Under the hood: Exploring the AI models powering GitHub Copilot
Learn how GitHub Copilot’s evolving models and infrastructure center developer choice and power agentic workflows.
Prompting Is A Design Act: How To Brief, Guide And Iterate With AI — Smashing Magazine
Prompting is more than giving AI some instructions. You could think of it as a design act, part creative brief and part conversation design. This second article on AI augmenting design work introduces a designerly approach to prompting: one that blends creative briefing, interaction design, and structural clarity.
Evaluating image segmentation models for background removal for Images
An inside look at how the Images team compared dichotomous image segmentation models to identify and isolate subjects in an image from the background.
Make Your Website Conversational for People and Agents with NLWeb and AutoRAG
Bring conversational search to your website so people and AI agents can ask natural language questions and get direct answers. With NLWeb, an open project by Microsoft, and Cloudflare AutoRAG, conversational search is now a one-click setup for your website.
A deeper look at AI crawlers: breaking down traffic by purpose and industry
We are extending AI-related insights on Cloudflare Radar with new industry-focused data and a breakdown of bot traffic by purpose, such as training or user action. These new views help website owners better understand the impact of AI crawlers.
The age of agents: cryptographically recognizing agent traffic
Cloudflare now lets websites and bot creators use Web Bot Auth to segment agents from verified bots, making it easier for customers to allow or disallow the many types of user and partner directed bots the explosion of AI agents has created.
The next step for content creators in working with AI bots: Introducing AI Crawl Control
Cloudflare launches AI Crawl Control (formerly AI Audit) and introduces easily customizable 402 HTTP responses. Instead of blocking crawlers outright, content creators can now send "Payment Required" responses with custom messages, creating direct communication channels for AI partnerships.
From Black Box to Blueprint
A common enterprise problem: crucial legacy systems become “black boxes”—key to operations but opaque and risky to touch. We worked with a client to use AI-assisted reverse engineering to reconstruct functional specifications from UI elements, binaries, and data lineage to overcome analysis paralysis. We developed a methodical “multi-lens” approach—starting from visible artifacts, enriching increm
Some thoughts on LLMs and Software Development
I’m about to head away from looking after this site for a few weeks (part vacation, part work stuff). As I contemplate some weeks away from the daily routine, I feel an urge to share some scattered thoughts about the state of LLMs and AI.
How GitHub Models can help open source maintainers focus on what matters
Learn how GitHub Models helps open source maintainers automate repetitive tasks like issue triage, duplicate detection, and contributor onboarding — saving hours each week.
How we accelerated Secret Protection engineering with Copilot
Learn how the Secret Protection engineering team collaborated with GitHub Copilot coding agent to expand validity check coverage.
Preparing for the worst: Our core database failover test
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 Gateway now gives you access to your favorite AI models, dynamic routing and more — through just one endpoint
AI Gateway simplifies AI app development with unified billing, secure key storage, and dynamic routing. Gain observability and control over costs, API keys, and traffic, connecting to major AI providers through a single endpoint.
How Cloudflare runs more AI models on fewer GPUs: A technical deep-dive
In order to support a growing catalog of AI models while maximizing GPU utilization, Cloudflare built an internal platform called Omni. This platform uses lightweight isolation and memory over-commitment to run multiple AI models on a single GPU, allowing us to serve inference requests closer to users and improve overall availability across our network.
How we built the most efficient inference engine for Cloudflare’s network
Existing LLM serving engines aren’t efficient enough when deployed across a globally distributed network, so we built our own, in Rust. Infire is an LLM inference engine that employs a range of techniques to maximize resource utilization, allowing us to serve AI models more efficiently and with better performance for Cloudflare workloads.
State-of-the-art image generation Leonardo models and text-to-speech Deepgram models now available in Workers AI
We're expanding Workers AI with new partner models from Leonardo.Ai and Deepgram. Start using state-of-the-art image generation models from Leonardo (Phoenix, Lucid Origin) and real-time TTS and STT models from Deepgram (Nova 3, Aura 1). Build full-stack, low-latency AI applications, all hosted on Cloudflare's global network.
Research, Review, Rebuild
The Bahmni open-source hospital management system started over nine years ago with a front end using AngularJS and an OpenMRS REST API. We wished to convert this to use a React + TypeScript front end with an HL7 FHIR API. In exploring how to do this modernization we used a structured prompting workflow of Research, Review, and Rebuild - together with Cline, Claude 3.5 Sonnet, Atlassian MCP server,
Building your own CLI Coding Agent with Pydantic-AI
CLI coding agents are a fundamentally different tool to chatbots or autocomplete tools - they're agents that can read code, run tests, and update a codebase. While commercial tools are impressive, they don't understand the particular context of our environment and the eccentricities of our specific project. Instead we can build our own coding agent by assembling open source tools, using our specif
How to use GitHub Copilot on github.com: A power user’s guide
Explore how to use GitHub Copilot on github.com to automate tasks, assign agents, prototype ideas, and streamline your entire workflow — all without an IDE.
Designing For TV: The Evergreen Pattern That Shapes TV Experiences (Part 1) — Smashing Magazine
TV interface design is a unique, fascinating, and often overlooked field. It’s been guided by decades of evolution and innovation, yet still firmly constrained by its legacy. Follow Milan into the history, quirks, and unshakable rules that dictate how we control these devices.
Introducing Cloudflare Application Confidence Score For AI Applications
Cloudflare will provide confidence scores within our application library for Gen AI applications, allowing customers to assess their risk for employees using shadow IT.
ChatGPT, Claude, & Gemini security scanning with Cloudflare CASB
GenAI tools bring power — and risk. Cloudflare CASB now scans ChatGPT, Claude, and Gemini for misconfigurations, sensitive data exposure, and compliance issues, helping organizations adopt AI with confidence.
Best Practices for Securing Generative AI with SASE
This guide provides best practices for Security and IT leaders to securely adopt generative AI using Cloudflare’s SASE architecture as part of a strategy for AI Security Posture Management (AI-SPM).
Securing the AI Revolution: Introducing Cloudflare MCP Server Portals
We’re excited to announce Cloudflare MCP Server Portals are now available in Open Beta. MCP Server Portals are a new capability that enable you to centralize, secure, and observe every MCP connection in your organization. This feature is part of Cloudflare One, our secure access service edge (SASE) platform that helps connect and protect your workspace.
