50 posts · 16 companies · newest first
Ryan is joined by Yanbing Li, Chief Product Officer at Datadog, to talk about applying observability to non-deterministic AI agents, blurring the boundaries between software development and production workflows, and navigating emerging challenges in AI security and tokenomics.
A maturity model for taking agents from an impressive demo to a system people can depend on — with a self-assessment and the map to a deep-dive on each layer.
Your service can be 100% up and still quietly approving the wrong things, burning its budget, or failing over into untested quality. Level 5 is the infrastructure that lets you see your decisions, bound your spend, route and fail over between models, kill bad behavior in seconds — and the platform that makes all of it possible.
Agents don't build trust for another reason, structurally worse than the first. It isn't only that the tool keeps changing shape. It's that the feedback loop you would need in order to learn the tool is broken at the point of measurement.
The level where an LLM system stops being a demo and earns the right to touch real data and real decisions: layered guardrails that fail closed, PII handled at the boundary, an immutable audit trail, and scoped memory. By the time an LLM system is making decisions that matter, “it usually works” is no longer the bar. This is Level 4 of the maturity model — safety and governance — and it’s where four disciplines that teams tend to bolt on late have to be designed in instead. They share one idea: don’t trust a single point to do the right thing. Layer independent guardrails so a miss at one is…
The most important number an agent produces isn’t its answer — it’s how sure it is. Compose that number from independent signals, check it’s calibrated, grade the high-stakes calls with a second model, and route the rest to humans well. This is Level 3 of a six-level maturity model for running LLM systems in production. Levels 1 and 2 got you to where the system works and you can see it working. Level 3 is confidence: the system acts on its own only when its calibrated confidence is high, grades the decisions that matter with an independent judge, and routes everything it’s unsure about to a…
If you can deploy a prompt change without an eval failing the build, you don’t have evals — you have a notebook. And once the gate is green, the slow leaks are still coming for you. Here’s the gate, the baseline, and the shadow-eval loop that catch both. This is Level 2 of the maturity model: evaluation. The principle is short — you don’t ship on hope, you ship on a gate, and then you watch for drift afterward. A gate protects the moment of deploy. Drift detection protects the weeks in between. You need both, and they’re built from different machinery. Most teams “do evals” the way they once…
The trick to putting LLM agents in high-stakes systems isn’t a smarter model — it’s containing the model to one node so the rest of the system is ordinary, testable code. Here are the structural moves, with the contracts and types to implement them. Demos love autonomous agents that loop, call tools, and “figure it out.” Production hates them. The moment an agent’s behavior depends on which path the model wandered down today, you can’t test it, can’t audit it, and can’t let it touch anything that matters. In a regulated or high-consequence system — money movement, healthcare, infrastructure —…
Coding agents are great for an afternoon and mediocre for a quarter. Here’s the small set of files and rules — with the actual configs — that keeps quality from decaying across months and thousands of edits, whether you run one agent or a fleet of them on the same repo.
At a Microsoft event in San Francisco on Wednesday, Jensen Huang and Satya Nadella outlined how NVIDIA and Microsoft are co-engineering hardware and software for AI agents to run on Windows PCs. NVIDIA was founded because of Windows, Huang said. Now AI agents are coming to Windows. “If you look at the entire journey of […]
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. The post Secret protection must scale with software appeared first on The GitHub Blog.
Last month, I built an AI agent that could search the web before answering a question. While working on the article around that project, I got another project idea and that was around the visibility of a website in the world of AI-powered search. The idea essentially revolves around the fact that whether the AI-powered search mentions your website in its answer or not or whether it cites your website as a source or not, and lastly, compare these resulst with the regular Google search results. Does your website show up when AI-powered search answers questions related to the topics it covers?…
Telecom operators are increasingly building their AI strategies on open models — and the reasons go beyond mere cost. Open models give telcos the ability to trust, control and customize AI across their most critical workloads — from autonomous networks to customer care. NVIDIA’s latest State of AI in Telecommunications report reflects this shift, with […]
Introduction Existing systems estimate user price sensitivity primarily from spending behavior or demographic proxies. They do not systematically account for residential property values, which can indicate a user’s financial circumstances. This omission creates three limitations: Limited property insights: Existing profiles do not account for property values. One-dimensional profiles: Users with similar spending patterns but different living standards receive the same classification. Regional variation: Manual classification does not adapt well to differences between property markets. This…
How I used GitHub Copilot and Lighthouse reports to improve my blog's performance, taking some of its worst pages from a score of 73 to 100.
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. The post ReviewBench: An open benchmark for AI code review appeared first on The GitHub Blog.
Breast cancer is the most commonly diagnosed cancer among American women — yet the gaps in care are wide. A majority of women over age 40 skip the recommended annual screening. Radiologists are reading more mammograms with fewer colleagues. And when a diagnosis arrives, the tests that inform treatment can take weeks to return results. […]
We celebrated our 16th birthday with 46 announcements across open source, post-quantum security, AI agents, and developer platform upgrades. Here’s a day-by-day roundup of everything we shipped.
My blog began as a blosxom (Perl) site running on a VPS. In 2011 I moved to the new GitHub Pages, with the site generated statically by Jekyll (Ruby) on a GitHub server. It was a no-brainer: easier, faster, and cheaper, better in every way. After 15 years of Jekyll, this week I replaced it with a new, custom-built static site generator, dubbed ssg, in “C with templates” C++20. The ~8KLoC source closely follows my personal coding style including templated arenas and slices, zero dependencies, and a libc-free core. It’s wicked fast, and a complete, cold generation of my blog takes 150ms on my…
Learn three ways to get noticed and grow your career as AI reshapes how developers build software. The post AI is rewriting the developer career ladder. Here’s how to stand out. appeared first on The GitHub Blog.
Local AI is becoming more useful by the token. As AI agents move from experiments into everyday development, increasingly capable open models are shrinking to fit on more devices, giving builders more to run locally. Coming this month, NVIDIA DGX Spark will be available with 64GB of unified memory from top manufacturer partners — Acer, […]
Ryan chats with Julien Verlaguet, CEO at Skip Labs, about finding the balance between human tolerance and tooling constraints, the spectrum of typed programming languages, and building cost-effective tooling for AI agents.
GPT-6 Astra Ultrafast, running on NVIDIA Blackwell GPUs, is available now in the OpenAI API and to eligible ChatGPT Work and Codex users. Accelerated by inference optimizations through OpenAI’s models that tap into the capabilities of the NVIDIA Blackwell architecture, Ultrafast offers up to 8x faster token generation than the Astra Standard mode. For developers, […]
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.
Quick caveats: this is a post on AI safety, written by a cryptography professor. If that troubles you, you should read something else. I try hard not to work on AI (except when the topic occasionally tosses itself in my path), so in this post I’m mostly trying to referee arguments made by others. If … Continue reading Is sandboxing sufficient to contain rogue agents? →
Bringing together the world’s brightest minds and the latest accelerated computing technology leads to powerful breakthroughs that help tackle some of the biggest research problems. To foster such innovation, the NVIDIA Graduate Fellowship Program provides grants, mentors and technical support to doctoral students doing outstanding research relevant to NVIDIA technologies. The program, in its 26th […]
AI can make the first part remarkably fast. It can find the page, the discussion and the person who might know. The harder work begins when those sources disagree, or when they become stale.
Cloudflare AI Gateway now features a model router that evaluates request complexity using an edge-deployed classifier to select the optimal model. By balancing expected output quality against token costs, organizations can dramatically cut AI spend while maintaining performance.
AI Gateway User Insights now adds task, model, turn, and user categories to help teams understand AI adoption and make better model decisions. This is available free to AI Gateway users.
Cloudflare’s AI Gateway, Ceramic.ai, Stocktwits, and more are using the Cloudflare Monetization Gateway today to charge agents for access to tokens, APIs, and MCP tools. U.S.-based sellers can now apply for access to the closed beta.
Pay Per Use is now in beta. AI companies report when they use publishers’ content, and Cloudflare handles billing, payouts, and reporting, so our customers are paid according to use.
Cloudflare Registrar’s new search delivers fast, transparent results across 420+ extensions using Workers, Durable Objects, and WebSockets. Its expanded API and cf CLI also let agents search, register, and transfer domains.
Cloudflare Containers now start 6x faster, let your agent choose each sandbox's image and instance type at runtime, and support filesystem snapshots in public beta, all controlled from a Durable Object.
More than half the traffic reaching sites on Cloudflare is now automated, and AI agents are the fastest-growing part of it. We're giving site owners the tools to see who's visiting, decide who gets in, and charge for access.
One Postgres table with two indexes beat every published RAG pipeline on MuSiQue. Every architectural addition is a bet the model stays weak.
Authors: Camila Mirabal, Tech writer, and Travis Turner, Tech Editor Topics: Developer Community, Rails, AI Regular SF Ruby Conference tickets are $450 through September 30. Meet Ruby friends, play The Pier, join small-group conversations, and explore the 2026 program in San Francisco. Not a single person in the Ruby community has told us they go to conferences for anything other than meeting new people and catching up with old friends. Our community needs that shared warmth and joy more than ever. But going to a conference alone can be intimidating. You walk into a room full of people you…
How Airbnb uses proximity signals to personalize without relying on individual user history.By: Wei Jiang, Bin Xu, Bharathi Thangamani, Weiwei Guo, Sundar Srinivasavaradhan, Tracy Yu, Huiji Gao, Swapnil Ghike, Michael KinotiGreat personalization starts with knowing your user. But what happens when the user is a stranger?A significant share of Airbnb users arrive without a login, without a recent search history, or without any prior booking — especially those landing from paid advertising or organic search. For these users, the ML models that power search ranking, destination recommendations,…
Model routers are everywhere right now: a small model reads each turn and picks which model should handle it. The inconvenient truth is that the router is always less capable than the model it’s choosing for. Replit Agent lets the model decide instead. The main agent, or core loop, chooses its subagents’ tier and effort, and adjusts its own as the task unfolds. Given that freedom, Astra hands routine implementation to less costly subagents and decides for itself where its tokens are worth spending. On both DeepSWE and Terminal-Bench, Replit Agent is Pareto-efficient against Astra on its own:…
We built a WAF tester that adapted each request based on what the WAF blocked or passed. This helped us explore variations that a fixed test might miss. We ran it across six attack categories on an authorized staging environment and discovered detection gaps worth fixing. Here’s how the loop worked, what got through, and what we did about it.
We’re building CryptoLabe, an internal AI-powered tool that discovers cryptography across our codebase, surfaces dependencies, and helps us progress toward a full post-quantum migration by 2029. Here’s what we’ve learned so far.
How we redesigned Reclaim for AI and natural-language requests while preserving the scheduling experience people rely on.
In 2026, Kotlin turned fifteen. Over those fifteen years, Kotlin has built a mature ecosystem, been adopted by companies around the world, and established a large and active developer community. Fifteen years is long enough to understand which technology trends lasted and which didn’t. This report looks back at Kotlin’s first fifteen years to see […]
Ryan sits down with Div Garg, CEO at AGI Inc., to talk about running AI agents entirely on mobile devices, optimizing models for edge computing chips, and building safety mechanisms into autonomous app interactions.
Build Agentic UI with the new Blazor AI components for streamed content, tools, approvals, shared state, and generative experiences. The post Build Agentic UI with the new Blazor AI components appeared first on .NET Blog.
In the rush to adopt AI and automation, many teams implement human-in-the-loop (HITL) frameworks. They believe that involving a person in the process solves the problems with reliability, quality, and trust. But as we’ve learned from real engineering workflows and integrations, the story isn’t that easy. In some contexts, humans-in-the-loop do improve outcomes, but in others, they can unintentionally become bottlenecks that limit speed, scalability, and innovation. In this post, we’ll analyze when human-in-the-loop is truly valuable, when it slows systems down, and how to strike the right…
Vinext 1.0 graduates from an AI experiment to a production-ready framework, letting developers run Next.js apps on Vite. This release brings advanced cache warming, broader compatibility, and an automated testing pipeline.
We’ve updated Kitesurf, our Workers-based browser for AI agents, with WebMCP support, improved DOM performance, and terminal-based rendering. With over 730,000 Web Platform subtests passing, agents can now navigate complex sites faster.
41 experiments in 6 days took LoCoMo memory from F1 0.392 to 0.666. Claude wrote the code; the human caught the metrics that were lying.
The Internet is changing more today than at any point since Cloudflare launched back on September 27, 2010. As automated traffic surpasses human activity, we reflect on the rise of AI agents, new creators, and how we can help build a fair, sustainable future for the web.