
Kitesurf is now open source
Kitesurf, our experimental browser engine for AI agents, is now open source. Inspect the code, run it locally, or deploy your own instance on Cloudflare Workers.
1,015 articles on AI & ML.

From autofill to AI agent approvals, every 1Password interaction counts. Here's how the design team uses Figma Make to design moments users trust.

Kitesurf, our experimental browser engine for AI agents, is now open source. Inspect the code, run it locally, or deploy your own instance on Cloudflare Workers.

Which parts of the creative process can AI do for us—and which do we insist on keeping for ourselves?

Agent skills capture repeatable engineering work in files teams can review and reuse, while tools, project context, and permissions remain specific to the host that runs them.

An AI feature can save users time on a task, only for them to spend it checking the results. This practical audit helps product teams decide where AI earns its place and what users need to verify its output.

Automated testing in the age of AI coding assistants is problematic: when AI agents write both production and test code, developers risk losing the assurance that automated tests protect against functional errors. I make three claims: (1) when AI writes the code, developers become its customers; (2) therefore customer tests, not developer tests, become the primary contract between humans and AI; (

Ads ranking models are growing toward LLM scale faster than the hardware to run them can keep up. An extra unit of compute has more impact on some ad requests, models, and chips than on others. The challenge is deciding where to allocate it to get the best outcome for the entire system. We built [...] Read More... The post Intelligent Delivery: Making Every Unit of Compute Serve Better Ads appeare

How we train and serve a shared generative model for personalized search and recommendation at Shopify scale.

Your algorithm is a suite of AI-powered tools that makes Facebook recommendations more transparent and steerable, with a single editable view of the interests that shape Feed and Reels. We’re sharing how Your algorithm turns people’s natural language preferences into responsive recommendations, and how LLMs are tailored to specific tasks within the system. Traditionally, the [...] Read More... The

Almost every article or podcast about product management and AI refers to "the AI PM" as one job. But what...

On why design is the new code, shaping AI’s creative output, and the human vision and judgment behind what we make.

Writing code got faster. The work around it didn't. See how you can plan, write code, review changes, and investigate production issues with GitHub Copilot, and what work still needs your judgment.

AI agents act for millions, but servers see intermediaries that strip user visibility. This post defines the problem space and introduces a collaborative approach to safely identifying, allowing, and managing this automated traffic.

Two side projects explored a new way to get work done with files already in Dropbox. Here’s how engineers brought them together and turned those experiments into a new customer experience.

From sharing features across web and desktop to testing the details customers depend on, this is how AI-assisted development helped our engineers deliver the updated Dropbox experience.

As LLM chat patterns become more widespread, making them accessible is essential to ensuring everyone can access the information, tools, and opportunities they offer. Drawing on his work improving these interfaces, Eric Bailey shares practical ways to make chat-based experiences on the web more accessible and usable for people who rely on assistive technology.

Personal AI agents have changed how users interact with the web, blurring the lines between automated and human traffic. Learn how Cloudflare gives site owners visibility and control to manage personal agent access.

The AI 2027 Conference is a live online day for designers and engineers on where AI stands today, what to expect in 2027, and where teams are getting it right. Smashing AI Conference originally handwritten and published with love on CSS-Tricks . You should really get the newsletter as well.

Facebook Feature Framework (F3) is Meta’s framework for authoring, compiling, and serving the machine learning features underlying ads ranking models, where a single request can require more than 20,000 features. We first presented F3 at AI @ Scale 2020. F3 reduced execution computational costs by compiling all features into a single merged graph, but that [...] Read More... The post F3 Lightning:

When we looked at how well agents used test/verification techniques in August 1 , we saw that GPT-5.6 Sol generally did what you might call a caricature of various techniques when asked to use a technique or library such as TDD, QuickCheck, Lean 4, etc.; not specifying any particular test method (which we'll call Default) resulted in many worthless unit tests, which was one of the best performing

AI can help us create almost anything now. But from icons and NFTs to art installations and fashion design, it's still up to the maker to deliver something that resonates.


Over the last year we’ve been sharing our work leveraging large language models to catch bugs on the fly — a novel approach we call Catching Just-in-Time Tests (JiTTests). Now, we’re sharing the results and positive impact we’ve seen with Catching JiTTests deployed into production. Our paper, “Just-in-Time Catching Test Generation at Meta,” fully details [...] Read More... The post Catching Bugs B

This post describes the next generation of Meta Andromeda, Meta’s personalized ads retrieval engine, and how co-designing the model, system, and GPU hardware unlocks a new efficiency frontier for ads retrieval. In production, the system scores every eligible ad with near ranking-level model performance at retrieval scale and surfaces the top candidates at over one [...] Read More... The post Meta




Since early this year, Michael Malis (of pgrust ) has been showing me interesting things he's done and saying [W]e should be more ambitious 1 with the software we build There is, understandably, a lot of skepticism about projects like pgrust because there are so many low-quality AI-generated projects out there. If I didn't know Malis and didn't look into it, I would just assume that pgrust was ano

We built Remote Dev so AI agents can build and test apps in parallel, without maxing out developers’ laptops.

Almost 100,000 Commerce.com domains now give AI agents real shopping tools through WebMCP on Cloudflare. Here's how we turned it on across every store at once, while keeping each merchant in control.

Three Java Champions share how they use GitHub Copilot to solve problems, accelerate development, and keep humans responsible for the results.

When our AI code reviewer's cost per run doubled, we dug into the token usage to find out why. Learn how we used prompt caching and intelligent model routing to slash our inference bill by 68% while speeding up reviews.

Clairic is a new model from Cloudflare that is a System One extraction modeI, capable of extracting, computing, estimating, and forecasting data from unstructured inputs.

Learn how to move an agent session from the GitHub Copilot app into VS Code without losing the conversation, code changes, or working context.

Generative Recommenders (GenRecs) represent a paradigm shift from scoring every ad to reasoning about ad content and user preferences together in order to predict the best outcome for advertisers. Leveraging the world knowledge built into LLMs makes ad matching more intelligent and precise, compounding gains for advertisers. GenRecs Tokenization is the foundational data representation that [...] R

Sometimes, giving an AI agent all of the knowledge it needs is the wrong approach. At Meta, we’ve seen notable improvements in efficiency and accuracy by keeping the orchestration layer of our data pipeline agents deliberately thin: It routes work and enforces reliability checks, while specialized agents do the domain reasoning. We’re sharing our own [...] Read More... The post The Thin Orchestrat

Identity alone doesn't guarantee a bot will behave responsibly. We are introducing a system to continuously evaluate whether Verified bots honor site preferences, like robots.txt and HTTP 429s, ensuring they remain accountable over time.

What can digital transformation teach us about AI adoption? Paul Boag revisits his book Digital Adaptation to show how lessons from the past can help organizations navigate the challenges of AI today. - AI - Workflow - Business

At Spotify, every surface and interaction is personalized to you as a user: the content on the Home page, the...

How Cloudflare and OpenAI are working together to help AI find useful content, keep up with changes, and make fewer wasted requests — making the experience better for users and website owners alike.

AI, agents, voice, and physical controls are shifting software development from operating tools to expressing intent—and helping developers stay focused on building.

While death by PowerPoint has been a much-talked-about phenomenon for decades, collaborative slideware and AI have elevated slideuments, Frankendecks and the resulting poor presentations to epidemic proportions. This article introduces a new series focusing on how knowledge workers can make effective presentations.


GitHub’s context-aware secret classifier improves detection quality, raises weighted acceptance by 11.5%, and reduces median scan execution time by 86%.

Last year, we introduced GEM, the industry’s largest recommendation system (RecSys) foundation model. GEM established Meta’s first LLM-inspired paradigm for ads recommendation, driving major performance gains. Building on this foundation, our next goal is to further scale both compute and intelligence transfer with next-generation hardware, and expand this capability across Meta’s entire ads ecosy

Leaders at Monetize 2026 shared the biggest shifts reshaping AI monetization, from hybrid pricing and stronger spend controls to flexible packaging, outcome-focused finance, and pricing built for human and AI buyers.

Learn how to add custom instructions and skills to your repository, use custom agents, and connect MCP servers like Playwright.

At Meta, we’ve built a system that enhances ads recommendations by leveraging idle inference capacity in our fleet. Two elasticity levers in the system allow ads recommendation work to expand across opportunistic capacity, without compromising baseline performance. This post describes how we designed and now operate the system at Meta’s scale and how it drives [...] Read More... The post Turning O

Here are four ways teams at Figma, Mercari, Atlassian, and Sephora are making it easier for people to drive real value with AI.

We are expanding the Clef decision model family with Clef-omni, natively processing audio, video, images, and text in a single pipeline. We’ve also lowered Clef-flash pricing and boosted Clef inference speeds by up to 2.0x.

How do you drive AI adoption and make better decisions about what to build?

Developers aren’t becoming more careless; they’re being outpaced. The tools that let developers create more software should also take on more of the work of protecting it.

We’re launching ReviewBench, a benchmark for code review agents built on representative GitHub pull requests, multi-source ground truth, calibrated evaluation, and production-aligned metrics.

Cloudflare AI Gateway now supports native web search API integration in partnership with Ceramic.ai, Exa, and Linkup. Developers can now inject real-time web context into model inference calls via AI Gateway, REST APIs, or Workers bindings.

Some of the world's leading organizations are building the future of non-profit work with Cloudflare.

Learn three ways to get noticed and grow your career as AI reshapes how developers build software.

We are introducing Clef and Clef-flash, open-source decision models hosted on Workers AI for high-speed classification and agentic workflows. Also launching: a new reinforcement learning platform that allows developers to fine-tune decision models using their own data.

AI sovereignty is not a zero-sum game, but many governments now believe it is. Cloudflare's answer: more local open-source models, model-agnostic security tools, and a commitment to giving nations genuine choice.

Cloudflare OS gives everyone in your organization an agent workspace that knows how your company works and connects to its data and systems. We’re opening the waitlist for fully managed deployments that you’ll be able to launch in a few clicks.

Cloudflare is hosting a competition to see who will build the next Git platform for an era of AI agents. Artifacts is in open beta, with Workers bindings, data jurisdiction controls, and event subscriptions for repository changes.