Build a repeatable workflow

Use this topic-specific sequence: target → draft → differentiate → solve → review → teach. Give each stage one input, one output, and one gate. The first run should be narrow and reversible. Later automation is earned by measured reliability, not by how easy it is to connect tools.

For design a differentiated fraction mini-lesson while keeping assessment judgment with the teacher, begin with the job card and sanitized packet. Run the constrained prompt:

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.

Save the response beside its prompt and input version. Then apply the quality rubric and solve every item, confirm support versions assess the same target, check reading load and cultural assumptions, and have the teacher approve classroom use. A failed check returns to the smallest responsible stage; do not regenerate everything. If the source was missing, repair context. If the instruction was ambiguous, repair the prompt. If the candidate violates policy, stop and escalate rather than prompt around the policy.

Name an owner for source approval, generation, verification, and release. One person may hold several roles on a small project, but the role changes should remain visible. The reviewer needs the evidence packet, not merely the final artifact.

Define operational states: draft, needs evidence, blocked, approved, released, and rolled back. This vocabulary prevents a plausible draft from being mistaken for an approved result. Attach timeouts, retry limits, and an off switch to any automated stage.

Log the defect category rather than just “bad output.” This chapter's recurring defects are wrong answer keys; difficulty changed by changing the target; accidental answer reveal in hints; biased examples; automated grading or discipline recommendations. Track their rate on representative cases. Review false positives and false negatives separately when classification is involved; track factual, continuity, or rights defects when producing media.

The end product is a teaching packet with target alignment map, vetted materials, misconception plan, accessibility review, and teacher sign-off. Adapt the route to learning, not the destination. AI drafts examples and supports; the teacher remains responsible for accuracy, context, and consequential decisions. Periodically rerun a stable set of cases after changing models, prompts, source material, formulas, or settings.

Imagine the independent check fails after release. Identify how to stop distribution, identify affected outputs, restore the last approved version, notify the owner, and preserve enough evidence to learn. A workflow without rollback is only a happy-path demo.