where can I get a lobster in London?” The agent returned phone numbers, email addresses, and websites. Swyx clicked through the options, considered them, and requested more research. He credits that process with sourcing the lobster used at the conference; the described workflow includes his evaluation of the results, rather than an unattended purchase.
For this kind of task, his requirements are simple: web access and a sufficiently capable model. Whether the assistant is called OpenClaw, NanoClaw, or something else matters less than whether it can do knowledge work he would otherwise assign to an executive assistant or junior employee. A coding agent becomes an on-demand worker for research and coordination as well as implementation.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
From planning notes to speaker research
Swyx broadens the examples beyond Devin, disclosing that he now advises Cognition rather than working there in the capacity described earlier. He has begun exploring Town as coding agents expand into general knowledge work. He connects this direction with purpose-built knowledge tools, Andrej Karpathy’s discussions of wikis, and what he describes as OpenClaw’s adoption of that approach. He expects this expansion to be one of the leading trends of 2026.
For World’s Fair planning, he starts with Apple Notes containing prospective speakers and tracks. He supplies those notes to Town and gets a formatted Notion document containing research on the speakers he is considering approaching and curating. The names on the displayed notes are intentionally small; the useful part of the example is the transformation from a personal planning list into researched material that supports the next decision.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
The people who inherit a replacement must trust it
Success with individual tasks can lead to a larger ambition: replacing an entire SaaS product with something built internally. Swyx shows himself debating an unnamed replacement with employees. He jokingly calls his stronger enthusiasm “psychosis,” but takes the disagreement seriously. A manager cannot dismiss the objections of the people who will have to operate the result.
Those concerns are valid because employees bear the consequences when the replacement fails—and swyx explicitly acknowledges that the team gets things wrong. His method is to identify the three most important concerns and systematically reduce them. At the time of the talk, that evaluation is still underway. The example is an approach to earning confidence in a replacement, not a completed story of eliminating a SaaS dependency.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Build interfaces for the user that is arriving
These internal changes also suggest a product-design problem: the entity using a service may increasingly be an agent. Swyx attributes to Malte’s opening keynote a claim that 60% of Vercel’s user base consists of bots or agents. The denominator and measurement period are not established here, so that figure should not be treated as a measured share of customers. It motivates swyx’s broader emphasis on APIs, CLIs, and MCP interfaces as ways for agents to use software.
There is a related change in where interfaces appear. Swyx points to MCP Apps speakers Ido and Liad, also referencing their ETN appearance, as advocates for shipping UI into someone else’s application. MCP Apps supplies a concrete setting for that idea: users can encounter a service’s interface within an MCP client. A product’s own dashboard no longer has to be the sole destination for using it.
Agent experience means designing for this changing primary user. Swyx’s own Figma workflow makes the shift tangible: he cares less about navigating the dashboard himself when he can give the task to Claude Cowork and hope it completes the work. His closing invitation is to bring that experimentation into everyday work, including the tasks surrounding software development. The AGI-pill joke returns as an invitation to bring hesitant colleagues along.
Suggest correction
This note stays in this page until you copy or download it. Nothing is submitted; reloading clears the draft.
Resources
From the talk
Swyx's synthesis of hiring, culture, operations, and technical practices from the World's Fair Tiny Teams track.
An AI assistant for delegated work that maintains context about how its user works.
A customizable personal assistant whose agents run in separate Linux containers.
The personal AI assistant project mentioned as another way to delegate everyday knowledge work.
Further reading
Current setup and collaboration instructions for starting Devin sessions and sharing attachments through Slack.
Examples of connecting Devin to external tools, including working with Figma designs.
Benchmark-specific evidence on falling inference prices, including GPT-3.5-level performance on MMLU.
- MCP AppsArticle
The official announcement explaining how interactive application interfaces appear inside MCP clients.
Read the complete timestamped transcript
- 0:00
[upbeat music] The future of work has many paths.
- 0:18
Our next presenter will discuss the path that he walked with Devin as he organized this very conference. Please join me in welcoming to the stage the co-founder of AI Engineer Conferences, swyx. [upbeat music]
- 0:33
Oh. [audience applauding] Hi, everyone. Uh, I am not the chief AI officer of the UK. Uh, I-- unfortunately, he, he had to leave for a personal reason. Uh, but, you know, you get me.
- 0:47
Uh, thanks for staying so long. I hope-- [audience applauding] Is everyone having a good time? Thank you.
- 0:51
Uh, it, it's so endearing and, and, and heartwarming to, to hear from you guys. Uh, I'll take you a little bit into how we build AI Engineer with AI, and it's, it's probably the biggest revelation that I've had.
- 1:05
Uh, so yeah, we've had, we've had a lot of really warm reception from you guys, and I think it's really great. And, uh, I think this is something that we really try to engineer, and, and hopefully, you know, this is our first event in London.
- 1:16
Hopefully, you have us back next year. Um, one, one thing I wanted to, so for those who are newer to us, uh, I do one of these keynotes every single AIE.
- 1:25
Um, the, the first, very first one three years ago, I s- talked about the productivity gain that you get from the increased AI eng-- uh, from, from the increased usage of AI.
- 1:35
Um, and the second one, we talked about how you should just use more AI because the cost curve of AI is going down roughly a hundred times, uh, per, per every twelve to eighteen months, and I think it's still continuing to, to trend that way.
- 1:50
Um, the third year, we started to talk about tiny teams, uh, which, which was basically this definition that I had that teams with more millions in revenue than number of employees.
- 2:00
Um, and I even curated an entire track at the World's Fair about this, uh, where we ta-- where we sort of summarized it as the Tiny Teams playbook if you're interested in building that.
- 2:09
Uh, the reason I liked this emphasis is because, um, I think people are maybe too egotistical about looking at-- for the one-person billionaire or, or unicorn founder. Um, every company can have a tiny team, whether you're small or large.
- 2:23
Um, and I think when I look at how I-- how we run AI Engineer, uh, me being the, the, the leadership of Ben Li and myself, uh, we are also a tiny team.
- 2:31
Um, this is us. Uh, it's just, uh, nine full-time people, and, uh, we're running a business that is more than nine million dollars, so we are a tiny team.
- 2:43
Um, and I wanted to show you the most significant changes in our workflow, uh, since we started this two years ago. Uh, by the way, this is, uh, our taking the AGI pill moment.
- 2:53
Uh, did you guys get the AGI pills?
- 2:55
Yeah.
- 2:55
Yes. [laughs] I'm very proud of this. This is my brainchild. Uh, if one of your coworkers is not sufficiently AGI pilled, you should prescribe one of this. You are all AGI doctors now.
- 3:07
Okay. Our stack was very stable and completely non-AI, which is very ironic for an AI conference. Uh, we do Figma, React, Supabase, Tido, Fig-- uh, Google Sheets, Sessionize. Um, and then I had this funny, weird moment where I joined Cognition, uh, and, and started talking, uh, started using coding agents seriously at work, mostly because they were free.
- 3:31
Um, and I started adding it to the company Slack, and then I started doing things with it and showing people, "Hey, here's how you use it to do coding on the, the company website."
- 3:41
All well and good, and something strange starts happening. Um, I start introducing-- uh, this is, this is a, a c- a workflow of our contract designer, now full-time, um, uh, showing me a Figma page and asking me to go through it and expecting that we would take a week, two weeks, four weeks to turn it into reality.
- 4:00
Um, I just added Devin to it, um, and ul- and ultimately, uh, before I had to add Devin to it, I had to hook up Devin to Figma, and I'm not gonna be doing that shit.
- 4:10
So Cowork is doing it for me. You should use Cowork for, [laughs] uh, for doing this. And which, uh, which by the way, leads me to my first lesson, which is anytime there's, like, random yak shaving, I think one underappreciated, um, uh, benefit of agents is that they save you the yak shaves.
- 4:24
Like, all the dependency tree crawling of like, "Oh, no, I have to do that first. Oh, no, I have to do that first." And particularly when it comes to installing dependencies or fixing Python dependencies, fantastic for that.
- 4:34
And I think, um, a, a mo- model of productivity that doesn't sufficiently appreciate parallelism and not just autonomy, I think, uh, and, and sort of depth of the yak shaving is not fully capturing the, the benefit of agents.
- 4:46
Um, so anyway, back to the agent story. Uh, hooked up Devin to Figma, and we, uh, in very short order, we have a perfectly functioning website, uh, that is pixel perfect to the Figma.
- 4:57
And to me, uh, that was a surprise because I'd never done it before. You know, you always mistrust marketing until you see it for yourself. And more importantly, our, our designer was very happy about it.
- 5:07
Um, and that's the, that's basically the, the website that you see live today when you go to ai.engineer. Um, the other interesting thing that happened was then we started using it more, right?
- 5:17
After, after one initial success, you start using it more. Uh, something that you can't see because it's very small text, but I'm gonna highlight for you, is that that is two hundred and seven replies just exploding in usage.
- 5:27
Like, what the hell? Um, and when you dig into it, um, it's, it's very interesting, right? So first of all, uh, I start kicking off some, some work, and then I go to bed, and then, uh, my designer who's in Indonesia wakes up and starts messing with Devin.
- 5:41
Starts prompting Devin with red lines, uh, on annotations, which is something that, uh, Steve Ruiz, one of our speakers from yesterday, does with tldraw. And I never taught him to do this, and there's no instruction manual.
- 5:52
It was just mostly like, how would you communicate with another human being? And so I work mostly with a non-technical team, and I think that's very important that they need to be comfortable with agents, and I think they're finally at the point that they are.
- 6:04
Um, we start working on things that we would never normally have worked on. Uh, nobody has reported this, so I assume none of you have discovered it, but there's a Easter egg on the website.
- 6:12
Why? 'Cause I put it there. Why? 'Cause it was fun. 'Cause I could, right? So if you're on an ultra wide, you sc- you scan your mouse over the, the highlights, you'll, you'll see an Easter egg.
- 6:21
Um, uh, I saw a tweet that was viral a- about a design aesthetic that I liked. I threw it into Devin. Out pops, um ...
- 6:32
And then, and then, and then, you know, 127 replies later, uh, I, I, literally I popped it in. I was like, "Oh, let's just see what the, the clanker will, will do for me.
- 6:39
Uh, I don't want to waste my designer's time. I just wanna see what a clanker do, does for me." Designer jumps in,
- 6:45
um, and, and does, and does, and start, actually starts working on this thing which I thought was throwaway and fun. And the most interesting thing, it's so small I can't even read it.
- 6:53
I'm so sorry for this. Uh, so basically the reason he starts working on it, even though it's a throwaway project, is because it's fun, and I think that's something, uh, that was like a big aha moment for me.
- 7:02
Like, I am getting more work out of my employees because they enjoy doing it, because the feedback cycle for them from, like, waiting, blocking on me or a contract d- uh, developer that we have is gone.
- 7:13
Like, they, they just literally, they have the idea, they go do it, right? Um, and, uh, they're doing more things. They're doing animations, they're doing polish. Uh, things that we've just- I'm getting work that I've never gotten out of, uh, my employees before, and I think that's something that's appre- that's something you, you should appreciate, too.
- 7:29
Um, I'm-- If you haven't noticed, I'm no longer talking about agents for coding or, like, how many lines of code I'm producing. I'm getting more productivity out of my humans, and I, I, I think this is something that is a major theme for this year that I'm really trying to investigate, which is agents for everything else.
- 7:45
Um, then obviously, okay, I had that success with Figma to, uh, to, to website. I have the success with tweet to website. What else? Right? Like, you start to think about other use cases.
- 7:57
Um, this whole conference is a giant data management problem. Like, I have to sync with 130 speakers and a couple dozen sponsors and all the attendees that come in with all various, uh, needs.
- 8:11
Um, and really, uh, it's just a CMS, right? Like, we, we, we've, we've messed with the Sanity. I'm not a, the, the biggest fan of Sanity in the world, um, because I want to keep some sanity to myself.
- 8:22
Um, but, but basically, like, I, I can throw in, uh, spreadsheets and, and Devin can manage that for me. And once I really-- I think the unlock ho- uh, happened when I threw away the CMS and just kinda committed that to code, but used that code as my s- sort of source of truth, and let Devin, whatever
- 8:36
coding agent you use, uh, start to manage it. And so this entire schedule, uh, is managed by Devin. What does that mean? It means that whenever, um, someone comes in with a speaker change, for example, Marta, one of the speakers from today, uh, sends in an email, I just say, "Devin, handle it for me," right?
- 8:54
No other furth- further communication is needed. I can just forward the email. I can, uh, paste a screenshot, whatever. Um, and that kind of volume lets us as a small team of nine people manage a thousand-person conference, right?
- 9:06
We're gonna manage 6,000 people in San Francisco this fall, uh, th- this summer. Um, and w- I'm pretty sure we can stay the same size. Like, it, it is incredible the amount of productivity that you can get once you're sufficiently onboarded and you have the workflows ironed out.
- 9:20
Um, we have agents for ETL. We, we deal with an external vendor system that has data that we don't have in a, in a central source of truth, so I need to get the API key to sync over data and make sure there's a single source of truth.
- 9:33
Uh, these are very boring routine tasks. Um, well, there's, there's another, you know, another fun story that I can tell you is agents for buying. Uh, so I saw this viral tweet about how somebody put a claw in, uh, Wall Street next to the Wall Street bull, and I was like, "Oh, that's funny.
- 9:47
Like, we should put a claw in front of our, um, conference," and that's exactly... And so, so I asked Devin to research, "Where can I get a lobster in London?"
- 9:58
Devin comes back with phone numbers and email addresses and websites, and I just click through and, and think about it and ask it to do some more research, uh, and out pops this guy.
- 10:08
Uh, that's literally the, the lobster that you had was bought from Devin. Uh, and I think, um, this kind of personal automation for everything else, it just matters that you have an agent that has web access, that has some, uh, smart enough model.
- 10:22
Uh, it-- I mean, this is effectively a claw, right? Like, a, an OpenClaw, NanoClaw, whatever the, whatever clanker you call it. It doesn't really matter. It matters that you're using agents for things that you would otherwise have spent knowledge work on.
- 10:34
I might have had an executive assistant, I might have had a junior employee do these things for me, but now I can do it serverless on demand with a coding agent.
- 10:44
Um, I'm not here to only show Devin. Uh, I, I, you know, I o- I just advise with the company now. Um, but, uh, I, you know, I started exploring Town because I think, uh, what's, what's happening here is coding agents kind of breaking containments, right?
- 10:57
Um, there's all these other more f- fit for purpose knowledge management tools, uh, like the wikis that Andrej Karpathy is, is talking about that, uh, NanoClaw, uh, that OpenClaw is, is, is now adopting as well.
- 11:08
Um, you're gonna see an explosion of this this year. Uh, this is, like, probably the top trend of maybe top three to five trends, uh, of 2026 that I want to alert you to.
- 11:17
Um, so here is me managing t- uh, the World's Fair in 2020, uh, in, in, in this summer. Uh, here are all the tracks I'm planning. Here's my Apple Notes.
- 11:27
Uh, on the left is my Apple Notes of all the people. I'm, uh, it's intentionally small, and I threw it into, into Town, and on- out pops a nicely formatted Notion doc with, uh, research on all the speakers that I intend to, uh, solicit and, uh, think about curating.
- 11:43
Um, and then obviously once you get enough psychosis, you are thinking about replacing entire pieces of SaaS. Here's me arguing with my employees [laughs] about kicking out a, a SaaS tool and building it ourselves because we can.
- 11:57
Um, so I clearly have the most psychosis. I think one of the annoying things is if you're in a position of power or management to deal with employees who are, who are not as much in psychosis and try to bring them along the journey and, and not, uh, talk down or, or, or, or ignore their concerns, right?
- 12:13
Because they are very valid concerns, because they are exactly the people that will have to deal with your bullshit when you get it wrong, and we do get it wrong.
- 12:20
Um, so, uh, one, one ch- one top, one method I, I, I'm approaching these sort of AI replacing SaaS concept, which I think is, is, should be relevant for a lot of you, uh, is, well, let's identify the top three concerns and let's systematically reduce, uh, reduce them.
- 12:34
And that's the process that we're going through right now. So, um, I just wanted to give you a little bit of that t- taste of like, here's how AI is changing our business, uh, as managing the conference.
- 12:44
Um, it's come really, it's come really a long way. I- it's a, it's a consistent theme I'm seeing even among our, our speakers. Uh, this is Malta opening keynote, uh, talking about how the, the 60% of the, the, the sort of user base of Vercel now is bots, is, is, is agents.
- 13:00
It's not humans. So actually, your dashboards don't matter. Your APIs matter, your CLIs matter, your MCPs matter. Um, here is the MCP, uh, apps guys, Ido and Liad, uh, who spoke today, um, on, speaking on ETN about how basically your custom UI is kind of going away.
- 13:17
Like, you should ship UI to, uh, somebody else's app. And I think, like, this patterns of, like, how your primary user is changing is really shifting towards what people are calling agent experience, and I think that's something that, again, I'm really inspired by and focused on because it is helping me, right?
- 13:32
I no longer care about the Figma dashboard. I throw it into co- Cloud Cowork and I hope that it works for me. Um, so that's my message. Agents for everything else are coming.
- 13:42
Wake up, use it, bring it home to work. If people are insufficientally bought on, prescribe them one of these. Thank you. [clapping] [upbeat music]