AI for Teachers
Work a full example
A worked project proves the method by showing decisions, failures, corrections, and evidence.
Before you start
Why this matters
Without opening an AI tool, write the acceptance test for this job: design a differentiated fraction mini-lesson while keeping assessment judgment with the teacher. Name one fact that must be exact, one judgment a person must make, and one condition that should stop the workflow. Compare your answer with the professional standard below; the gap is what you should practice.
1Learn the idea
Read
Project brief
The project is to create a mini-lesson with two support levels, a hint ladder, exit ticket, answer audit, and teacher-use notes. The user is ten-year-old learners with mixed confidence. Definition of done: the intended action is clear, the candidate uses approved evidence, blocking safety checks pass, and another person can reproduce the key result.
Stage 1: prepare
Create the job card and collect learning target, prior knowledge, reading level, allowed representations, misconception patterns, time, and accessibility needs. Remove or replace prohibited material: never submit names, grades, disability details, behavior records, private writing, or any identifiable student information to an unapproved system. Add one ordinary case, one boundary case, and one hostile or misleading case. Record unknowns instead of filling them with plausible guesses.
Stage 2: draft
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.
The first candidate should be An age-appropriate explanation, a correctly solved example, practice that measures the same target, and a misconception note about comparing denominators directly. In this worked run, imagine it also exhibits one realistic defect from this set: wrong answer keys; difficulty changed by changing the target; accidental answer reveal in hints; biased examples; automated grading or discipline recommendations. Do not hide the defect. Mark the exact criterion it violates and decide whether the cause belongs to context, instruction, model capability, or the surrounding process.
Stage 3: repair narrowly
Issue a targeted revision:
Revise only the failed criterion identified below.
Preserve all verified content and the original output contract.
Do not add facts or assets.
Return the corrected artifact plus a one-line change note.
Failed criterion: [paste criterion and evidence]
A narrow repair keeps the review surface understandable. If the model cannot repair without new authoritative information, pause and obtain that information.
Stage 4: verify and release
Now solve every item, confirm support versions assess the same target, check reading load and cultural assumptions, and have the teacher approve classroom use. Record pass/fail evidence for each criterion and have the named reviewer make the release decision. Adapt the route to learning, not the destination. AI drafts examples and supports; the teacher remains responsible for accuracy, context, and consequential decisions. Save limitations in language the audience can understand.
Read
Retrospective
The durable deliverable is not only the final result. It is a teaching packet with target alignment map, vetted materials, misconception plan, accessibility review, and teacher sign-off. Write what surprised you, which check found it, what you changed, and which control should become the default. A clean retrospective distinguishes a prompt improvement from a data, tool, or policy change.
Continue learning · glossary & guides
- Can the reviewer see the failed first attempt and why the correction was justified?
- Does the release packet contain evidence, ownership, and known limitations?
- Reference · Related concept
- Previous
- Next