Agents & LLMs
LLM internals, agent design, tools, RAG, evals. · 18 lessons. Read them top to bottom and tick each as you go.
Lessons
0 / 18 read
- 00 — LLM Internals for Agent Builders
- 01 — Agent Foundations
- 02 — Design Patterns
- 02a — Building One: Evaluator–Optimizer, Three Tiers
- 03 — Tools & MCP
- 04 — Memory & Context
- 05 — RAG for Agents
- 06 — Multi-Agent
- 07 — Reliability & Guardrails
- 08 — Evaluation
- 09 — Production & Cost
- 10 — Design Interview Playbook
- 12 — Scenario Debugging
- 13 — Rapid-Fire Q&A
- 14 — Code Lab
- 15 — Thinking Models, and Where the Token Budget Goes
- 16 — Concurrency and async in Python, the way the interview actually tests it
- 17 — LLM Inference Performance