Learn in a sequence that builds cleanlyor jump straight to the recipe you need.
Every recipe follows the same model: TL;DR, mental model, practical moves, anti-patterns, and measurement. Browse by topic when you know what you need, or follow the recommended learning path from discovery fundamentals to agent tooling.
Build durable discovery fundamentals
Start with the search and information-architecture layer because every other surface inherits its strengths and weaknesses.
Adapt the stack for AI answer surfaces
Once the foundation is sound, learn how generative discovery systems quote, condense, and rank source material.
Generative Engine Optimization
Getting your content cited, quoted, and recommended by LLMs and AI search systems.
llms.txt
A practical guide to llms.txt: what it is, what it is not, when it helps, and how to publish one without turning it into cargo cult AI SEO.
Understand the tool layer behind real agents
Finish with the protocol layer so you can connect content, products, and workflows to model-driven tooling.
Model Context Protocol
A practical guide to MCP for engineers: what it is, where it helps, how to design better tools, and where production implementations usually go wrong.
Agent Loops
A practical guide to the control loop behind AI agents: model turns, tool calls, state, stopping conditions, safety boundaries, and evaluation.
Context Engineering
The infra engineer's treatment of the context window: a fixed-capacity cache with per-layer budgets, eviction policy, placement discipline, and observability.
Agent Skills
How to turn expert workflows into reliable, discoverable agent capabilities: scope, SKILL.md design, progressive disclosure, scripts, triggering, evaluation, security, and distribution.
Skill Learning Loops
How agents improve between tasks: distilling completed work into reusable skill files, retrieving them later, and securing the write path.
Agent Memory
A layered architecture for agent memory: context window, session memory, persistent memory, and skills, with explicit write paths, retrieval, and decay.
Sub-Agent Orchestration
When and how to spawn isolated sub-agents: fan-out versus one loop, task contracts, partitioning, supervision, and the token economics of parallelism.
Evaluation for LLM Features
A practical 2026 guide to evaluating LLM features: task success, grader design, regression checks, safety coverage, and release decisions.