Page 1 • Showing 20 tweets
We've upgraded http://v0nanobanana.vercel.app with Nano Banana 2 via @vercel AI Gateway. What's cool about this playground is not just how convenient it is (try pasting, dragging, parallel jobs… it's good.) It's that you pay with your own @vercel AI Wallet. You sign in, then we debit your usage from AI Gateway. In this most recent iteration, you can now top up the Gateway credits directly from the app. The code is available to you so you can make your own apps where users pay for their AI inference.
Vercel AI Gateway now supports video generation. Grok Imagine Video & Image are 🆓 until tomorrow. We used @v0 to create an open source Creative Studio powered by @xai Grok. Create images, videos, or make your own design tool! https://v0-grokstudio.vercel.app – it's quite fast. Some cool technical tidbits: ▪️ Vercel Workflows for reliable generation Video generation can take long. Users might restart their browsers or their wifi / LTE might drop. We smooth over that automatically. ▪️ Instant vector search Try searching the public generations. Now back to me. We used @mixedbreadai to index the content visually, so you can search 𝚋𝚕𝚊𝚌𝚔 𝚏𝚎𝚕𝚒𝚗𝚎 and get a cat (try it!) ▪️ Vercel AI Gateway All existing and future Grok models are accessible via our gateway without extra setup. When you deploy to Vercel, you get access to hundreds of models with a single account and unified billing It's obviously built with @nextjs (RSC). Open it in v0 to make it your own! h/t @estebansuarez for shipping this.
Let me g̶o̶o̶g̶l̶e̶ generate that for you
AI is an amplifier of your intellect and values. A mirror of your soul. If you were a confirmation bias person, AI can be catastrophic for you. There’s some way to contort almost any prompt to give you the answer you’re looking for. The extreme version of this is AI psychosis. If you’re a “more is more” product company, then you’ll inundate yourself in garbage. Imagine joining a company that invented a custom operating system, programming language, and every kind of app they need just because they can. I’m somewhat conflicted here. The more software gets produced, the more Vercel benefits. It all needs to be built, hosted, secured, and scaled. And yet I don’t think every single line of code is worth your company producing. Play the long term game.
From now on, hype-centric splashy launches will likely be strongly uncorrelated with success. If by the time you launch you don’t have escape velocity, you will likely get Sybil attacked¹. Agents will spin up 10 competing products with your same interface. Start with an audience of 1 and get confirmation that it works. Then expand to a circle of friends or design partners. By the time you go public, your moat needs to be deeper than it’s ever been. ¹ https://en.wikipedia.org/wiki/Sybil_atta…
en.wikipedia.org
Sybil attack - Wikipedia
If you don’t use your body, it atrophies, so you go to the gym or on a run. If you don’t use your brain, it atrophies, so you… What’s your plan?
🆕 GPT 5.3 Codex (xhigh) achieves 90% on Next.js evals out of the box, "frame-mogging" the competition so to speak: http://nextjs.org/evals
If you thought your company's edge was "how fast you ship", you're in for a rude awakening. Everyone can ship fast now. Obviously, not everyone can ship tastefully, with quality and restraint in mind. That's the new edge.
I started the @nextjs you know today from a 𝚁𝙴𝙰𝙳𝙼𝙴.𝚖𝚍 specification. That was the singular commit that set it on the trajectory you see today. We proceeded to furiously write code for weeks as we saw a unique window to disrupt the React ecosystem, which primarily consisted of "boilerplate" repos and static-only tooling. I now believe most software (and companies) will start out as markdown files, but it's agents that will be doing the furious coding. And the releasing. And the maintenance. I'm pretty happy that the API we laid out is as relevant as ever today. It's simple, filesystem focused, and its principles remain unchanged. http://v0-nextjs-hello-world.vercel.app
"Creation as a Service" will always beat "Software as a Service". I don't want your lowest-common-denominator software. I want software to work for me and meet my needs. I want platforms and infrastructure. To me, Slack is a good example of an ideal in-between of SaaS and Platform. I have zero interest in vibe coding my own Slack. (It's also particularly difficult software to perfect and scale, and if you disagree you have no idea how to build software 🤡). I do have a strong interest in extending Slack with our own agents. As I shared yesterday, more of our company runs on Slack-based "@" agents. We're making it easier than ever to deploy Slack agents on Vercel, with our AI infrastructure (gateway, workflows, sandbox, etc), starting with @v0. A lot of SaaS might be cooked, but Salesforce has a generational re-birth opportunity with Slack.
http://skills.sh night was packed with 1,000+ RSVPs. We’ll done it again soon!
📝 On APIs When I started angel investing my thesis was: the best companies are going to start out as APIs. I went on to seed invest in Scale AI, called scaleapi.com at the time, the API to human intelligence. Auth0, the API to identity. Clearbit, the API to business data. cc @vcbrags. Why was "API" a thesis? React was coming out, the idea of Next.js & Vercel was forming in my mind. The best software is the one that works for you, represents you, looks like you. Off-the-shelf software was "worst-common-denominator" software. The barrier to entry to building your own software would collapse with the rise of frameworks and cloud infrastructure. Building on that early success, my advice to aspiring entrepreneurs became: just build the API. Make your / homepage the description of that API. Focus on problems where a simple API can hide enormous amounts of real-world and business complexity. (Incidentally this advice works extra-well because it helps founders focus and not over-build.) Fast forward to the age of AI, agentic engineering, and the SaaS public market bloodbath. Software is now free to build. But when you sit down to vibe code your next 25k/mo MRR app with no mistakes, that app will sit on the shoulders of giants. Your agent will read Markdown. Then, it will run CLIs and call MCP tools. Your software will make API calls to other services. And software will become more and more invisible. Computers talking to other computers to get you an answer, even before you ask. If you're starting now (or starting over), focus on the API. Do it for the agents. http://x.com/i/article/20220407149397073…
Full self-driving infrastructure getting closer every day. Today we shipped: 1️⃣ 𝚐𝚎𝚝_𝚛𝚞𝚗𝚝𝚒𝚖𝚎_𝚕𝚘𝚐𝚜 in our MCP server¹ 2️⃣ 𝚟𝚌 𝚕𝚘𝚐𝚜 CLI filters² e.g.: --𝚜𝚝𝚊𝚝𝚞𝚜-𝚌𝚘𝚍𝚎 𝟺𝟶𝟺 --𝚕𝚒𝚖𝚒𝚝 𝟷𝟶 Just ask Claude Code to fix your crashes. Or trigger an agent when an anomaly alert webhook fires, or on a cron schedule. This stuff is basically science-fiction 😄 ¹ http://vercel.com/changelog/agents-can-n… ² http://vercel.com/changelog/vercel-logs-…
Every Monday I get a deep AI analysis of our metrics across every product area to enjoy with my coffee. Anomalies, growth, trends, recommendations. AI spots patterns human analysts easily miss. I can @ the agent for further questions. AI will soon be running every company.
We've identified, responsibly disclosed, and confirmed 2 critical, 2 high, 2 medium, 1 low security vulnerabilities in Cloudflare's vibe-coded framework Vinext. We believe the security of the internet is the highest priority, especially in the age of AI. Vibe coding is a useful tool, especially when used responsibly. Our security research and framework teams are extending their help and expertise to Cloudflare in the interest of the public internet's security.
The future of design is… engineering. All designers at @vercel now also build, thanks to tools like @v0, Claude Code, and Cursor. They've been contributing to our frontends and apps for a while now. But over the past few months, the leap they've made is engineering the design process itself by building agents. A big part of shipping is getting the word out in a compelling way, especially on the @x platform, the everything app. In the past, we used to spend a bunch of time hand-crafting images and illustrations for social cards. Our design team built an internal agent and web ui using @v0 and Claude Code that makes this process fully self-serve. It even includes a previewer of what the final artifact will look like on X. It's called Leap. It's probably saved us hundreds of hours of work but also massively raised our quality bar. The artifacts it produces are beautiful. If you had asked me even 12 months ago whether our design team would be building their own design tools, let alone be this good, I would call bs. There was no master plan, or God forbid, a "sprint" to make this happen. It just took a handful of prompts to build and it propagated on Slack. Leap is now one of the many agents that helps us run our company more smoothly, built and securely deployed on @vercel for our internal use.
Engineering before AI: ◉ Ability to focus > ability to parallelize Engineering post AI: III Ability to parallelize > ability to focus
Today we're announcing our very own Vercel Flags. Flags are essential to "ship fast without breaking things" as engineering teams grow. But now *every* engineering team is growing, because it's you + agents. Flags help you de-risk agentic engineering: https://vercel.com/docs/flags/vercel-fla…
