For a real task, with a decision rule. This lesson sits inside Module II — Online evals — of Evaluation, the course that anchors the AI Engineering program. It is not a survey; it is the specific, working understanding of "Assignment: Design an eval" that the rest of the course assumes you carry forward.
- 01Define Assignment: Design an eval in the precise sense used across Evaluation.
- 02Recognize when Assignment: Design an eval is the correct lens for the situation in front of you, and when it is not.
- 03Apply Assignment: Design an eval to a concrete case drawn from Online evals, and defend the result in plain language.
- 04Connect Assignment: Design an eval to the adjacent lessons in this module without collapsing the distinctions between them.
The idea, stated plainly
For a real task, with a decision rule. That single sentence is the whole lesson in compressed form. The rest of the reading unfolds it — what it means when the terms are taken seriously, where it comes from, and what work it does inside Evaluation. Read the sentence, then read it again after the sections below; it should carry more weight the second time.
Why it belongs in Online evals
Module II exists because in production. "Assignment: Design an eval" is one of the pillars of that module: without it, the later lessons either become memorization or lose their bite. Notice which earlier lessons this one leans on, and which later lessons will lean on it — the shape of the module is easier to see once you place this piece.
How the School of Artificial Intelligence faculty use it
In practice, working school of artificial intelligence professionals reach for this idea before they reach for a formula or a tool. It is a way of framing the problem so that the right question comes first. The mark of understanding is not that you can recite Assignment: Design an eval; it is that you catch yourself using it, unprompted, when the situation calls for it.
Common misreadings
The most frequent error is to treat Assignment: Design an eval as a slogan and skip the mechanics. The second most frequent is the opposite — treating the mechanics as the point, when the mechanics are only there to make the idea usable. Both errors collapse the same distinction, and both are correctable by returning to the one-line summary and asking what it actually claims.
- Assignment: Design an eval is a working tool, not a slogan.
- Its meaning is set by the module it lives in: Online evals.
- Understanding is demonstrated by unprompted use in the correct situation.
- The adjacent lessons in this module are its natural context; read them together.
Produce a two-page written response to the question: "What does Assignment: Design an eval require of a practitioner working inside Online evals?" Submit through your Scholar portfolio.
Deliverables
- — Two pages, plain prose, institutional register.
- — At least one example drawn from Evaluation.
- — A closing paragraph naming the strongest counter-argument to your position.
Rubric
- — Structure — the argument moves in a defensible order.
- — Precision — terms are used in the technical sense the course established.
- — Ownership — the response reads as your considered position, not a paraphrase of the lesson.
- — Composure — the register is calm, direct, and free of ornament.
- 202 — Evaluation, Module II: Online evals — The parent module for this lesson. Re-read the module blurb after finishing the lesson.
- The Anabasis Academy — School of Artificial Intelligence, AI Engineering — The wider program this lesson serves; the Certificate in AI Engineering (Practitioner tier). credential ultimately certifies mastery of ideas like this one.