Set a quality and verification bar

For design a differentiated fraction mini-lesson while keeping assessment judgment with the teacher, define quality across accuracy, completeness, usefulness, safety, and reproducibility. Weight dimensions according to harm. A cosmetic miss can be revised; an unsupported claim, broken calculation, privacy leak, or rights violation blocks release.

Translate each dimension into observable checks. Accuracy means a claim, value, behavior, or frame agrees with an authoritative source. Completeness means every required field or stage appears. Usefulness means ten-year-old learners with mixed confidence can take the intended action. Safety includes the boundary that you must never submit names, grades, disability details, behavior records, private writing, or any identifiable student information to an unapproved system. Reproducibility means the prompt, input version, settings, and review evidence are saved.

Use checks from cheapest to strongest:

1. Contract check: required sections, schema, length, and prohibited content.
2. Source check: trace claims and values to supplied evidence.
3. Edge check: run normal, boundary, missing, and adversarial cases.
4. Independent check: calculate, test, rehearse, listen, inspect, or open the original.
5. Human gate: a responsible reviewer approves consequential use.

In this chapter, the concrete verification is to solve every item, confirm support versions assess the same target, check reading load and cultural assumptions, and have the teacher approve classroom use. The expected candidate is An age-appropriate explanation, a correctly solved example, practice that measures the same target, and a misconception note about comparing denominators directly. Record actual evidence, not a checkbox copied from the prompt.

Score each criterion 0 (fails), 1 (partly), or 2 (passes). Any zero for factual correctness, permission, privacy, or required disclosure is an automatic stop. A total score is useful for comparing iterations, but it must never average away a blocking defect.

Learning target: compare fractions with unlike denominators. Create a three-minute explanation using a pizza model, one worked example, four practice items from easy to challenging, and an answer key naming likely misconceptions. Use fictional learners only. Keep the target fixed and do not make grading or placement decisions.

After generation, sample beyond the happy path. Failures such as wrong answer keys; difficulty changed by changing the target; accidental answer reveal in hints; biased examples; automated grading or discipline recommendations often survive a superficial review because the output has the right shape. Use a counterexample designed to expose the riskiest assumption.

Store the rubric result, reviewer, date, input version, failed cases, and unresolved limitations. If the artifact changes, rerun affected checks. Adapt the route to learning, not the destination. AI drafts examples and supports; the teacher remains responsible for accuracy, context, and consequential decisions. Quality assurance is part of the work, not an apology added at the end.