# Vercel Blog > The Vercel blog covers engineering, product updates, and customer stories. > Each post is available as markdown at /blog/{slug} Total posts: 576 --- ### [How Speechify serves 500,000 dynamic pages to 60 million users on Vercel](/blog/how-speechify-serves-50000-dynamic-pages-to-60-million-users-on-vercel) Published: 2026-07-15 Category: Customer stories Speechify serves 500,000 dynamic pages across 45 languages to 60 million users on Vercel. With Cache Components, ISR, and Instant Rollbacks, their growth team ships twice a day without breaking anything. ### [Open-weight models surge to 29% of volume, price per token flattens](/blog/ai-gateway-production-index-july-2026) Published: 2026-07-13 Category: Company News The AI Gateway production index covering data from June 2026: Open-weight models increased to a third of all token volume; Anthropic continues to dominate spend with 61% ### [Introducing the new Vercel Agent](/blog/vercel-agent) Published: 2026-07-08 Category: Company News Today we are expanding access to Vercel Agent: an AI agent that safely and autonomously investigates incidents, fixes builds, and reviews PRs on your production ### [Vercel acquires Better Auth to accelerate open source auth](/blog/vercel-acquires-better-auth) Published: 2026-07-07 Category: Company News Vercel is acquiring Better Auth, the open source TypeScript auth library. It stays free and MIT licensed as the team builds identity for the agent era. ### [Run any Dockerfile on Vercel](/blog/dockerfile-on-vercel) Published: 2026-06-30 Vercel now runs any HTTP server straight from a Dockerfile. Bring a Rails, Django, Spring Boot, or Go app and Vercel builds, deploys, autoscales, and runs it on Fluid compute with Active CPU pricing. ### [Vercel Ship 2026 recap](/blog/vercel-ship-2026-recap) Published: 2026-06-30 Category: Company News For a decade, Vercel has shaped how the web gets built. Now, we’re doing the same for agents. Vercel Ship 2026 brought over 2,500 people to London to build on Agentic Infrastructure. ### [Vercel and Shopify are rebuilding Hydrogen](/blog/vercel-and-shopify-are-rebuilding-hydrogen) Published: 2026-06-30 Vercel commits to being a design partner on the open source rebuild of Hydrogen, Shopify's framework for headless storefronts. ### [Vercel Services: Run full stack on Vercel](/blog/vercel-services-run-full-stack-on-vercel) Published: 2026-06-30 Run your whole backend on Vercel. Vercel Services deploys your frontend and every backend as one project, with routing, environment variables, and internal service-to-service communication wired automatically. ### [Vercel Open Source Program: Spring 2026 cohort](/blog/vercel-open-source-program-spring-2026-cohort) Published: 2026-06-29 Category: Community Announcing the spring 2026 cohort of Vercel's Open Source Program. Open source community tools, frameworks, and libraries ### [Build realtime voice agents on AI Gateway](/blog/realtime-voice-agents-on-ai-gateway) Published: 2026-06-29 Audio/voice support is live on AI Gateway, with realtime. Build realtime, low-latency voice agents with the AI SDK on Vercel AI Gateway, plus text to speech and speech to text behind one API key and your existing tooling. ### [AI SDK 7](/blog/ai-sdk-7) Published: 2026-06-25 AI SDK is the TypeScript SDK for building AI applications, features, frameworks, and agents across any model provider. AI SDK 7 focuses on what it takes to run AI in production. ### [Teaching agents product design at Vercel](/blog/teaching-agents-product-design-at-vercel) Published: 2026-06-25 Learn how Vercel teaches agents product design with agent skills, lint rules, Vercel Agent code reviews, evals, and a human-led update loop. ### [Vercel Flags: Platform-native feature flags](/blog/vercel-flags-platform-native-feature-flags) Published: 2026-06-22 Vercel Flags is a platform-native feature flag provider built into the Vercel developer platform, server-side by default with zero impact on page performance. ### [The Agent Stack](/blog/agent-stack) Published: 2026-06-17 Category: Company News Build production-grade AI agents with Vercel's Agent Stack. Connect to any model, run durable multi-step workflows, and securely link agents to your data and tools. Every building block you need, in one place. ### [Introducing Vercel Connect](/blog/introducing-vercel-connect) Published: 2026-06-17 Vercel Connect lets your apps and agents access Slack, GitHub, and other services without storing long-lived secrets. Register a connector once and request scoped, short-lived tokens at runtime. Now in Public Beta. ### [Introducing eve](/blog/introducing-eve) Published: 2026-06-17 Category: Company News Introducing eve, the open-source agent framework from Vercel for building, running, and scaling agents in production, with durable execution, sandboxed compute, approvals, channels, tracing, and evals built in. ### [Vercel for Enterprise Apps and Agents](/blog/vercel-for-enterprise-apps-and-agents) Published: 2026-06-16 Category: Company News Vercel for Enterprise Apps and Agents gives your entire company the ability to ship apps and agents safely, with identity, credential scoping, and infrastructure controls built into the platform by default. ### [How Okara runs CMO agents for 120,000 companies on Vercel](/blog/how-okara-runs-cmo-agents-for-120000-companies-on-vercel) Published: 2026-06-11 Category: Customer stories Okara built an AI CMO on Vercel that directs eight specialized agents to handle SEO, content, and social for 120,000+ businesses, powered by a team of four using Vercel AI Gateway and Sandboxes. ### [How the Weather Company serves real-time forecasts to 350 million daily active users on Vercel](/blog/how-the-weather-company-serves-real-time-forecasts-to-350-million-daily-active-users-on-vercel) Published: 2026-06-09 Category: Customer stories The Weather Company rebuilt its web stack and CMS on Vercel and v0, cutting design-to-launch from days to hours and lifting productivity 80%. ### [How Code and Theory cut time-to-prototype 75% with v0](/blog/how-code-and-theory-cut-time-to-prototype-75-with-v0) Published: 2026-06-09 Category: Customer stories Code and Theory cut time-to-prototype by 75% and deployment timelines 50 to 75% by replacing wireframes and requirement docs with prompt-to-code in v0. ### [How Fern runs multi-tenant docs for Webflow and ElevenLabs on Vercel ](/blog/how-fern-runs-multi-tenant-docs-for-webflow-and-elevenlabs-on-vercel) Published: 2026-06-09 Category: Customer stories Fern runs multi-tenant docs for Webflow and ElevenLabs on Vercel, serving 6M+ monthly page views with 50 to 80% faster page loads and 3x faster TTFB. ### [DeepSeek enters the fight for token volume, Anthropic continues to dominate spend](/blog/ai-gateway-production-index-june-2026) Published: 2026-06-08 Category: Company News The June 2026 AI Gateway production index: DeepSeek's token share jumped to 17% as low-cost models entered production, while Anthropic held 65% of all spend. ### [Protecting against token theft](/blog/protecting-against-token-theft) Published: 2026-05-29 Category: Field Engineering Inference theft lets attackers resell your paid AI calls. See how the attack works, why rate limits and auth walls fail, and how Vercel BotID stops it on every request. ### [How Conductor moved parallel coding agents from the laptop to the cloud with Vercel Sandbox](/blog/how-conductor-moved-parallel-coding-agents-from-the-laptop-to-the-cloud-with-vercel-sandbox) Published: 2026-05-27 Category: Customer stories Conductor built Cloud Workspaces on Vercel Sandbox so developers can run a fleet of coding agents in parallel, close the laptop, and have the agents keep working. Used by teams at Notion, Linear, and Ramp. ### [AI Gateway production index](/blog/ai-gateway-production-index) Published: 2026-05-12 The state of production AI in 2026. Data from seven months of AI Gateway traffic across hundreds of models and tens of trillions of tokens. ### [How Superset built the IDE for AI agents on Vercel](/blog/how-superset-built-the-ide-for-ai-agents-on-vercel) Published: 2026-05-10 Category: Customer stories How Superset built the IDE for AI coding agents on Vercel, running up to 10 coding agents in parallel per developer and nearly 600 preview deployments a day. ### [How KIKO Milano scales for Black Friday](/blog/how-kiko-milano-scales-for-black-friday) Published: 2026-05-05 Category: Customer stories Global beauty brand KIKO Milano migrated from AWS to Vercel, eliminating Black Friday prep, cutting build times 75%, and accelerating their release cycle. ### [How General Intelligence used agents to build an agent platform on Vercel](/blog/how-general-intelligence-used-agents-to-build-an-agent-platform-on-vercel) Published: 2026-05-04 Category: Customer stories Learn how General Intelligence built Cofounder, a multi-tenant platform that gives founders an AI team, using their own coding agents on Vercel. ### [Introducing deepsec: The security harness for finding vulnerabilities in your codebase](/blog/introducing-deepsec-find-and-fix-vulnerabilities-in-your-code-base) Published: 2026-05-04 Today we're open sourcing deepsec, an AI security harness that runs on your infrastructure, with your keys, against your code. ### [How GitBook serves 30,000 sites with sub-second content updates](/blog/how-gitbook-serves-30000-sites-with-sub-second-content-updates) Published: 2026-05-01 Category: Customer stories GitBook hosts 30,000 documentation sites on Vercel, serving 120 million monthly page views for companies like Nvidia, Zoom, and n8n. ### [2026 Vercel AI Accelerator recap](/blog/2026-vercel-ai-accelerator-recap) Published: 2026-04-28 Read the recap of the 2026 Vercel AI Accelerator, where 39 AI startups spent six weeks building with Vercel before pitching at Demo Day at our San Francisco headquarters. ### [How Zo Computer improved AI reliability 20x on Vercel](/blog/how-zo-computer-improved-ai-reliability-20x-on-vercel) Published: 2026-04-17 Category: Customer stories See how Zo Computer used Vercel AI Gateway and AI SDK to cut retry rates 20x, raise chat success to 99.93%, reduce P99 latency by 38%, and add new model support in under a minute while scaling its personal AI cloud platform.⁠ ### [A new programming model for durable execution](/blog/a-new-programming-model-for-durable-execution) Published: 2026-04-16 Vercel Workflows is now GA. Write durable, long-running functions in TypeScript or Python. No orchestrator, no Kubernetes, no separate infrastructure. 100M+ runs in beta across 1,500+ customers. ### [Agentic Infrastructure](/blog/agentic-infrastructure) Published: 2026-04-09 The shift to agentic infrastructure. For fifty years, infrastructure assumed a human operator. Someone to configure the server, click the deploy button, or read the logs. ### [Zero Data Retention on AI Gateway](/blog/zdr-on-ai-gateway) Published: 2026-04-08 Enforce zero data retention across your entire team and prevent providers from training on your data. AI Gateway handles routing and provider agreements for you. ### [Optimizing Vercel Sandbox snapshots](/blog/optimizing-vercel-sandbox-snapshots) Published: 2026-04-02 Vercel Sandbox snapshots let you save and restore your entire filesystem. Learn how we optimized snapshot restores with parallel downloads, streaming decompression, and local NVMe caching. ### [How Waldium made a blog platform work for humans and AI alike](/blog/how-waldium-made-a-blog-platform-work-for-humans-and-ai-alike) Published: 2026-04-01 Category: Customer stories How Waldium made a blog platform work for humans and AI alike. Waldium started the way most content platforms do: building blogs for humans to read. But something Amrutha kept noticing was quietly changing who, and what, showed up to read them. ### [How FLORA shipped a creative agent on Vercel's AI stack](/blog/how-flora-shipped-a-creative-agent-on-vercels-ai-stack) Published: 2026-03-31 Category: Customer stories Flora’s FAUNA creative agent turns ideas into visual workflows on a digital canvas. Built on the Vercel AI Stack (AI SDK + Workflow SDK DurableAgent + Fluid Compute) to ship faster and iterate at scale. ### [Agent responsibly](/blog/agent-responsibly) Published: 2026-03-30 There's a difference between leveraging AI and relying on it. A framework for shipping agent-generated code with the judgment and guardrails it requires. ### [Making Turborepo 96% faster with agents, sandboxes, and humans](/blog/making-turborepo-ninety-six-percent-faster-with-agents-sandboxes-and-humans) Published: 2026-03-30 Category: Field Engineering Turborepo 2.9 is up to 96% faster than Turborepo 2.8. Here's how we did it, using coding agents, a human in the loop, and Vercel Sandboxes. ### [Unified reporting for all AI Gateway usage](/blog/unified-reporting-for-your-ai-spend) Published: 2026-03-25 Break down AI inference costs by model, provider, user, and pricing tier. The Custom Reporting API gives you the data to calculate margins, track customer usage, and optimize spend across BYOK and system credentials. ### [new.website joins forces with v0](/blog/new-website-joins-forces-with-v0) Published: 2026-03-23 Category: v0 v0 and new.website have joined forces to shorten the path from prototype to production for websites and web apps. ### [SERHANT.'s playbook for rapid AI iteration](/blog/serhants-playbook-for-rapid-ai-iteration) Published: 2026-03-23 Category: Customer stories Learn how SERHANT. scaled its AI platform S.MPLE to 900+ real estate agents using Next.js, Vercel, and AI SDK, without replatforming or locking into a single model provider. ### [Build knowledge agents without embeddings](/blog/build-knowledge-agents-without-embeddings) Published: 2026-03-19 Category: Field Engineering Open source file-system and knowledge based agent template. Build AI agents that stay up to date with your knowledge base. Grep, find, and cat across your sources, no embeddings, no vector DB. ### [Two startups at global scale without DevOps](/blog/two-startups-at-global-scale-without-devops) Published: 2026-03-19 Category: Customer stories Discover how small AI teams in APJ scale to millions of users without hiring platform engineers. See how Vercel powers their growth. ### [Chat SDK brings agents to your users](/blog/chat-sdk-brings-agents-to-your-users) Published: 2026-03-19 Chat SDK is a unified TypeScript library for building chat bots that work across Slack, Discord, Teams, and more from a single codebase. Write once, deploy everywhere. ### [360 billion tokens, 3 million customers, 6 engineers](/blog/360-billion-tokens-3-million-customers-6-engineers) Published: 2026-03-18 Category: Customer stories Durable rewrote its multi-tenant AI platform onto Vercel to serve 3M customers with six engineers, cutting infra costs 3-4x and shipping new production agents in a single day. ### [Vercel Open Source Program: Winter 2026 cohort](/blog/vercel-open-source-program-winter-2026-cohort) Published: 2026-03-17 Category: Community Announcing the winter 2026 cohort of Vercel's Open Source Program. Open source community frameworks, libraries, and tools we rely on every day to build the web. ### [Meet the 2026 Vercel AI Accelerator Cohort](/blog/2026-vercel-ai-accelerator-cohort) Published: 2026-03-16 The Vercel AI Accelerator is back with 39 early-stage teams from around the world, $8M+ in partner credits, and a Demo Day in San Francisco on April 16. ### [How Notion Workers run untrusted code at scale with Vercel Sandbox](/blog/notion-workers-vercel-sandbox) Published: 2026-03-12 Category: Customer stories Learn how Notion Workers uses Vercel Sandbox to run untrusted code at scale with hard VM isolation, credential injection, and dynamic network policies. ### [How we run Vercel's CDN in front of Discourse](/blog/how-we-run-vercels-cdn-in-front-of-discourse) Published: 2026-03-10 Category: Security Vercel Community uses Vercel as a CDN in front of monolithic servers like Discourse or Wordpress. Use microfrontends to incrementally migrate to a new app. ### [From idea to secure checkout in minutes with Stripe](/blog/from-idea-to-secure-checkout-in-minutes-with-stripe) Published: 2026-03-05 You can now connect or import an existing Stripe account directly into your Vercel project, automatically configure environment variables, and move from Stripe Sandbox to production without manual key exchanges. ### [Building Slack agents can be easy](/blog/building-slack-agents-can-be-easy) Published: 2026-03-03 Build and deploy Slack agents in a single session. This skill handles configuration, secrets, and deployment, taking you from idea to production with just a conversation with your coding agent. ### [Scaling redirects to infinity on Vercel](/blog/scaling-redirects-to-infinity-on-vercel) Published: 2026-03-03 Redirects are trivial at a small scale, but at millions, latency and cost become real systems problems. This is the story of how Vercel implemented bulk redirects. ### [Advancing Python typing](/blog/advancing-python-typing) Published: 2026-03-02 PEP 827 introduces type manipulation to Python, bringing programmable, TypeScript-inspired type features to improve static typing, metaprogramming, and framework ergonomics. ### [Gamma builds design-first agents with Vercel](/blog/gamma-builds-design-first-agents-with-vercel) Published: 2026-02-28 Category: Customer stories How Gamma builds design-first AI agents at scale using the AI SDK, Vercel Functions, and the Edge Network. ### [How Avalara turns pipe dreams into patent-pending with v0 ](/blog/How-avalara-turns-pipedreams-into-patent-pending-with-v0) Published: 2026-02-28 Category: Customer stories For Chief Strategy and Product Officer Jayme Fishman, the path to modernizing Avalara starts with how it builds. ### [Keeping community human while scaling with agents](/blog/keeping-community-human-while-scaling-with-agents) Published: 2026-02-27 Category: Community Learn how Vercel scales community support with AI agents. We automated logistics to reclaim human focus, empowering our team to solve complex problems ### [How OpenEvidence built a healthcare AI that physicians actually trust](/blog/how-openevidence-built-a-healthcare-ai-that-physicians-can-trust) Published: 2026-02-25 Category: Customer stories How OpenEvidence built a healthcare AI that physicians actually trust and became the most widely used clinical decision support platform among U.S. clinicians, supporting over 20 million clinical consultations in January 2026. ### [Security boundaries in agentic architectures](/blog/security-boundaries-in-agentic-architectures) Published: 2026-02-24 Category: Security A framework for drawing security boundaries in agentic architectures. Most agents run with zero isolation between the agent and the code it generates. Learn where to draw the boundaries, from secret injection to full application sandboxing. ### [Skills Night: 69,000+ ways agents are getting smarter](/blog/skills-night-69000-ways-agents-are-getting-smarter) Published: 2026-02-20 Andrew Qu reflects on Skills Night SF: how a weekend project became 69,000 community-created skills, the security partnerships protecting them, and what eight partner demos revealed about agents, context, and the future of development. ### [Video Generation with AI Gateway](/blog/video-generation-with-ai-gateway) Published: 2026-02-19 Build video generation into your apps with AI Gateway. Create product videos, dynamic content, and marketing assets at scale. ### [We Ralph Wiggumed WebStreams to make them 10x faster](/blog/we-ralph-wiggumed-webstreams-to-make-them-10x-faster) Published: 2026-02-18 Category: Field Engineering WebStreams had too much overhead on the server. We built a faster implementation. See how we achieved 10-14x gains in Next.js rendering benchmarks. ### [How Ramp kept 100% uptime through 100x traffic surges on Vercel ](/blog/how-ramp-kept-100-uptime-through-100x-traffic-surges-on-vercel) Published: 2026-02-17 Category: Customer stories Ramp rebuilt its marketing site on Next.js and Vercel, holding 100% uptime and 0% error rates through 100x traffic surges during stunt-marketing events. ### [How Stably ships AI testing agents in hours, not weeks](/blog/how-stably-ships-ai-testing-agents-in-hours-not-weeks) Published: 2026-02-17 Category: Customer stories How Stably, a 6-person team, ships AI testing agents faster with Vercel, moving from weeks to hours. Their shift highlights how Vercel's platform eliminates infrastructure anxiety, boosting autonomous testing and enabling quick enterprise growth. ### [How we built AEO tracking for coding agents](/blog/how-we-built-aeo-tracking-for-coding-agents) Published: 2026-02-09 Learn how we built an AI Engine Optimization system to track coding agents using Vercel Sandbox, AI Gateway, and Workflows for isolated execution. ### [Anyone can build agents, but it takes a platform to run them](/blog/anyone-can-build-agents-but-it-takes-a-platform-to-run-them) Published: 2026-02-09 Why competitive advantage in AI comes from the platform you deploy agents on, not the agents themselves. ### [Introducing Geist Pixel](/blog/introducing-geist-pixel) Published: 2026-02-06 Geist Pixel is a bitmap-inspired typeface built on the same foundations as Geist and Geist Mono, reinterpreted through a strict pixel grid. It’s precise, intentional, and unapologetically digital. ### [The Vercel AI Accelerator is back with $6m in credits](/blog/the-vercel-ai-accelerator-is-back-with-6-million-in-credits) Published: 2026-02-05 Category: Company News A six-week program to help you scale your AI company offering over $6M in credits from Vercel, v0, AWS, and leading AI platforms ### [Making agent-friendly pages with content negotiation](/blog/making-agent-friendly-pages-with-content-negotiation) Published: 2026-02-03 Category: Field Engineering Learn how Vercel uses HTTP content negotiation to serve markdown to agents and HTML to humans from the same URL, reducing response sizes by 90% while keeping both versions synchronized. ### [The Vercel OSS Bug Bounty program is now available](/blog/the-vercel-oss-bug-bounty-program-is-now-available) Published: 2026-02-03 Category: Security Vercel is opening its open source software bug bounty program to the public for researchers find vulnerabilities and make OSS safer ### [Introducing the new v0](/blog/introducing-the-new-v0) Published: 2026-02-03 Category: v0 The new v0 brings production-ready AI coding to enterprises with git workflows, security, and real integrations. Ship faster with agents and teams. ### [Run untrusted code with Vercel Sandbox, now generally available](/blog/vercel-sandbox-is-now-generally-available) Published: 2026-01-30 AI agents need secure, isolated environments that spin up instantly. Vercel Sandbox is now generally available with filesystem snapshots, container support, and production reliability. ### [How Stripe built a game-changing app in a single flight with v0](/blog/how-stripe-built-a-game-changing-app-in-a-single-flight-with-v0) Published: 2026-01-28 Category: Customer stories Stripe built a production GTM value calculator in a single flight using v0, boosting adoption 288% and cutting value analysis time by 80%. ### [How Sensay went from zero to product in six weeks](/blog/how-sensay-went-from-zero-to-product-in-six-weeks) Published: 2026-01-27 Category: Customer stories Sensay went from zero to an MVP launch in six weeks for Web Summit. With Vercel preview deployments, feature flags, and rollbacks, the team shipped fast without a DevOps team. ### [AGENTS.md outperforms skills in our agent evals](/blog/agents-md-outperforms-skills-in-our-agent-evals) Published: 2026-01-27 A compressed 8KB docs index in AGENTS.md achieved 100% on Next.js 16 API evals. Skills maxed at 79%. Here's what we learned and how to set it up. ### [Agent skills explained: An FAQ](/blog/agent-skills-explained-an-faq) Published: 2026-01-26 A plainspoken Skills FAQ with a ready-to-use guide: what skill packages are, how agents load them, what skills-ai.dev is, how Skills compare to MCP, plus security and alternatives. ### [Testing if "bash is all you need"](/blog/testing-if-bash-is-all-you-need) Published: 2026-01-22 We tested bash vs SQL agents on structured data queries. SQL dominated, but combining both tools achieved 100% accuracy. Try the open-source eval harness. ### [AWS databases are now live on the Vercel Marketplace and v0](/blog/aws-databases-are-now-live-on-the-vercel-marketplace-and-v0) Published: 2026-01-15 v0 can now provision AWS databases as it builds your app. Aurora PostgreSQL, DynamoDB, and Aurora DSQL available in the Vercel Marketplace. ### [Use Perplexity Web Search with Vercel AI Gateway](/blog/use-perplexity-web-search-with-vercel-ai-gateway) Published: 2026-01-14 Vercel AI Gateway now supports Perplexity Web Search as a model-agnostic tool that works for all models and providers. Use the tool to get access to the most recent information to supplement your AI queries. ### [Introducing: React Best Practices](/blog/introducing-react-best-practices) Published: 2026-01-14 Category: Field Engineering 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. ### [Nick Bogaty joins Vercel as Chief Revenue Officer](/blog/nick-bogaty-joins-vercel-as-chief-revenue-officer) Published: 2026-01-13 Nick Bogaty joins Vercel as first Chief Revenue Officer from Adobe, bringing more than 20 years of enterprise GTM experience to lead an AI-forward sales organization. ### [How Mux shipped durable video workflows with their @mux/ai SDK](/blog/how-mux-shipped-durable-video-workflows-with-their-mux-ai-sdk) Published: 2026-01-12 Learn how Mux built durable AI video workflows into their @mux/ai SDK using Workflow DevKit, with automatic retries, state persistence, and zero infrastructure setup. ### [How to build agents with filesystems and bash](/blog/how-to-build-agents-with-filesystems-and-bash) Published: 2026-01-09 How to build agents with filesystems and bash, production agents, context management, template, bash ### [How we made v0 an effective coding agent ](/blog/how-we-made-v0-an-effective-coding-agent) Published: 2026-01-07 Category: v0 v0’s composite AI pipeline boosts reliability by fixing errors in real time. Learn how dynamic system prompts, LLM Suspense, and autofixers work together to deliver stable, working web app generations at scale. ### [Stopping the slow death of internal tools](/blog/stopping-the-slow-death-of-internal-tools) Published: 2025-12-27 Category: v0 Internal tools often decay due to high maintenance costs and security tradeoffs. Learn how Vercel uses v0 to build secure, sustainable custom software that business teams can ship and maintain without pulling engineers off the roadmap. ### [Pixel Portraits: AI generated trading cards](/blog/pixel-portraits-ai-generated-trading-cards) Published: 2025-12-23 How Vercel built AI-generated pixel trading cards for Next.js Conf and Ship AI, then turned the same pipeline into a v0 template and festive holiday experiment. ### [We removed 80% of our agent’s tools](/blog/we-removed-80-percent-of-our-agents-tools) Published: 2025-12-22 We spent months building a sophisticated text-to-sql agent, but as it turns out, sometimes simpler is better. Giving it the ability to execute arbitrary bash commands outperformed everything we built. We call this a file system agent. ### [AI SDK 6](/blog/ai-sdk-6) Published: 2025-12-22 Category: Field Engineering Introducing agents, tool execution approval, DevTools, full MCP support, reranking, image editing, and more. ### [Our $1 million hacker challenge for React2Shell](/blog/our-million-dollar-hacker-challenge-for-react2shell) Published: 2025-12-19 Category: Security We paid $1M to security researchers to break our WAF. Here's what we learned defending against React2Shell. ### [Cline now runs on Vercel AI Gateway](/blog/cline-on-ai-gateway) Published: 2025-12-16 Cline scales its open source coding agent with Vercel AI Gateway, delivering global performance, transparent pricing, and enterprise reliability. ### [How to prompt v0](/blog/how-to-prompt-v0) Published: 2025-12-15 Category: v0 The best v0 prompts include three things. What you're building, who uses it and when, and your design constraints. This guide walks through the framework with side-by-side tests showing faster generation times, less code, and better UX decisions. ### [Build smarter workflows with Notion and v0](/blog/build-smarter-workflows-with-notion-and-v0) Published: 2025-12-15 Category: v0 v0 now connects to Notion via MCP. Build dashboards, tools, and prototypes from your existing docs and databases, and write generated content back to your workspace. ### [Vercel launches partner certification](/blog/vercel-launches-partner-certification) Published: 2025-12-10 Vercel introduces the inaugural cohort of Vercel Certified Solution Partners. These industry-leading teams share our commitment to creating a faster, more accessible, and innovative web for our customers. ### [Inside Workflow DevKit: How framework integrations work](/blog/inside-workflow-devkit-how-framework-integrations-work) Published: 2025-12-09 Category: Field Engineering A deep dive into how Workflow DevKit integrates with modern frameworks, from Next.js and SvelteKit to Express and Hono, using a unified pattern for creating framework integrations. ### [React2Shell Security Bulletin](https://vercel.com/kb/bulletin/react2shell) Published: 2025-12-05 Active exploits exist for CVE-2025-55182 (React2Shell). Vercel WAF protections are in place, but upgrading is the only complete fix. Detection and mitigation steps for Next.js and React Server Components. ### [Billions of requests: Black Friday-Cyber Monday 2025](/blog/bfcm-2025) Published: 2025-12-02 Every year, Black Friday and Cyber Monday reveal how people shop, browse, and discover products at global scale. For Vercel, the weekend is not a different operating mode. The platform behaves the same way it does every day, only at heightened scale. ### [Investing in the Python ecosystem](/blog/investing-in-the-python-ecosystem) Published: 2025-12-02 Vercel welcomes the Gel Data team and deepens support for the Python ecosystem through PSF sponsorships, community funding, and improved Python developer tools. ### [AWS Databases coming to the Vercel Marketplace](/blog/aws-databases-coming-to-the-vercel-marketplace) Published: 2025-12-01 Vercel Marketplace adds Aurora PostgreSQL, Amazon DynamoDB, Aurora DSQL, available December 15. One-click provisioning, zero-config setup, and full v0 support. ### [How we built the v0 iOS app](/blog/how-we-built-the-v0-ios-app) Published: 2025-11-24 Category: v0 The v0 engineering team breaks down the challenges and decisions behind building the v0 app for iOS. ### [Security through design: Creating the improved Firewall experience](/blog/security-through-design-creating-the-improved-firewall-experience) Published: 2025-11-24 Category: Security Vercel introduces a new Firewall UI for better surfacing of events and alerts while providing deeper information on mitigation activity ### [Workflow Builder: Build your own workflow automation platform](/blog/workflow-builder-build-your-own-workflow-automation-platform) Published: 2025-11-24 Category: Field Engineering Workflow Builder is a free, open-source template, powered by Next.js and the Workflow DevKit, that helps you build workflow builder applications and agents. ### [Vercel Open Source Program: Fall 2025 cohort](/blog/vercel-open-source-program-fall-2025-cohort) Published: 2025-11-21 Category: Community Announcing the fall 2025 cohort of Vercel's Open Source Program. Open source community frameworks, libraries, and tools we rely on every day to build the web. ### [Self-driving infrastructure](/blog/self-driving-infrastructure) Published: 2025-11-21 At Vercel, we’re building self-driving infrastructure, a system that autonomously manages production operations, improves application code using real-world insights, and learns from the unpredictable nature of production itself. ### [Vercel collaborates with Google for Gemini 3 Pro Preview launch](/blog/vercel-collaborates-with-google-for-gemini-3-pro-launch) Published: 2025-11-18 The Gemini 3 Pro Preview model, released today, is now available through AI Gateway and in production on v0.app. ### [Vercel: The anti-vendor-lock-in cloud](/blog/vercel-the-anti-vendor-lock-in-cloud) Published: 2025-11-10 Framework-defined infrastructure interprets your code and provisions what you need, keeping your application portable across any platform. ### [How Nous Research used BotID to block automated abuse at scale](/blog/how-nous-research-used-botid-to-block-automated-abuse-at-scale) Published: 2025-11-07 Category: Customer stories Vercel BotID Deep Analysis protected Nous Research by blocking advanced automated abuse from attacking their application ### [How AI Gateway runs on Fluid compute](/blog/how-ai-gateway-runs-on-fluid-compute) Published: 2025-11-06 The AI Gateway is a simple application deployed on Vercel, but it achieves scale, efficiency, and resilience by running on Fluid compute and leveraging Vercel’s global infrastructure. ### [What we learned building agents at Vercel](/blog/what-we-learned-building-agents-at-vercel) Published: 2025-11-06 We're presenting a simple methodology for discovering successful agent projects that perform well with current generation AI ### [Build and deploy data applications on Snowflake with v0](/blog/build-and-deploy-data-applications-on-snowflake-with-v0) Published: 2025-11-04 Category: v0 The v0 Snowflake integration lets you build and deploy Next.js data applications with natural language. Your data stays secure in your Snowflake account. ### [BotID Deep Analysis catches a sophisticated bot network in real-time](/blog/botid-deep-analysis-catches-a-sophisticated-bot-network-in-real-time) Published: 2025-10-31 Category: Field Engineering BotID Deep Analysis is a sophisticated, invisible bot detection product. This article is about how BotID Deep Analysis adapted to a novel attack in real time, and successfully classified sessions that would have slipped through other services. ### [Vercel Agent can now run AI investigations](/blog/vercel-agent-can-now-run-ai-investigations) Published: 2025-10-31 Vercel Agent Investigation intelligently conducts incident response investigations to alert, analyze, and suggest remediation steps ### [Vercel achieves TISAX AL2 compliance to serve automotive partners](/blog/vercel-achieves-tisax-al2-compliance-to-serve-automotive-partners) Published: 2025-10-29 Category: Security Vercel has achieved TISAX Assessment Level 2 security standard to align with automotive and manufacturing industries ### [Bun runtime on Vercel Functions](/blog/bun-runtime-on-vercel-functions) Published: 2025-10-28 Category: Field Engineering Vercel Functions now supports the Bun runtime, giving developers faster performance options and greater flexibility for optimizing JavaScript workloads. ### [David Totten Joins Vercel to Lead Global Field Engineering](/blog/david-totten-joins-vercel-to-lead-global-field-engineering) Published: 2025-10-27 David Totten joins Vercel as VP of Global Field Engineering from Databricks to oversee Sales Engineering, Developer Success, Professional Services, and Customer Support Engineering under one integrated organization ### [Vercel Ship AI 2025 recap](/blog/ship-ai-2025-recap) Published: 2025-10-27 Earlier this year we introduced the foundations of the AI Cloud: a platform for building intelligent systems that think, plan, and act. At Ship AI, we showed what comes next. What and how to build with the AI Cloud. ### [You can just ship agents](/blog/you-can-just-ship-agents) Published: 2025-10-23 Vercel AI Cloud combines unified model routing and failover, elastic cost-efficient compute that only bills for active CPU time, isolated execution for untrusted code, and workflow durability that survives restarts, deploys, and long pauses. ### [AI agents and services on the Vercel Marketplace](/blog/ai-agents-and-services-on-the-vercel-marketplace) Published: 2025-10-23 Category: Company News Agents and Tools are available in the Vercel Marketplace, enabling AI-powered workflows in your projects with native integrations, unified billing, and built-in observability. ### [Built-in durability: Introducing Workflow Development Kit](/blog/introducing-workflow) Published: 2025-10-23 The Workflow Development Kit (WDK) makes async workflows in TypeScript reliable, durable, fault-tolerant, and portable across any cloud. ### [Zero-config backends on Vercel AI Cloud](/blog/zero-config-backends-on-vercel-ai-cloud) Published: 2025-10-23 Build, scale, and orchestrate AI backends on Vercel. Deploy Python or Node frameworks with zero config and optimized compute for agents and workflows. ### [Introducing Vercel Agent: Your new Vercel teammate](/blog/introducing-vercel-agent) Published: 2025-10-23 Vercel Agent provides AI-powered code reviews and production investigations, delivering accurate, context-aware insights to help you ship reliable software. ### [Update regarding Vercel service disruption on October 20, 2025](/blog/update-regarding-vercel-service-disruption-on-october-20-2025) Published: 2025-10-21 Update regarding Vercel service disruption on October 20, 2025. Read the summary of impact, timeline, root cause, and steps we’re taking to improve reliability. ### [Agents at work, a partnership with Salesforce and Slack](/blog/agents-at-work-a-partnership-with-salesforce-and-slack) Published: 2025-10-15 Category: Company News Vercel and Salesforce are partnering to help teams build, ship, and scale AI agents across the Salesforce ecosystem, starting with Slack. ### [Running Next.js inside ChatGPT: A deep dive into native app integration](/blog/running-next-js-inside-chatgpt-a-deep-dive-into-native-app-integration) Published: 2025-10-15 Next.js now runs natively in ChatGPT with working navigation, React Server Components, and full features. Learn how we made this possible behind ChatGPTs triple iframe architecture and deploy our starter template to get started. ### [Talha Tariq joins Vercel as CTO of Security](/blog/talha-tariq-joins-vercel-as-cto-security) Published: 2025-10-15 Talha Tariq joins Vercel as CTO of Security, bringing expertise from HashiCorp and IBM to lead security innovation in the AI era. ### [Just another (Black) Friday](/blog/just-another-black-friday) Published: 2025-10-15 Vercel customers can treat Black Friday like just another day, ready to scale to billions of requests. ### [Server rendering benchmarks: Fluid Compute and Cloudflare Workers](/blog/fluid-compute-benchmark-results) Published: 2025-10-09 Fluid Compute outperforms Cloudflare Workers by 1.2x–5x in server-side rendering benchmarks, offering faster, more consistent response times through an optimized in-region architecture. ### [Towards the AI Cloud: Our Series F](/blog/series-f) Published: 2025-09-30 Category: Company News Today, Vercel announced an important milestone: a Series F funding round valuing our company at $9.3 billion. ### [Collaborating with Anthropic on Claude Sonnet 4.5 to power intelligent coding agents](/blog/collaborating-with-anthropic-on-claude-sonnet-4-5) Published: 2025-09-29 Claude Sonnet 4.5 is now available on Vercel AI Gateway and across the Vercel AI Cloud. Also introducing a new coding agent platform template. ### [Preventing the stampede: Request collapsing in the Vercel CDN ](/blog/cdn-request-collapsing) Published: 2025-09-25 Category: Field Engineering The Vercel CDN now supports request collapsing for ISR routes. For a given path, only one function invocation per region runs at once, no matter how many concurrent requests arrive. ### [BotID uncovers hidden SEO poisoning](/blog/botid-uncovers-hidden-seo-poisoning) Published: 2025-09-22 A financial institution's suspicious bot traffic turned out to be Google bots crawling SEO-poisoned URLs from years ago. Here's how BotID revealed the real problem. ### [How we made global routing faster with Bloom filters](/blog/how-we-made-global-routing-faster-with-bloom-filters) Published: 2025-09-19 Category: Field Engineering We replaced slow JSON path lookups with Bloom filters in our global routing service, cutting memory usage by 15% and reducing 99th percentile lookup times from hundreds of milliseconds to under 1 ms. Here’s how we did it. ### [What you need to know about vibe coding](/blog/what-you-need-to-know-about-vibe-coding) Published: 2025-09-18 Category: v0 Vibe coding is revolutionizing how we work. English is now the fastest growing programming language. Our state of vibe coding report outlines what you need to know. ### [Scale to one: How Fluid solves cold starts](/blog/scale-to-one-how-fluid-solves-cold-starts) Published: 2025-09-18 Learn how Vercel solves serverless cold starts with scale to one, Fluid compute, predictive scaling, and caching to keep functions warm and fast. ### [Addressing security and quality issues with MCP tools in AI Agent](/blog/generate-static-ai-sdk-tools-from-mcp-servers-with-mcp-to-ai-sdk) Published: 2025-09-17 Use mcp-to-ai-sdk to generate MCP tools directly into your project. Gain security, reliability, and prompt-tuned control while avoiding dynamic MCP risks. ### [AI agents at scale: Rox’s Vercel-powered revenue operating system](/blog/ai-agents-at-scale-roxs-vercel-powered-revenue-operating-system) Published: 2025-09-16 Category: Customer stories Learn more about how Rox runs global, AI-driven sales ops on fast, reliable infrastructure thanks to Vercel ### [Helly Hansen migrated to Vercel and drove 80% Black Friday growth ](/blog/how-helly-hansen-migrated-to-vercel-and-drove-80-black-friday-growth) Published: 2025-09-15 Category: Customer stories The 150-year-old Norwegian brand leveraged Next.js and Vercel to achieve 154% Black Friday growth and 30%+ conversion lift while competing against industry titans in a crowded space ### [Introducing Vercel Drains: Complete observability data, anywhere](/blog/introducing-vercel-drains) Published: 2025-09-15 Vercel Drains give you a single way to stream observability data out of Vercel and into the systems your team already rely on. ### [Introducing x402-mcp: Open protocol payments for MCP tools](/blog/introducing-x402-mcp-open-protocol-payments-for-mcp-tools) Published: 2025-09-12 We built x402-mcp to integrate x402 payments with Model Context Protocol (MCP) servers and the Vercel AI SDK. ### [MongoDB Atlas is now available on the Vercel Marketplace](/blog/mongodb-atlas-is-now-available-on-the-vercel-marketplace) Published: 2025-09-10 MongoDB Atlas is now available on the Vercel Marketplace, enabling developers to provision, manage, and scale fully managed MongoDB databases directly from the Vercel dashboard. ### [The second wave of MCP: Building for LLMs, not developers](/blog/the-second-wave-of-mcp-building-for-llms-not-developers) Published: 2025-09-09 Category: Field Engineering The second wave of MCP, building for LLMs, not developers. Explore the evolution of MCP as it shifts from developer-focused tools to LLM-native integrations. Discover the future of AI connectivity. ### [A more flexible Pro plan for modern teams](/blog/new-pro-pricing-plan) Published: 2025-09-09 Category: Company News We’re updating Vercel’s Pro plan to better align with how modern teams collaborate and how applications consume infrastructure, and how workloads are changing shape with AI. ### [Critical npm supply chain attack response – September 8, 2025](/blog/critical-npm-supply-chain-attack-response-september-8-2025) Published: 2025-09-08 Category: Security How Vercel responded to the September 2025 npm supply chain attack on chalk, debug and 16 other packages. Incident timeline, impact analysis, and customer remediation. ### [Stress testing Biome's noFloatingPromises lint rule](/blog/stress-testing-biomes-nofloatingpromises-lint-rule) Published: 2025-09-04 Category: Field Engineering We partnered with Biome to push their noFloatingPromises lint rule to the limit, uncovering edge cases and showing how we solve hard problems together. ### [Open SDK strategy](/blog/open-sdk-strategy) Published: 2025-09-03 Vercel’s Open SDK strategy commits to building frameworks, SDKs, and tools in the open, under permissive licenses. Learn how we’re avoiding lock-in, ensuring portability, and investing in open source to build a better web for everyone. ### [Preparing for the worst: Our core database failover test](/blog/preparing-for-the-worst-our-core-database-failover-test) Published: 2025-08-28 Category: Field Engineering On July 24, 2025, we successfully performed a full production failover of our core control-plane database from Azure West US to East US 2 with zero customer impact. ### [AI-powered prototyping with design systems](/blog/ai-powered-prototyping-with-design-systems) Published: 2025-08-22 Category: v0 Why AI-native design systems unlock true brand-ready, production-aligned prototyping for teams using v0 ### [AI Gateway: Production-ready reliability for your AI apps](/blog/ai-gateway-is-now-generally-available) Published: 2025-08-21 AI Gateway, now generally available, ensures availability when a provider fails, avoiding low rate limits and providing consistent reliability for AI workloads. ### [Rethinking prototyping, requirements, and project delivery at Code and Theory](/blog/rethinking-prototyping-requirements-and-project-delivery-at-code-and-theory) Published: 2025-08-20 Category: Customer stories How the agency, Code and Theory, cuts time-to-prototype by 75% and moves faster from idea to execution ### [