You can wire any feature the SDK offers. What you still cannot do is look at a problem and know which feature to reach for, or whether you need an agent at all. Anthropic’s five agent patterns are a vocabulary for design decisions. This maps each one onto the Claude Agent SDK constructs that implement it, sorts them into workflows versus agents, and shows how to tell when you do not need an agent at all.
In this article: You will learn the one architectural distinction that organizes every agent design pattern, namely workflow versus agent, and the single question that sorts any pattern into the right family. We walk Anthropic’s five composable patterns, map each onto a concrete Claude Agent SDK construct, and end with a decision rule that ties pattern choice to task complexity. The transformation by the end: you stop wiring features and start designing systems.
