Building Blocks

Building Blocks

BasicTopic6 lessons~4h 45m

Lessons, in order

01 Model Access and GatewaysApplications should never call a model directly. They call an AI gateway, and the gateway calls models. That one indirection is where every cross-cutting concern lives: who is calling, how … Basic 45 min 02 Context and RetrievalA model knows only what is in its context window on this call. Context engineering is the work of deciding, on every call, what goes into that window: instructions, the conversation, … Basic 55 min 03 State, Memory and CachingThe model is stateless, so the system holds all the state — and there are four different kinds that are often confused. Session state is the conversation. Task state is how far a long job … Basic 45 min 04 Tools and ProtocolsA model can only produce text. It acts on the world through tool calling: you describe functions to it, it replies with a structured request to call one, your code runs the function and … Basic 50 min 05 Evaluation and QualityYou cannot unit-test a probabilistic component with assert equal. You evaluate it: run it on a fixed set of cases, score each output, and track the pass rate. An evaluation is to an AI … Basic 45 min 06 Reliability PatternsA model dependency fails in ways an ordinary dependency does not. It gets slow without failing, it is rate-limited by tokens, it returns well-formed nonsense, and one request can cost a … Basic 45 min

About this topic

Six components appear in almost every AI system, whatever its shape. Learn each one once — what it does, what it stores, how it fails — and a full design becomes a matter of arranging them.

#	Lesson	The question it answers
01	Model Access and Gateways	How do applications reach models, and what belongs in the gateway?
02	Context and Retrieval	How does the right information get into the context window?
03	State, Memory and Caching	Where does state live, and which of the four caches helps?
04	Tools and Protocols	How does a model act on the world, and what do MCP and A2A standardise?
05	Evaluation and Quality	How do I know it works, and keep knowing after every change?
06	Reliability Patterns	What keeps the system up when a model is slow, wrong or gone?

Each lesson ends with a short list of the tools that fill the box. Read the mechanism first; the list will have changed by the time you need it.