How to Run an Agent Loop That Actually Converges
A four-checkpoint how-to for agent loops: name a measurable job, bound the tool surface, refresh sandbox fixtures from real traffic, and verify at agent speed.
A five-step readiness checklist for teams whose sites are increasingly visited by AI agents: expose callable functions, verify bot traffic, measure real-user speed, and control crawler load.
AI agents now browse the web alongside people, and they interact with pages differently: they call functions, follow machine-readable contracts, and generate far more automated traffic than a human ever would. This explainer walks through a practical five-step readiness path, from publishing callable site functions through a WebMCP-style contract, to hardening bot verification with a real backend check, to measuring real-user performance instead of lab numbers, and finally to capping the resource cost that crawler traffic imposes on your origin. Each step ends with a checkpoint you can verify before moving on, so the diagram doubles as a rollout plan rather than a reading exercise.
Simulated clicking is brittle: it depends on layout, timing, and element ordering that change with every redesign. Kitesurf's WebMCP support lets agents call named site functions such as searchFlights() directly, and site owners can enable it with a single switch. That makes agent traffic a supported integration surface rather than a fragile screen-scraping exercise.
The posts behind it
Vinext 1.0 graduates from an AI experiment to a production-ready framework that lets Next.js applications run on Vite, supporting both Pages and App Router. It achieves over 99% test compatibility for customer-requested features, excluding cache components, and includes support for pre-rendering, cache warming, and observability with OpenTelemetry and Sentry. Cache warming moves page prerendering from the build machine to Cloudflare’s network by deploying a new Worker version to zero traffic and requesting pages to populate the cache before promotion. The framework supports React Server Components, Server Actions, API routes, middleware, and shared caching functions across both routers, with first-class runtime support for Cloudflare Workers and bindings like image optimization and hyperdrive. Migration requires only two commands, and the project is open source with a nightly Next.js end-to-end test suite and community-driven issue tracking, also supporting output: ‘export’ for fully static sites and background revalidation.
Cloudflare has released the BEACON dataset, an anonymized collection of billions of real-user performance measurements from 10,000 of the largest websites. The dataset reports Core Web Vitals (LCP, CLS, INP) with full histograms, enabling analysis of any percentile including the long tail. It reveals that WebKit browsers underperform Blink in 46 countries, and that resource-discovery and render-blocking contribute more to slow LCP than download time. Soft navigations in single-page applications load two to three times faster than hard navigations, but landing pages remain heavy. The dataset is publicly available on Google BigQuery and includes differential privacy via the RAPPOR algorithm to protect individual user data.
Kitesurf, Cloudflare’s browser for AI agents built entirely on Workers, has received a major update. It now supports WebMCP, enabling agents to call site functions like searchFlights() instead of simulating clicks, and site owners can enable WebMCP with one switch. The browser passes over 730,000 Web Platform Tests, up 500,000 since launch, and adds support for CSS Layout, CSSOM, custom elements, URL-based module resolution, and improved iframe behavior. Efficiency optimizations reduce DOM traversal overhead, font fetching, and timer work, keeping CPU usage in line with launch benchmarks despite expanded capabilities. Kitesurf also gains full Browser Run API coverage, including Quick Actions from Worker bindings, and a terminal rendering mode using the Kitty protocol or ANSI text, with open-sourcing planned soon.
Cloudflare’s 2026 founders’ letter, marking the company’s 16th birthday, examines rapid changes in internet traffic driven by AI. Since mid-2025, new website creation has exploded, fueled by ‘vibe coding’ tools that allow non-programmers to build apps, with over 7 million developers now using Cloudflare’s platform. Automated traffic from AI agents and crawlers is projected to surpass human traffic by May 2026 and could reach 1,000 times human levels within five years. This surge risks a tragedy of the commons: agents consume resources from many sites but benefit only one, threatening small businesses that lack the information volume older competitors hold. Cloudflare proposes reducing crawler load by fetching only changed content and enabling creators to receive payment when agents use their content, alongside partnerships to shape a fairer internet.
Cloudflare launched Turnstile Spin, an agent-mediated implementation of its Turnstile CAPTCHA alternative that AI coding agents use to set up security on any website. The two-step Turnstile flow requires a frontend widget and a backend Siteverify call, but many sites skip the backend validation, leaving them exposed to bots. Spin uses the user’s AI coding agent to find frontend and backend code, propose a plan, and after approval automatically embed the widget and wire up the Siteverify call without sending code to Cloudflare. It also fixes improperly installed widgets detected by monitoring Siteverify calls and handles migrations from other CAPTCHA providers. Since its July release over 65,000 widgets have been created via Spin and the generated prompt has been copied more than 30,000 times, and the service remains free.
More like this
A four-checkpoint how-to for agent loops: name a measurable job, bound the tool surface, refresh sandbox fixtures from real traffic, and verify at agent speed.
A five-checkpoint walkthrough of BYOC: name the control you need, split control and data planes, build the landing zone, govern data in place, then operate inside your own tenant.
A five-checkpoint workflow for making large-scale training runs bitwise reproducible: pick the guarantee, fingerprint the run, and trace divergence down to the kernel.
The Good Stuff
Paid picks we use ourselves. Links carry a referral code — a subscription through one earns us a commission at no extra cost to you.
One useful email. Unsubscribe anytime.