Recursive self-improvement is the process of building AI agents that learn from their own output and get smarter every time they complete a task. Anthropic recently shared that they’re generating eight times more code than they were just a few quarters ago using this same approach. The principle is straightforward: when an agent does work, it documents what it did, …
Stop Typing to AI: Give Agents the Context They Need
Short prompts make AI guess. Dennis Yu shows how context-rich voice briefs give AI agents the goal, evidence, constraints, and definition of done they need to deliver useful work.
How Coaches and Course Creators Can Turn Their Content Into AI Agents That Help Their Students Win
A step-by-step guide for coaches and course creators to inventory their content, build a task library of SOPs, and deploy AI agents that help their students win—following the same Content Factory process we used for Sigrun Gudjonsdottir.