Home › Reference
🗂️ One page

The Map

Every topic on one page, grouped the way the site is, and every deep dive reachable from it — the one-liner, the point that governs it, and a link to all of them.

340in-depth guides
56key terms
18topics
6groups

Tip: print this page (or save as PDF) for a portable one-sheet. Every chip opens its own page; “Show all” reveals the rest of a topic.

What is different about this stack10

Ten places where building on models departs from ordinary software engineering. Every row has pages below it.

ConcernTraditional softwareA production AI system
CorrectnessDeterministic. The same input returns the same output, every time.Probabilistic. The same input returns different output, so correctness is a rate over a sample rather than a property of a run.
TestingUnit tests assert exact values. A pass is a boolean.Eval sets score a held-out sample. A pass is a threshold on a rate, and it moves when the model, the prompt or the corpus moves.
How it failsIt throws. You get a stack trace pointing at the line.It answers confidently and wrongly, with no error anywhere. The dangerous failure is the one that looks exactly like success.
Cost shapeFixed per deploy, scaling with infrastructure and traffic.Per call and per token, so a longer answer costs more than a shorter one and a retry costs the whole call again.
LatencyMilliseconds, and roughly constant for the same operation.Seconds, varying with how much the model chooses to say. Time to first token and total time are different products.
Security boundaryAround the process and the network.Around every value that enters the context. Retrieved documents and tool results are attacker-controlled input in the same token stream as your instructions.
What changes under youOnly the code you deployed.The model version, the provider's defaults, the corpus and the prompt — four moving parts, three of which you do not own.
ImprovementReproduce the bug, fix it, add a regression test.Read a sample of real failures, label what went wrong, turn the recurring ones into an eval set, change one thing, re-measure.
DataA schema you designed and control.A corpus with a licence, a stated purpose and an erasure obligation, plus derived copies in an index, a cache and possibly some weights.
ObservabilityLogs and metrics: what was called, how long it took.Traces including what was retrieved and which prompt was assembled. Without those an answer cannot be explained after the fact.

Foundations3

the data-science bedrock every model stands on

🛤️ The Road to LLMs

How seven decades of AI led to models that understand and generate language.

Left to right: each era removed a limitation of the one before it, until models learned language itself.

9 deep dives
Key terms

📊 Data Science & ML Fundamentals

The discipline of turning data into predictions - the bedrock under all AI.

Most enterprise 'AI' still lives in this loop; an LLM is one option inside 'Train', not a replacement for it.

8 deep dives
Key terms

🧠 Neural Networks & the Transformer

The architecture family - and the one design - that made LLMs possible.

Read bottom-up: self-attention lets every token weigh every other token, in parallel.

7 deep dives
Key terms

Models3

the engine you call — and how to change what it does

🤖 LLMs & Foundation Models

Large models pre-trained on vast data, adaptable to almost any task.

The training pipeline explains why a raw base model and a helpful chat model behave so differently.

9 deep dives
Key terms

🎯 Fine-Tuning & Alignment

Actually changing the model's weights for your task, style, or values.

You are changing the weights, not the prompt. Reach for it to move behaviour, style and format — facts belong in retrieval, which is cheaper and updatable.

20 deep dives
Show all 20
Key terms

Ground2

making a general model useful for your job

Build5

wiring models into real, multi-step products

🔗 Orchestration Frameworks

The glue that chains models, data, and tools into a real workflow.

Frameworks wire these steps together, add memory, and handle branching and retries.

10 deep dives
Key terms

Agent Skills

What a skill actually is, which surface it runs on, and what it is constantly confused with — every claim dated, because provider surfaces move monthly.

A skill is a folder of instructions the model loads when it needs them. Which surface it runs on decides what it can actually do, and those surfaces move monthly.

35 deep dives
Show all 35
Key terms
SKILL.mdProgressive disclosureThe description fieldSurfaceVolatility

🗄️ Data for AI

The pipelines, ownership and quality work that decide whether any of the rest can work.

11 deep dives

Forward-Deployed Engineering

Engineering that starts at the customer's workflow and ends at a measured outcome — coding is only part of the job.

Four nested loops: a deployment cycles until validation clears, delivery repeats it across real workflows, and field learning feeds the roadmap — so the next deployment starts further ahead.

4 deep dives
Key terms

Operate5

making it trustworthy, measurable, affordable and production-ready

✅ Evals & Testing

How you know the system is actually good - and staying good.

No evals = shipping on vibes. A regression set lets you change a prompt or model with confidence.

11 deep dives
Key terms

What Happens After You Hit Enter

The forty-two stages between your API call and the first character on screen — one fixed sequence, not a menu, and any one of them can be why the answer is wrong or slow.

Forty-two stages sit between your call and the first character on screen, in one fixed sequence. Any single one of them can be why an answer is wrong or slow.

42 deep dives
Show all 42
Key terms
PrefillDecodeKV cacheTTFTStop reason

🔒 Security

Prompt injection, data exfiltration, and the tool permissions an agent should never hold.

8 deep dives

Reference1

consult, don't read — look it up and run the numbers

A living map of modern AI — kept current every morning