Skip to content
Skip to content

11-part series

AI Engineering Atlas

Building systems on top of models you did not train

The application layer, in dependency order: embeddings and search, vector stores, RAG, agents and tool use, MCP, and everything that sits between a working demo and a system that survives real traffic.

Part 01

LLM Fundamentals

The floor everything else stands on. What the model actually is, what it costs, what it cannot do. The thing that explains why your token budget matters more than your parameter count.

17 min8 sections5 figures
Part 02

Embeddings & Search

Turning meaning into geometry, then searching that geometry fast enough to matter. The compression, the metrics, and the real cost of approximate nearest neighbour.

13 min7 sections2 figures
Part 03

Vector Databases

Where the vectors live, and everything that gets hard once they do. Persistence, filtering, replication, and the operational constraints that library users never touch.

7 min4 sections3 figures
Part 04

Retrieval-Augmented Generation

The most-built system in applied AI, and the one most often described too shallowly. Chunking, retrieval, generation, and the evaluation that tells you which half is broken.

15 min7 sections4 figures
Part 05

Agents

What happens when the model, not your code, decides what happens next. Tool schemas it can actually use, planning loops that drift, memory that has to be deliberately persisted, and the retries, budgets and step caps that keep the whole loop from running away.

27 min9 sections2 figures
Part 06

Model Context Protocol

A standard socket between models and the tools they call. The newest material in this Atlas, and the one most likely to be stated wrong with confidence — treat every specific detail here as something to check against the current spec before you repeat it.

8 min3 sections2 figures
Part 07

Production

Anyone can build a demo in an afternoon. What separates it from a system is everything covered here — the tail latency nobody load-tested, the token bill nobody budgeted, the cache that lies with a straight face, and the guardrail that only logs.

17 min7 sections4 figures
Part 08

Choosing a Model

Buy, host, or adapt — and how to defend the choice. API tradeoffs, open weights, and why fine-tuning is almost never the first move.

13 min4 sections3 figures
Part 09

Images and the Documents That Aren't Text

When your retrieval corpus contains charts, tables and scanned PDFs, text extraction is silent sabotage. How vision-language models work, what they cost, and why document-aware parsing is not optional.

9 min2 sections1 figures
Part 10

System Design

Everything above, assembled into one system, under constraints that conflict. The AI-system-design interview, and the section that proves the rest was understood rather than collected.

21 min7 sections5 figures
Part 11

Rapid Fire

Ten sections compressed to their load-bearing claims, plus the fifteen questions an interview actually probes and the one-line answers that show you shipped rather than read.

17 min11 sections3 figures