AI Engineering Fundamentals

Core concepts for building with large language models: context, retrieval, agents, and evaluation. A starter deck that also shows the file format.

14 cards · space to flip · 1–4 to grade · d to go deeper

Practise this deck as a timed round →

Loading your progress…

Reading list

The works this deck draws on, in the order worth reading them. Cards point to a specific chapter or paper where one fits.

BookAI Engineering · Chip Huyen, 2025The one book that covers this whole deck from an engineer's seat: sampling, prompting, retrieval, agents, and two chapters on evaluation. Read the evaluation chapters first.
TalkIntro to Large Language Models · Andrej Karpathy, 2023An hour on what a model is, how it is trained, and why it behaves as it does; the fastest honest grounding for the fundamentals cards.
GuideBuilding Effective Agents · Anthropic (Erik Schluntz and Barry Zhang), 2024The clearest line between workflows and agents, with the composable patterns and the advice to start with the simplest thing that works.
EssayPatterns for Building LLM-based Systems & Products · Eugene Yan, 2023A long practitioner survey of evals, retrieval, fine-tuning, caching, and guardrails, with the research each pattern rests on.
PaperRetrieval-Augmented Generation for Knowledge-Intensive NLP Tasks · Patrick Lewis et al., 2020The paper that named retrieval-augmented generation; the introduction and the first figure are enough to see the original shape.
PaperAttention Is All You Need · Ashish Vaswani et al., 2017The transformer paper. Read it once for the architecture that tokens, context windows, and attention cost all come from.
BookBuild a Large Language Model (From Scratch) · Sebastian Raschka, 2024Builds a small GPT in plain PyTorch; the chapters on tokenization and attention make the fundamentals concrete.
WebsiteSimon Willison's Weblog · Simon WillisonThe running practitioner record of what new models and tools actually do, including the long series on prompt injection.