AI Engineering Foundations
What a language model actually is, and what changes when you stop chatting with one and start building on it. Vendor-neutral: tokens, context, sampling, prompts, system instructions, hallucination, and the first evaluation you should write. No prior AI experience assumed.
Start courseWhat you will cover
- What a Language Model Actually DoesNext-token prediction, and how that one mechanism explains almost every behaviour you will meet: fluency without understanding, confidence when wrong, and why the same question can get two different answers.25 min
- Tokens, Context, and Why They Cost YouHow text becomes tokens, what a context window really limits, and why input and output are priced and paced differently. Counting tokens before they surprise you, and what happens when you run out of room.25 min
- Sampling, Temperature, and Non-DeterminismWhy a model that is deterministic underneath gives you different answers anyway: temperature, top-p, seeds, and how to decide when variation is a feature and when it is a bug you have to design around.25 min
- Writing a Prompt That Holds UpThe four parts of a prompt that survives contact with real inputs — instruction, context, examples, output contract — and the vague, overloaded and politely-worded prompts that quietly fail.25 min
- System Prompts and Rules FilesThe durable instruction layer that sits above every request: what belongs in it, what does not, and why project rules files have become a standard part of working with AI tools regardless of vendor.25 min
- Few-Shot Examples That TeachWhen showing beats telling, how to choose examples that generalise instead of ones the model copies verbatim, and how a badly-chosen example set narrows the model instead of guiding it.25 min
- Why Models HallucinateThe mechanism behind confident invention, why asking a model to be accurate does not make it accurate, and the three things that genuinely reduce it: grounding, permission to refuse, and verifiable citations.25 min
- Giving the Model Your DataThe decision map every AI feature runs into: put it in the prompt, retrieve it at query time, give the model a tool to fetch it, or train it in. What each option costs and which problems it actually solves.25 min
- Structured Output Instead of ProseWhy parsing a model's paragraphs is a bug factory, and how asking for a schema instead turns an AI call into an ordinary function you can type, validate and test.25 min
- What to Never Hand a ModelSecrets, personal data, and irreversible actions: the categories that need a boundary rather than a careful prompt, plus what retention and training policies mean for data you send to a provider.25 min
- Measuring Instead of VibingYour first evaluation: a fixed set of real inputs, an expected outcome for each, and a number you can compare. How to build one in an afternoon and why prompt tuning without it is guessing.25 min
- The Shape of an AI FeatureAssembling everything so far into one small end-to-end feature — input handling, prompt, schema, validation, fallback and evaluation — and seeing which parts are AI and which are ordinary software.25 min