Recipes

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.

Step 01

Build durable discovery fundamentals

Start with the search and information-architecture layer because every other surface inherits its strengths and weaknesses.

Know how crawlability, structure, trust, and internal links reinforce each other.
Spot the highest-leverage fixes on a page template before chasing new content.
Step 02

Adapt the stack for AI answer surfaces

Once the foundation is sound, learn how generative discovery systems quote, condense, and rank source material.

Separate classic SEO requirements from answer-layer visibility tactics.
Decide when a compact route map like llms.txt clarifies your highest-value pages.
Step 03

Understand the tool layer behind real agents

Finish with the protocol layer so you can connect content, products, and workflows to model-driven tooling.

Explain what MCP does and where it fits in a modern software stack.
Recognize when an AI feature needs retrieval alone versus a real tool interface.
Design a bounded agent loop with explicit state, tools, stopping conditions, and approval gates.
Engineer the context window as a budgeted cache with tiers, eviction, and per-layer observability.
Turn expert workflows into focused, discoverable, tested, and safely executable Agent Skills.
Understand how agents distill completed tasks into reusable skills and how to secure the write path.
Structure agent memory as tiers with explicit write, retrieval, and decay policies.
Decide when to fan work out to isolated sub-agents and when a single loop is cheaper.
Build a practical evaluation loop so prompt, tool, and model changes can be judged reliably.
AI Tooling & InterfacesStep 03

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.

Open recipe
AI Tooling & InterfacesStep 03

Agent Loops

A practical guide to the control loop behind AI agents: model turns, tool calls, state, stopping conditions, safety boundaries, and evaluation.

Open recipe
AI Tooling & InterfacesStep 03

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.

Open recipe
AI Tooling & InterfacesStep 03

Agent Skills

How to turn expert workflows into reliable, discoverable agent capabilities: scope, SKILL.md design, progressive disclosure, scripts, triggering, evaluation, security, and distribution.

Open recipe
AI Tooling & InterfacesStep 03

Skill Learning Loops

How agents improve between tasks: distilling completed work into reusable skill files, retrieving them later, and securing the write path.

Open recipe
AI Tooling & InterfacesStep 03

Agent Memory

A layered architecture for agent memory: context window, session memory, persistent memory, and skills, with explicit write paths, retrieval, and decay.

Open recipe
AI Tooling & InterfacesStep 03

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.

Open recipe
AI Tooling & InterfacesStep 03

Evaluation for LLM Features

A practical 2026 guide to evaluating LLM features: task success, grader design, regression checks, safety coverage, and release decisions.

Open recipe