AGENTSstill growing

Agents from first principles

Explain what makes a model an agent, and build the core loops of tool use, planning, ReAct and reflection.

For Developers who have called an LLM API and want to understand how agents are built from it.

9 notes, in order. Each one assumes the one before it. Still growing: more notes may be added.

Notes in this trail

Start the trail
  1. Why agentic patterns, not yet read
  2. LLM versus agent, not yet read
  3. Agent design principles, not yet read
  4. State graphs, not yet read
  5. Agent memory, not yet read
  6. Tool use, not yet read
  7. Planning, not yet read
  8. ReAct, not yet read
  9. Reflection, not yet read