Master ReAct, Plan-and-Solve, and self-reflecting architectures. Part of the free AI Agents Academy — every lesson below is open to everyone, no signup required.
The ReAct Pattern ReAct (Reasoning + Acting) is the foundational pattern for modern AI agents. Instead of just answering a question, the model emits a...
Hierarchical Planning While ReAct is great for short tasks, it fails on long horizons because the agent loses track of the overarching goal. Enter Pla...
The Inner Critic Agents that act without checking their work make catastrophic mistakes. Adding a Reflection step improves reliability by 30-40%. A Se...
Modeling Agents as Graphs The most reliable production agents are not free-form loops — they are state machines modeled as directed graphs. This is th...
Giving Agents a Private Thinking Space Humans don't jump straight to answers — we mutter to ourselves, scribble notes, and reason through problems. Th...