Vercel News

Optimizing Vercel Sandbox snapshots

3 Apr 2026

When we recently shipped filesystem snapshots (https://vercel.com/changelog/filesystem-snapshots-supported-on-vercel-sandboxes) in Vercel Sandbox to let teams capture and restore a sandbox's entire

How Waldium made a blog platform work for humans and AI alike

3 Apr 2026

Waldium (https://www.waldium.com) is a two-person, YC-backed startup that built an agentic CMS for businesses. Co-founded by Amrutha Gujjar and CTO Shivam Singhal, the platform automates content

Vercel Queues now supports 7-day message TTL

1 Apr 2026

How FLORA shipped a creative agent on Vercel's AI stack

31 Mar 2026

FLORA on Vercel • 2x faster to production with their generation system • Zero infrastructure debates after migration • 50+ image models orchestrated A seasonal fashion launch is a story, not

Axios package compromise and remediation steps

31 Mar 2026

Agent responsibly

31 Mar 2026

The following is based on an internal talk given at Vercel. We're sharing it publicly because the problem it describes isn't unique to us, and the framework is useful for any team shipping with

Unified reporting for all AI Gateway usage

31 Mar 2026

If you're shipping AI features, you already have usage data. The problem is that it's split across providers, keys, and dashboards, so it's hard to answer basic questions before the bill shows up.

new.website joins forces with v0

31 Mar 2026

v0 and new.website have joined forces to accelerate our vision of helping anyone ship complete, production-ready software with AI. new.website was founded to make it effortless to create beautiful

SERHANT.'s playbook for rapid AI iteration

31 Mar 2026

Impact at a glance • Started with Next.js on Vercel, which made it easier to expand to a React Native iOS app without rebuilding their backend • Engineers focus on AI design and iteration

Making Turborepo 96% faster with agents, sandboxes, and humans

31 Mar 2026

Turborepo (https://turborepo.dev/blog/2-9) is now 81-91% faster to compute its task graph in our repositories, scaling with repo size. On our 1,000+ package monorepo, turbo run now feels instant.

Build knowledge agents without embeddings

31 Mar 2026

Most knowledge agents start the same way. You pick a vector database, then build a chunking pipeline. You choose an embedding model, then tune retrieval parameters. Weeks later, your agent answers a

Two startups at global scale without DevOps

31 Mar 2026

Leonardo.AI processes more than 4.5 million images every day across cities worldwide, and Relevance AI's agents run autonomously across time zones, touching Salesforce, HubSpot, Slack, and dozens of

Chat SDK brings agents to your users

31 Mar 2026

In early January, we gave the entire company a challenge: figure out how to multiply your output. People created agents. Mostly chat bots, but dedicated ones, purpose-built for real workflow

360 billion tokens, 3 million customers, 6 engineers

31 Mar 2026

Impact at a glance • Durable ships new production agents to customers in a single day • AI features and agents serve ~1.1B tokens per day (360B per year) • 10x leverage for every engineer,

Meet the 2026 Vercel AI Accelerator Cohort

31 Mar 2026

The Vercel AI Accelerator is back, and this year we selected 39 early-stage teams from across the US, Europe, Asia, and Latin America to build with us for six weeks. The next generation of AI

Vercel Open Source Program: Winter 2026 cohort

17 Mar 2026

In April, we launched the Vercel Open Source Program (https://vercel.com/open-source-program) to give maintainers the resources, credits, and support they need to ship faster and scale confidently.

How Notion Workers run untrusted code at scale with Vercel Sandbox

12 Mar 2026

Notion Workers let you write and deploy code to give Custom Agents new powers: sync external data, trigger automations, call any API. With Workers, developers can build agents that sync CRM data on a

How we run Vercel's CDN in front of Discourse

10 Mar 2026

Vercel's CDN can front any application, not just those deployed natively on the platform, and it's simple to set up. This allows you to add firewall protection, DDoS mitigation, and observability to

From idea to secure checkout in minutes with Stripe

5 Mar 2026

Building commerce applications looks very different than it did even a few years months ago. Teams are no longer treating storefronts and billing systems as long-running integration projects that

Building Slack agents can be easy

3 Mar 2026

Slack is already where teams work. It provides a natural interface for agents, with messages, threads, buttons, and events, so you don't need to invent a new UI or onboarding flow. Getting from "I

Scaling redirects to infinity on Vercel

3 Mar 2026

Redirects are trivial at a small scale, but at millions, latency and cost become real systems problems. Previously on Vercel, redirects were handled by routing rules and middleware. Routing rules

Advancing Python typing

2 Mar 2026

We’re excited to share a year-long research effort aimed at making Python’s type system more expressive and composable, something closer in spirit to the programmable types in TypeScript, but

Gamma builds design-first agents with Vercel

28 Feb 2026

Gamma began with a simple idea: what if your presentation could design itself? With a single sentence, users can generate a complete presentation that respects layout, spacing, and hierarchy. Columns

How Avalara turns pipe dreams into patent-pending with v0

28 Feb 2026

Avalara connects businesses to more than 1,400 systems to automate tax compliance around the world. It’s a massively complex ecosystem that spans ERP systems, finance platforms, and compliance

Keeping community human while scaling with agents

27 Feb 2026

At Vercel, our developer community is at the heart of everything we do. It's how we stay closest to the people using what we build. As our community grew, automation helped us scale. But questions

How OpenEvidence built a healthcare AI that physicians actually trust

25 Feb 2026

Andy Yoon was scrolling through Slack when he saw the message: OpenEvidence had gone viral on TikTok. Not "gaining traction.” Actually viral, reaching around two million views in less than a week.

Security boundaries in agentic architectures

24 Feb 2026

Most agents today run generated code with full access to your secrets. As more agents adopt coding agent patterns, where they read filesystems, run shell commands, and generate code, they're becoming

Skills Night: 69,000+ ways agents are getting smarter

20 Feb 2026

The room was full of people who had already used skills. Tuesday night we hosted Skills Night in San Francisco, an event for developers building on and around skills.sh (https://skills.sh), the open

Video Generation with AI Gateway

19 Feb 2026

AI Gateway now supports video generation, so you can create cinematic videos with photorealistic quality, synchronized audio, generate personalized content with consistent identity, all through AI

We Ralph Wiggumed WebStreams to make them 10x faster

18 Feb 2026

When we started profiling Next.js server rendering earlier this year, one thing kept showing up in the flamegraphs: WebStreams. Not the application code running inside them, but the streams

How Stably ships AI testing agents in hours, not weeks

17 Feb 2026

How the 6-person team at Stably ships AI testing agents faster with Vercel—moving from weeks to hours. Their shift highlights how Vercel's platform eliminates infrastructure anxiety, boosting

How we built AEO tracking for coding agents

9 Feb 2026

AI has changed the way that people find information. For businesses, this means it's critical to understand how LLMs search for and summarize their web content. We're building an AI Engine

Anyone can build agents, but it takes a platform to run them

9 Feb 2026

Prototyping is democratized, but production deployment isn't. AI models have commoditized code and agent generation, making it possible for anyone to build sophisticated software in minutes. Claude

Introducing Geist Pixel

6 Feb 2026

Today, we're expanding the Geist font family with Geist Pixel (https://vercel.com/font). Geist Pixel is a bitmap-inspired typeface built on the same foundations as Geist Sans and Geist Mono,

The Vercel AI Accelerator is back with $6m in credits

5 Feb 2026

Building an AI business is no small feat. Delivering a great agentic product requires infrastructure that handles deployment, security, and scale automatically, but that's table stakes. Startups also

Making agent-friendly pages with content negotiation

3 Feb 2026

Agents fetch web pages to answer questions, write code, and complete tasks. When an agent requests a page, it gets everything your browser gets, including navigation menus, stylesheets, JavaScript

The Vercel OSS Bug Bounty program is now available

3 Feb 2026

Security is foundational to everything we build at Vercel. Our open source projects power millions of applications across the web, from small side projects to demanding production workloads at

Introducing the new v0

3 Feb 2026

Since v0 became generally available in 2024, more than 4 million people have used it to turn their ideas into apps in minutes. v0 has helped people get promotions, win more clients, and work more

Run untrusted code with Vercel Sandbox, now generally available

30 Jan 2026

AI agents are changing how software gets built. They clone repos, install dependencies, run tests, and iterate in seconds. Despite the change in software, most infrastructure was built for humans,

How Stripe built a game-changing app in a single flight with v0

28 Jan 2026

What would traditionally require months of product-development coordination and building across multiple teams was achieved by one person in a single flight. Read more

How Sensay went from zero to product in six weeks

27 Jan 2026

Sensay went from zero to an MVP launch in six weeks by leaning on Vercel previews, feature flags, and instant rollbacks. The team kept one codebase, moved fast through pivots, and shipped without a

AGENTS.md outperforms skills in our agent evals

27 Jan 2026

We expected skills (https://agentskills.io/home) to be the solution for teaching coding agents framework-specific knowledge. After building evals focused on Next.js 16 APIs, we found something

Agent skills explained: An FAQ

26 Jan 2026

Learn what agents skills are, how to install them, how agents use them, and best practices for implementation. Read more (https://vercel.com/blog/agent-skills-explained-an-faq)

Testing if "bash is all you need"

22 Jan 2026

We invited Ankur Goyal from Braintrust to share how they tested the "bash is all you need" hypothesis for AI agents. There's a growing conviction in the AI community that filesystems and bash are the

AWS databases are now live on the Vercel Marketplace and v0

15 Jan 2026

AWS databases (https://vercel.com/marketplace/aws) are now available in the Vercel Marketplace (https://vercel.com/marketplace) and v0 (https://v0.app/). Read more

Use Perplexity Web Search with Vercel AI Gateway

14 Jan 2026

Models are powerful, but they're limited to their training data and knowledge cutoff date. When users ask about today's news, current prices, or the latest API changes, models can offer outdated

Introducing: React Best Practices

14 Jan 2026

We've encapsulated 10+ years of React and Next.js optimization knowledge into react-best-practices, a structured repository optimized for AI agents and LLMs. Read more

Nick Bogaty joins Vercel as Chief Revenue Officer

13 Jan 2026

It's a thrilling time to work in Sales at Vercel. The web is transitioning from pages to agents, and Vercel is building the self-driving infrastructure to power it. We've assembled a Sales

How Mux shipped durable video workflows with their @mux/ai SDK

12 Jan 2026

We invited Dylan Jhaveri from Mux to share how they shipped durable workflows with their @mux/ai SDK. AI workflows have a frustrating habit of failing halfway through. Your content moderation check

How to build agents with filesystems and bash

9 Jan 2026

Many of us have built complex tooling to feed our agents the right information. It's brittle because we're guessing what the model needs instead of letting it find what it needs. We've found a