A newsletter covering four topics: a comparison of MCP (Model Context Protocol) vs Agent Skills across five dimensions (integration, architecture, invocation, runtime, and use case), five layered defenses against prompt injection attacks (spotlighting, instruction hierarchy, least-privilege tools, human-in-the-loop, and planner/executor split), an overview of how the X (Twitter) recommendation algorithm works, and a pointer to a YouTube video on AI evaluations.
Table of contents
Over 80% of container spend is wasted. Here’s how to fix it. (Sponsored)Why Everyone Should Know About AI Evals: The Fundamentals ExplainedMCP vs Skills, Clearly ExplainedIaCConf 2026: AI, IaC, and platform engineering (Sponsored)5 Way to Defend Prompt InjectionHow the X Algorithm WorksSort: