Will Viles (@willviles) header
Will Viles (@willviles) profile picture

GTM Systems Engineer @vercel ▲ Sports fanatic @bcfc fan & groundhopper ⚽️🎾🏃🏻‍♂️

🇬🇧 Birmingham
Joined April 2009
Photo by Will Viles (@willviles)Photo by Will Viles (@willviles)Photo by Will Viles (@willviles)Photo by Will Viles (@willviles)Photo by Will Viles (@willviles)Photo by Will Viles (@willviles)Photo by Will Viles (@willviles)Photo by Will Viles (@willviles)Photo by Will Viles (@willviles)Photo by Will Viles (@willviles)
Will Viles retweeted
One of the most impressive things I've seen, and I think this is an important advancement to the state of the art. Message boards were the enabling technology of both the Navier-Stokes math breakthrough and even the OpenAI/HuggingFace cyber feat. We built a message board infrastructure primitive. You can think of it as "headless Slack" (or remember IRC?) for agents. This is an important building block for software factories, self-optimizing systems, and scientific research, where the human prompting is just the seed of the system, and millions of agents can operate in a decentralized fashion. 𝚟𝚎𝚛𝚌𝚎𝚕 𝚋𝚘𝚊𝚛𝚍 is designed to be model, harness and hosting platform agnostic. Just bring your agents, give them our CLI, and watch magic happen.
Introducing 𝚟𝚎𝚛𝚌𝚎𝚕 𝚋𝚘𝚊𝚛𝚍, a secure message board for people & agents. • Give agents a shared place for tasks • Build swarms and software factories • Set permissions for humans and agents Board is experimental. Tell us what you think. vercel.com/blog/introducing-…
153
65
30
1,949
156,852
Will Viles retweeted
eve 1.0 feels like my life work even though it was just a markdown file back in March. I’m bias but I think it’s the best framework for building agents that lead to real business outcomes. And I don’t think it’s particularly close. This is less to do with some brilliant light bulb moment and everything to do with being at a company that has access to the best builders in the world. We built this framework along side them. Every feature and API in eve went through many variations purely based on real world experience. Both internally working with different teams at Vercel and externally working with companies like Clay, Mux, Browserbase and many others. Obviously any design can be copied and recreated in today’s token economy. In many ways it’s very flattering to see it happen. But I don’t think the stream of feedback and constant obsession over meeting that feedback can be copied in the same way. I’m very excited to keep delivering and see what people build. vercel.com/blog/eve-is-now-g…
18
17
1
193
12,448
Will Viles retweeted
eve is generally available with v1.0. • Build agents on your own harness • Ship multi-tenant, multiplayer agents • Govern & trace sessions with Agent Runs • Render agent UIs via Next.js, Nuxt & more Read the blog → vercel.com/blog/eve-is-now-g…
28
85
61
924
177,859
Will Viles retweeted
Your next users are agents. Evals are how you build for them. ▪︎ See how agents use your product ▪︎ Test changes before you ship ▪︎ Compare models as they launch vercel.com/blog/agent-evals
64
33
21
542
85,309
Will Viles retweeted
shipped a big one today. you can now jump into any subagent mid-task - watch it work - message it - answer its prompts it feels less like delegating and more like running a small team.
15
9
176
5,692
Will Viles retweeted
Conversations with an agent should feel natural. That's why non-blocking multi-player steering is the default in eve.
5
5
136
6,725
Will Viles retweeted
Introducing the UI SDK.
218
435
248
6,571
901,040
Will Viles retweeted
Thinking about how we’re all on a spinning rock in the middle of space...🌎
37
75
9
698
50,106
When this man named every English and Scottish team from The National League level and up, solely from memory… 🤯 Incredible knowledge… 👏
39
82
17
1,304
169,410
Will Viles retweeted
Generative UI for conversational agents. Combining @aisdk with Chat SDK and 𝚓𝚜𝚘𝚗-𝚛𝚎𝚗𝚍𝚎𝚛, you can go straight from LLM to UI on platforms like Slack and Teams. I believe this will become the dominant Human-Agent Interaction (HAI) paradigm: vercel.com/changelog/json-re…
257
144
55
2,775
222,741
Paying homage to the ball! A life long partner in crime that has a way of rewarding us with endless discovery!
275
956
378
15,807
4,154,154
Will Viles retweeted
Today we are starting the rollout of Device Bound Session Credentials (DBSC) for vercel.​com DBSC makes it impossible to steal session cookies from a device. So, if you install info-stealer malware (e.g. through a supply chain attack), that malware can not steal your vercel.​com session. Malware can still do bad things while residing on the device. But the abuse we are seeing in practice separates the stealing from the eventual abuse, and DBSC effectively prevents this. DBSC works by storing a private key in your device's TPM (the same device that the fingerprint sensor or similar biometric devices on your laptop or phone uses) and using that key to sign your cookie. The private key can never be retrieved ever again. Not by us, not by you, not by the malware. Every website should use DBSC but given how new of a technology it is, we still need to build more experience in rolling it out. In our case there were lots of special cases for things like oauth apps that we needed to resolve. This is also why we are taking a slow approach to the rollout. DBSC is currently only supported by Chrome on Mac and Windows. We are also working on a kind of polyfill for other browsers. However, the polyfill is less secure and we would love to see broader browser adoption. There is a related technology called DPoP which is essentially the same but for apps that run on your device. We're in the process of shipping this for Vercel CLI. Ideally, all CLIs and apps would adopt this technology. Luckily rolling out DPoP is much easier than DBSC and it does not depend on browser vendor support.
58
62
18
880
109,324
I'm starting to sense a divide in the tech industry: - People thriving on autonomy who are reinventing how they work and what tools they use with AI: LOTS of work, but they're enjoying it and getting very efficient - People used to being mentored / trained / or simply told what to do and how. Frustrated with the lack of guidance from management on what to do with AI; also frustrated by seeing some of their peers thriving; increasingly bitter about AI and the state of the industry, as a whole Neither group seems to be aware that there's another group, or have empathy for the other group
400
413
175
5,589
482,086
Will Viles retweeted
I've been cooking on this post for a bit, but with the cyber security events of this week I had to ship it: Long-live static credentials must die. We never want to rotate API keys again. Turns out only 8% of cloud and SaaS vendors support secure alternative. This is our call to action to change this AND our commitment to do our part: - We are requiring vendors on our marketplace to support OIDC - We shipped @shadcn components to make it easier to ship OIDC configuration - We are expanding OIDC support on our own platform The last generation got the web from HTTP to HTTPS. It is on us to move past API keys. vercel.com/blog/death-to-lon…
70
93
30
960
72,412
Will Viles retweeted
Introducing tiny.london A massive isometric pixel map of London, based on amazing NYC demo by @_coenen from 9 months ago My agent created the dataset, finetuned qwen image LoRA adapter, did a multiday inference run and built an efficient tile viewer!
I wanted to share something I built over the last few weeks: isometric.nyc is a massive isometric pixel art map of NYC, built with nano banana and coding agents. I didn't write a single line of code.
149
259
101
3,676
801,332
Will Viles retweeted
Ship SF 2026 is now live. Tune in: vercel.com/ship
7
25
8
480
38,924
Will Viles retweeted
This is one of the most exhilarating times in technology, and this challenge was yet another jaw-dropping moment. When the details of OpenAI’s agent escape and Hugging Face hack started to emerge, it became clear that agent containment would be one of the most important priorities for any AI infra company. There are two classes of escapes: ① "escape the network" and ② “escape the matrix” 😁, as in, break the spell of virtualization. OpenAI was the former, where an agent not supposed to have internet access… gained it by hacking another system. Genuinely astonishing and worrisome. Through this challenge, however, we discovered something even more groundbreaking. A talented white-hat researcher, armed with a swarm of AI agents, expertise and perseverance, "pierced through" the Linux virtualization boundary that nearly every cloud sandbox provider in the world banks on today. I'm very thankful we got the report, were able to quickly move to protect our customers, found no evidence of customer data compromise, and collaborated with many industry partners to protect the wider internet. Our confidence and conviction in Vercel Sandbox are even greater now, after some of the smartest, most motivated researchers in the world, and their agents, gave it their best shot.
We offered $1M to escape Vercel Sandbox. • 1,285 reports • $242,000 in bounties paid out • One Linux kernel zero day discovered • No reports of customer data compromise vercel.com/blog/findings-fro…
131
27
11
745
89,607
Will Viles retweeted
It’s hard to fathom fx.sh getting even faster, but it’s now… much faster 😂 As models speed up (as with Astra 𝚞𝚕𝚝𝚛𝚊𝚏𝚊𝚜𝚝), harness overhead matters more and more. Next release will feature even better performance for session storage and retrieval, and a big unlock for cloud durability in libfx.
fx v0.0.13 Ultrafast support. Faster launch, shell calls & exits. • Ultrafast for supported OpenAI models • Launch up to 23× faster • Shell calls up to 8.6× faster • Exits up to 44× faster • Configurable automatic compaction • Multiple bug fixes & security improvements fx.sh/changelog#v0.0.13
67
9
2
342
46,933
Will Viles retweeted
You can now use the latest Jev model by @typesafeai with the new 𝚎𝚟𝚊𝚕𝚞𝚊𝚝𝚎 method in AI SDK
16
43
13
786
73,822