Flashcards

2,671 cards in 36 decks, written from the same source as the concepts. Space to flip, arrows to move, K and R to sort what you know from what you do not. Progress lives in your browser.

All decks 01Foundations 02Transformer Internals 03Training & Fine-Tuning 04Reinforcement Learning 05Inference, Systems & Hardware 06Applied LLM Engineering 07Reasoning, Evaluation & Safety 08Multimodal & Applications

Applied LLM Engineering

Building things people use: retrieval, prompts, agents and production architecture.

4decks

193cards

Retrieval & RAG

Vector stores, hybrid retrieval and reranking, and when to retrieve instead of fine-tune.

74 cards 10 concepts

Prompt Engineering

In-context learning, chain of thought, structured output, compression and injection-aware design.

34 cards 6 concepts

Agents & Tool Use

Function calling, ReAct loops, MCP, agent memory architectures and evaluation harnesses.

51 cards 10 concepts

Claude Certified Architect

Agentic loops, coordinator-subagent designs, tool interfaces and reliability patterns for Claude.

34 cards 7 concepts