How the GitHub legal team used Copilot CLI to streamline their workflows
Learn how to build tools to simplify how you work—without writing a single line of code.
Turn one giant AI-generated pull request to a reviewable stack
Instead of one huge, un-reviewable pull request, teach coding agents to decompose work into a clean, ordered stack with GitHub stacked pull requests.
GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model
Meta’s Generative Ads Recommendation Model (GEM), the foundation model behind ads recommendations across Instagram and Facebook, now trains at LLM scale on several thousand of the latest-generation GPUs. This post goes into the details on how we achieved: doubling end-to-end (E2E) training efficiency to 20–25% Model FLOPs Utilization (MFU) while scaling training FLOPs 4x in […]
AI fluency isn't the finish line
Ninety percent of product builders say AI skills are essential to their future success. But what if we’re focused on the wrong ones?
Stacked sessions and pull requests in the GitHub Copilot app
Learn how I modernized an old codebase of mine using stacked sessions and pull requests in the GitHub Copilot app.
Introducing the new Vercel Agent
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
The Bull And Bear Case For Digital Design In The Age Of AI — Smashing Magazine
As AI reshapes product design, it could give designers greater autonomy or expose the gaps that autonomy makes harder to hide. Exploring both the bull and bear cases, Andy Budd examines what happens when designers need less permission to act.
Thinking Outside The Box: Digital Design In The AI Era — Smashing Magazine
Many of the AI tools we interact with take the form of text boxes. But what if there was a different way to interact with AI? Oleksii Hrzhehorzhevskyi explores a different approach to creating a new AI assistant and how designers can navigate the field as AI continues to change it.
The harness is all you need (mostly)
A practical GitHub Copilot workflow for prototyping, planning, implementing, and reviewing software without chasing every new AI tool.
GitHub Copilot app for Beginners: Getting started
New to the GitHub Copilot app? Learn how to start projects, work with AI agents, explore canvases, and streamline your development workflow.
Nick Bogaty joins Vercel as Chief Revenue Officer
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.
Copilot vs. raw API access: What are you actually paying for?
Copilot now bills usage at listed API rates. Compare direct model access with the coding workflow, policy, and harness work around it.
How to build interactive experiences with canvases
Canvases turn AI into interactive workspaces where you can visualize information, explore workflows, and take action across complex tasks.
How our universal content processing platform Riviera evolved for AI and beyond
Riviera is the Dropbox content processing platform that’s been iteratively improving content transformation in our products for roughly a decade.
In-House LLM Serving at Netflix
The Archaeologist’s Copilot
This article explains the approach I used to modernize a Java 1.5 codebase that no longer built reliably on modern machines. My early use of LLMs gave me plausible answers that did not hold up in the codebase. Progress came when I grounded the process in evidence, using AI to support analysis, validation in a stable Docker environment, and gradual refactoring protected by tests. The main takeaway
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Hierarchical Interest Representation is a research area for Meta Ads. We’re exploring an upstream representation layer over the universe of Ads entities – users, advertisers, products, services – learning unified embeddings that connect users’ inferred interests with the breadth of what advertisers offer in their deep funnel ads. The innovations in Hierarchical Interest Representation are […] Read
No, People Don’t Want More AI In Their Life — Smashing Magazine
Many companies assume everyone craves new AI features. But the reality is that most people don
Modernizing the Meta Ads Service With an Open-Source Kernel Scheduler
TL; DR At Meta’s scale, a few milliseconds of latency degradation can have a significant negative impact on ads performance. When a Linux kernel upgrade risked regressing latency across Meta’s ad serving fleet, we turned to sched_ext — the upstream, BPF-based extensible scheduling framework — to build a scheduling policy customized to the Ads delivery […]
Open-weight models surge to 29% of volume, price per token flattens
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%
Better tools made Copilot code review worse. Here’s how we actually improved it.
How migrating Copilot code review to shared Unix-style code exploration tools reduced review cost by reshaping agent workflows around pull request evidence.
Why we cannot wait for better post-quantum signature algorithms
NIST is advancing nine new post-quantum signature algorithms as potential candidates for future standardization. We take a closer look at all of them, and argue that while they are in the works and show great potential, we should use ML-DSA for now — the best one currently available.
Automating cross-repo documentation with GitHub Agentic Workflows
Explore how the Aspire team turns merged product changes into SME-reviewed docs pull requests, closing the gap between release and documentation.
How GitHub Copilot enables zero DNS configuration for GitHub Pages
Go from an empty repository to a live custom domain with HTTPS in about 14 minutes, without manually editing a single DNS record.
Users Don’t Need More Tools: They Need Seamless Integrations — Smashing Magazine
A closer look at why users don’t need more tools in their daily lives. What they need are seamless integrations of useful features to match already existing, established mental models. Brought to you by Design Patterns For AI Interfaces, **friendly video course on UX** and design patterns by Vitaly.
Matching AI Modality To User Intent: Designing The Right Interface — Smashing Magazine
We’ve fallen into conversational tunnel vision, defaulting every AI capability into a chat-based interface simply because LLMs are trained on dialogue data. But great UX is about matching modality to users’ context, intent, and cognitive load, so the interface adapts to the user, not the other way around.
Vercel Agent can now run AI investigations
Vercel Agent Investigation intelligently conducts incident response investigations to alert, analyze, and suggest remediation steps
7 AI features you can add to your app today
Discover how AI is transforming businesses with Vercel. Learn about easy LLM integration, 7 game-changing applications, and how to implement AI features to boost user experience and growth.
Building secure AI agents
Learn how to design secure AI agents that resist prompt injection attacks. Understand tool scoping, input validation, and output sanitization strategies to protect LLM-powered systems.
v0.dev -> v0.app
v0.dev is now v0.app, the AI builder for everyone: founders, designers, developers, marketers, sales, finance, and more
Meet the 2026 Vercel AI Accelerator Cohort
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 to become an AI engineering company
The question isn’t if AI will transform your business, but how to use it to maintain your competitive edge. Vercel CTO Malte Ubl shows how companies can understand AI’s fundamental shifts, adapt their skills, and integrate AI into their businesses.
Building efficient MCP servers
MCP is becoming the standard for building AI model integrations. See how you can use Vercel's open-source MCP adapter to quickly build your own MCP server, like the teams at Zapier, Composio, and Solana.
Agent responsibly
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.
Use Perplexity Web Search with Vercel AI Gateway
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.
How Mux shipped durable video workflows with their @mux/ai SDK
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.
Proposal for inline LLM instructions in HTML based on llms.txt
llms.txt is an emerging standard for making content such as docs available for direct consumption by AIs. We’re proposing a convention to include such content directly in HTML responses.
Introducing x402-mcp: Open protocol payments for MCP tools
We built x402-mcp to integrate x402 payments with Model Context Protocol (MCP) servers and the Vercel AI SDK.
Towards the AI Cloud: Our Series F
Today, Vercel announced an important milestone: a Series F funding round valuing our company at $9.3 billion.
Grep a million GitHub repositories via MCP
Search 1M+ GitHub repositories from your AI agent using Grep's MCP server. Your agent can now reference coding patterns and solutions used in open source projects to solve problems.
If agents are building your app, who gets the W-2?
If agents can design, build, test, and deploy features, their work should be treated like a developer's under GAAP. With modern AI logging, you can tie usage directly to capitalizable development activity.
What we learned building agents at Vercel
We're presenting a simple methodology for discovering successful agent projects that perform well with current generation AI
Vercel Ship AI 2025 recap
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.
Video Generation with AI Gateway
Build video generation into your apps with AI Gateway. Create product videos, dynamic content, and marketing assets at scale.
Zero Data Retention on AI Gateway
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.
How Vercel's adapting SEO for LLMs and AI search
AI is changing how content gets discovered. Now, SEO ranking ≠ LLM visibility. No one has all the answers, but here's how we're adapting our approach to SEO for LLMs and AI search.
Introducing Vercel Agent: Your new Vercel teammate
Vercel Agent provides AI-powered code reviews and production investigations, delivering accurate, context-aware insights to help you ship reliable software.
Unified reporting for all AI Gateway usage
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.
Fluid compute: How we built serverless servers
Fluid Compute cuts cold starts and compute costs by up to 95%, scaling I/O-bound and AI workloads efficiently across 45B+ weekly requests.
The AI Cloud: A unified platform for AI workloads
We made it simple to build, preview, and ship any frontend, from marketing pages to dynamic apps, without managing infrastructure. Now we’re introducing the next layer: the Vercel AI Cloud.
Fluid compute: Evolving serverless for AI workloads
Fluid, our newly announced compute model, eliminates wasted compute by maximizing resource efficiency. Instead of launching a new function for every request, it intelligently reuses available capacity, ensuring that compute isn’t sitting idle.
Building AI-Generated Pixel Trading Cards with Vercel AI Gateway
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.
AI Gateway production index
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.
Making AI search smarter
Search is how we find nearly everything on the web — creators, merchants, answers. AI is rewriting the rules, leaving creators caught between staying discoverable in an agentic era and getting paid for their work. Today we're launching two initiatives to help.
Your site, your rules: new AI traffic options for all customers
For our second Content Independence Day, we’re giving website owners finer options to manage AI traffic. Instead of a one-size-fits-all block, all customers can now easily distinguish and manage Search, Agent, and Training bots, alongside the new ability to protect ad-monetized pages.
Content Independence Day, one year on- building the business model for the agentic Internet
One year after declaring Content Independence Day, a dynamic market for monetized content has officially emerged. In this report, we examine how the rise of autonomous AI agents is upending traditional search referrals and detail the new infrastructure required to support a sustainable web economy.
Agentic test processes, LLM benchmarks, and other notes on agentic coding from Galapagos Island
Trust you can verify: Figma is now ISO 42001 certified
Saying you use AI responsibly is easy, but proving it to an accredited auditor is harder. We decided that was a standard worth meeting.
10 Years of Meta’s Commitment to Python
This year marks Meta’s 10th consecutive year as a sponsor of the Python Software Foundation (PSF), the charitable organization dedicated to advancing, supporting, and protecting the open-source Python programming language and the community that sustains it. Python is one of the world’s most influential programming languages, and we use it across our engineering stack, from […]
