Introduction to Modern Agent Implementation (Slides)
This deck is my systematic blueprint for building modern LLM agents—in the same spirit as a course-style introduction to how LLMs are implemented, but aimed at the full agent stack: models, tools, memory, orchestration, evaluation, and production concerns wired into one coherent picture.
I use it as a map when I want to see how the pieces fit together end-to-end, rather than as isolated blog posts or framework tutorials. Among the material I have collected, it is still one of the most complete end-to-end views of agent system design I refer back to.
Browse the slides below, or download the PDF if you prefer reading offline.