https://shaigeva.com/tags/security/ Recent content in Security on Shai Geva Hugo -- 0.151.0 en-us Sat, 30 May 2026 13:01:56 +0300 https://shaigeva.com/posts/ai_frameworks/04_capabilities_design_pattern/ Sat, 30 May 2026 13:01:56 +0300 https://shaigeva.com/posts/ai_frameworks/04_capabilities_design_pattern/ <span class="aside"> this post is part of a <a href="https://shaigeva.com/posts/ai_frameworks/01_ai_frameworks_intro" target="_blank">series</a> about creating production-grade maintainable AI-first projects, using AI-first design patterns and frameworks. </span> <p>One design pattern that is a particularly great fit for AI-first dev is managed effects (AKA capabilities).</p> <p>The basic idea with managed effects is that we mechanically restrict what a piece of code can do by only giving it access to specific capabilities.<br> This creates a sort-of sandbox around that piece of code, which helps us make some issues that are specific to agentic dev far more manageable.</p>