Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

In this episode of This Week in NET, host João Tomé is joined by Matt Curry to break down Code Mode: a way to give AI agents access to the entire Cloudflare API (2,500+ endpoints) using two tools and roughly ~1,000 tokens of context. Instead of exposing thousands of individual tools (which quickly becomes expensive and brittle), Code Mode lets the model write JavaScript to search and execute against a compact API context. The result is massive compression, lower cost, and better performance.

An AI agent that browses docs, makes a video, and posts it to Slack — in under a minute. Clip from with VP of Engineering Celso Martinho on Moltworker (for OpenClaw).

In this episode, we look at Moltworker (for OpenClaw) and Markdown for Agents — including how converting HTML to markdown can reduce a 16,000-token page to ~3,000.

Celso explains how Markdown for Agents was conceived, built, and shipped in just one week, why AI systems prefer markdown over HTML, and how converting a typical blog post from 16,000 HTML tokens to roughly 3,000 markdown tokens can reduce cost, improve speed, and increase accuracy for AI models. We also explore Moltworker, a proof-of-concept showing how a personal AI agent originally designed to run on a Mac Mini can instead run on Cloudflare’s global network using Workers, R2, Browser Rendering, AI Gateway, and Zero Trust.

In this episode of This Week in NET, host João Tomé is joined by Emily Hancock, Cloudflare’s Chief Privacy Officer and Data Protection Officer, for a wide-ranging conversation about privacy in 2026 and how the role has evolved in the age of AI.

AI is powerful and organizations continue to adopt AI at a rapid pace, but without protections in place, it’s risky. In this session, you'll learn about the risks Enterprises face around AI and how Cloudflare provides a layered security approach incorporating AI Security. We’ll walk through how you can secure your AI-powered applications with Cloudflare.

Block sensitive data leaks (like PII and source code) and apply intent-based guardrails to detect and mitigate risky prompts before they reach the model.

See how Cloudflare’s API-based CASB integrates with tools like ChatGPT, Claude, and Gemini to detect and mitigate risks of misconfigurations and data exposure.

If you're more flexible, you're more modern with your technology, the experiment... will be faster." - Lior Gross, CTO at Caliente.mx. Old infrastructure is too costly for AI experiments.

At the start, we also go over some of our recent blog posts.