Security | Threat Detection | Cyberattacks | DevSecOps | Compliance

Code Mode: Giving AI Agents an Entire API in 1,000 Tokens (With Demos)

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.

Why Legal AI Governance Must Operate at the Point of Use

A recent report of a solicitor facing regulatory investigation after uploading client documents into ChatGPT is not an isolated incident. It is a visible symptom of a broader structural issue unfolding across highly regulated industries. Legal professionals operate under strict duties of confidentiality, and yet the tools reshaping their workflows are being adopted faster than governance and operational controls can keep pace. The challenge is not whether AI should be used in legal practice.

I Don't Treat AI Video as a Toy Anymore - Not After Testing It Through a Security Lens

I used to look at consumer AI media tools as a novelty. Fun, impressive, occasionally useful - but still something I'd keep in a separate mental bucket from the things I take seriously. That changed when I started testing them the way I test anything else that touches trust, identity, and digital hygiene.

How to Choose the Best Patreon Alternative in 2026

Creator monetization has changed fast. In 2026, relying on a single platform like Patreon is no longer your only option. Many creators now want more control, higher profit margins, and better ownership of their audience. If you are building a membership, selling exclusive content, or offering paid communities, choosing the right platform matters. The wrong choice can limit your growth. The right one can help you scale faster, keep more revenue, and improve your relationship with your audience.

Promoting Content Without Triggering TikTok's Safety Systems

TikTok is one of the fastest ways to reach new people online. But it's also one of the strictest platforms when it comes to safety. Many creators grow fast at first, then suddenly see views drop or promotions stop working. This usually happens when TikTok's safety systems detect behavior that looks risky or unnatural. The good news is that you can promote your content safely if you understand how TikTok thinks.

Building Predictable Engagement Without Daily Manual Effort

Growing on Instagram does not have to mean being glued to your phone all day. Many creators think engagement only happens if they like, reply, and post every single hour. In reality, the most stable accounts are built on systems, not constant effort. When you automate your Instagram engagement strategy, you create steady results without burning out.

The MCP Trojan Horse: AI's Hidden Security Risk

The race to adopt AI agents has created a massive, unmonitored blind spot in the enterprise software supply chain. At the heart of this revolution is the Model Context Protocol (MCP) – an open connectivity standard designed to move AI models (LLMs) out of their passive “chat box” and give them direct active access to your company’s internal systems.

Beyond the Bug: Why Cybersecurity Still Matters Even If AI Improves Secure Development

This post reflects the author’s views as of the publication date and contains forward-looking statements and opinions about technology trends. Actual outcomes may differ based on attacker behavior, customer environments, and broader market and regulatory developments. Last Friday’s announcement from Anthropic introducing tied to its Claude platform sparked immediate speculation about what AI-driven secure development could mean for cybersecurity.