Introducing the AI Gateway
With the AI Gateway, build with any model instantly. No API keys, no configuration, no vendor lock-in.
GitHub Copilot: Meet the new coding agent
Implementing features has never been easier: Just assign a task or issue to Copilot. It runs in the background with GitHub Actions and submits its work as a pull request.
Vibe coding: Your roadmap to becoming an AI developer
Learn how to go from curious coder to AI wizard—with a little help from GitHub.
Double click: Does efficiency kill love?
At Config 2025, we were in our feelings about AI—but not in the ways you’d expect. This time around, the buzz was around building connection and care.
GitHub for Beginners: Building a React App with GitHub Copilot
Follow along and build a frontend client using React and Copilot Chat.
Real‑world video demo: Using different AI models in GitHub Copilot
Curious about how AI models perform in real-world scenarios with GitHub Copilot? Same. We made a live video demo to find out, and wrote up our key takeaways.
Accelerating GPU indexes in Faiss with NVIDIA cuVS
Meta and NVIDIA collaborated to accelerate vector search on GPUs by integrating NVIDIA cuVS into Faiss v1.10, Meta’s open source library for similarity search. This new implementation of cuVS will be more performant than classic GPU-accelerated search in some areas. For inverted file (IVF) indexing, NVIDIA cuVS outperforms classical GPU-accelerated IVF build times by up […]
Evolution of Product Classification at Shopify: From Categories to Comprehensive Product Understanding (2025) - Shopify
Shopify’s product classification system has evolved from basic categorization to an AI-driven framework using Vision Language Models and the Shopify Product Taxonomy. It accurately classifies products, extracts attributes, and processes over 30 million predictions daily, improving search, discovery, trust, and efficiency.
Config 2025 launches deepen Figma’s design capabilities as its platform expands
Doubles product offering with new design and AI-powered features to help teams go from idea to product, all in one place
Function calling using LLMs
While LLMs excel at generating cogent text based on their training data, they may also need to interact with external systems. Function calling allows them to construct such calls. The LLM does not execute these calls directly, instead it creates a data structure that describes the call, passing that to a separate program for execution and further processing. The LLM's prompt includes details abou
Join the Vercel AI Accelerator
A six-week program to help you scale your AI company offering over $4M in credits from Vercel, v0, AWS, and leading AI platforms
How Headspace built an AI companion that fosters trust and transparency
Creating an AI-powered feature for mental health poses myriad challenges. Here, the product and brand teams talk through how they built Ebb with care and sensitivity.
Copilot ask, edit, and agent modes: What they do and when to use them
An introduction to the three distinct modes of GitHub Copilot and a practical guide for integrating them effectively into your workflow.
MCP Demo Day: How 10 leading AI companies built MCP servers on Cloudflare
We’re teaming up with Anthropic, Asana, Atlassian, Block, Intercom, Linear, PayPal, Sentry, Stripe, and Webflow to launch new remote MCP servers, built on Cloudflare, to enable Claude users to manage
The AI-powered DevOps revolution: Redefining developer collaboration
Collaboration is crucial to successful software delivery. Let’s dive into how AI can help your development teams decrease their time to delivery, and foster better communication and collaboration using GitHub Copilot.
Bringing streamable HTTP transport and Python language support to MCP servers
We're continuing to make it easier for developers to bring their services into the AI ecosystem with the Model Context Protocol (MCP) with two new updates: support for the new Streamable HTTP transport in remote MCP servers and the ability to deploy Python-based MCP servers using FastAPI-MCP.
Introducing AutoPatchBench: A Benchmark for AI-Powered Security Fixes
We are introducing AutoPatchBench, a benchmark for the automated repair of vulnerabilities identified through fuzzing. By providing a standardized benchmark, AutoPatchBench enables researchers and practitioners to objectively evaluate and compare the effectiveness of various AI program repair systems. This initiative facilitates the development of more robust security solutions, and also encourage
GitHub for Beginners: Building a REST API with Copilot
See how you can use GitHub Copilot to build an API.
Figma's 2025 AI report: Perspectives from designers and developers
Figma’s AI report tells us how designers and developers are navigating the changing landscape.
A guide to deciding what AI model to use in GitHub Copilot
What to look for with each model and how to test them in your workflows—with tips, tricks, and pointers.
Cannes: How ML saves us $1.7M a year on document previews
Optimizing payments with machine learning
Accelerating our A/B experiments with machine learning
Is this a date? Using ML to identify date formats in file names
Putting everything in its right place with ML-powered file organization
Smart move uses machine learning to analyze a user’s existing subfolder structure and suggest folders where they might want to move their files. Here's how the feature was built.
Bringing AI-powered answers and summaries to file previews on the web
From AI to sustainability, why our latest data centers use 400G networking
From prompt to production: Building a landing page with Copilot agent mode
See how I built a developer-focused landing page in under 30 minutes using GitHub Copilot agent mode and Claude 3.5 Sonnet—with just screenshots and prompts.
Which AI model should I use with GitHub Copilot?
Ever wondered which AI model is the best fit for your GitHub Copilot project? Here are some things to consider.
Inclusive Dark Mode: Designing Accessible Dark Themes For All Users — Smashing Magazine
Dark mode isn’t just a trendy aesthetic. It’s a gateway to more inclusive digital experiences, but only if designed thoughtfully. Discover how to craft dark modes that don’t just look good but work for everyone, from those with light sensitivity to machine learning algorithms.
GitHub for Beginners: Security best practices with GitHub Copilot
Learn how to leverage GitHub Copilot to make your code more secure.
The Post-Developer Era
When OpenAI released GPT-4 back in March 2023, they kickstarted the AI revolution. The consensus online was that front-end development jobs would be totally eliminated within a year or two.Well, it’s been more than two years since then, and I thought it was worth revisiting some of those early predictions, and seeing if we can glean any insights about where things are headed.
Startup spotlight: building AI agents and accelerating innovation with Cohort #5
Explore how developers are using Cloudflare to scale AI workloads and streamline automation. Learn more about what our participants in Workers Launchpad Cohort #4 have built, and check out the latest startups participating in Cohort #5.
What the heck is MCP and why is everyone talking about it?
Everyone’s talking about MCP these days when it comes to large language models (LLMs)—here’s what you need to know.
The next chapter: EpicAI.pro
What I'm working on with AI education and why I think it's the future.
Introducing Chatbot Template
Chatbot is a free, open-source template, powered by Next.js and the AI SDK, that helps you build chatbot applications.
Double click: You can just do things—but should you always?
The catchphrase is catching fire as early adopters ride the new wave of AI-powered tools. Here’s how we might channel that energy and avoid the risk of being overwhelmed.
Introducing AutoRAG: fully managed Retrieval-Augmented Generation on Cloudflare
AutoRAG is here: fully managed Retrieval-Augmented Generation (RAG) pipelines powered by Cloudflare's global network and powerful developer ecosystem. Simplify how you build and scale RAG pipelines to power your context-aware AI chatbots and search applications.
Vibe coding with GitHub Copilot: Agent mode and MCP support rolling out to all VS Code users
In celebration of MSFT’s 50th anniversary, we’re rolling out Agent Mode with MCP support to all VS Code users. We are also announcing the new GitHub Copilot Pro+ plan w/ premium requests, the general availability of models from Anthropic, Google, and OpenAI, next edit suggestions for code completions & the Copilot code review agent.
Meta Open Source: 2024 by the numbers
Open source has played an essential role in the tech industry and beyond. Whether in the AI/ML, web, or mobile space, our open source community grew and evolved while connecting people worldwide. At Meta Open Source, 2024 was a year of growth and transformation. Our open source initiatives addressed the evolving needs and challenges of […]
GitHub for Beginners: How to get LLMs to do what you want
Learn how to write effective prompts and troubleshoot results in this installment of our GitHub for Beginners series.
How To Argue Against AI-First Research — Smashing Magazine
Companies have been turning their attention to “synthetic,” AI-driven user testing. However, as convenient as it might seem, it’s dangerous, expensive, and usually diminishes user value. Let’s take a closer look at why exactly it is problematic and how we can argue against it to make a case for UX research with real users. Part of [Smart Interface Design Patterns](https://smart-interface-design-pa
Using AI to create dynamic, risk-based Radar rules
Last month, we improved our AI tooling to give you even more flexibility when combating fraud. Now, Radar’s new rules combine our machine learning models with the issuer’s CVC and postal code response in real time.
How Stripe is using AI to create personalized checkout experiences
The Optimized Checkout Suite uses AI to personalize the checkout experience—dynamically adjusting everything from payment method ordering to fraud interventions in order to maximize conversion and boost revenue.
Mastering GitHub Copilot: When to use AI agent mode
Discover the differences between agent mode and Copilot Edits with GitHub Copilot—and when to use them in your workflows.
AI SDK 4.2
AI SDK 4.2 introduces MCP clients, reasoning, image generation with language models, message parts, sources, and more
Introducing Cloudy, Cloudflare’s AI agent for simplifying complex configurations
Cloudflare’s first AI agent, Cloudy, helps make complicated configurations easy to understand for Cloudflare administrators.
World Water Day: how GitHub Copilot is helping bring clean water to communities
From simplifying the workflow of a developer to having an impact on the global water crisis, technology and AI are reshaping the way charity: water works.
xAI and Vercel partner to bring zero-friction AI to developers
Vercel partners with xAI to bring Grok models directly to your Vercel projects through the Vercel Marketplace—and soon v0—with no additional signup required. xAI adds a new free tier through Vercel to enable quick prototyping and experimentation.
How we train AI to uncover malicious JavaScript intent and make web surfing safer
Learn more about how Cloudflare developed an AI model to uncover malicious JavaScript intent using a Graph Neural Network, from pre-processing data to inferencing at scale.This AI model is part of our Page Shield offering, helping make web surfing safer.
Trapping misbehaving bots in an AI Labyrinth
How Cloudflare uses generative AI to slow down, confuse, and waste the resources of AI Crawlers and other bots that don’t respect “no crawl” directives.
GitHub for Beginners: Essential features of GitHub Copilot
Get the most out of Copilot with code completion, inline chat, slash commands, Copilot code review, and more.
In Conversation: Dylan Field and Garry Tan on design, AI, and the power of “locking in”
Figma’s Dylan Field and YC’s Garry Tan discuss exploring the idea maze, vibe coding, and preserving craft even when the models are “cooking.”
Global expansion in Generative AI: a year of growth, newcomers, and attacks
This post examines which Generative AI services are more popular, new entrants into the space, how these services have grown in traffic, where that traffic originates, and the evolution of cyberattacks targeting these services.
How we built enterprise search to be secure and private
Many don’t know that “Slack” is in fact a backronym—it stands for “Searchable Log of all Communication and Knowledge”. And these days, it’s not just a searchable log: with Slack AI, Slack is now an intelligent log, leveraging the latest in generative AI to securely surface powerful, time-saving insights. We built Slack AI from the…
Not just for developers: How product and security teams can use GitHub Copilot
GitHub Copilot isn’t just for developers! Discover how product managers, security professionals, scrum masters, and more use GitHub Copilot to streamline tasks, automate workflows, and boost productivity across teams.
Finding leaked passwords with AI: How we built Copilot secret scanning
Passwords are notoriously difficult to detect with conventional programming approaches. AI can help us find passwords better because it understands context. This blog post will explore the technical challenges we faced with building the feature and the novel and creative ways we solved them.
Building multimodal AI for Ray-Ban Meta glasses
Multimodal AI – models capable of processing multiple different types of inputs like speech, text, and images – have been transforming user experiences in the wearables space. With our Ray-Ban Meta glasses, multimodal AI helps the glasses see what the wearer is seeing. This means anyone wearing Ray-Ban Meta glasses can ask them questions about […]
GitHub for Beginners: How to get started with GitHub Copilot
Get started with GitHub Copilot and navigate features like Copilot Chat in this installment of the GitHub for Beginners series.
