Start from a learning goal, protect student information, and keep educator judgment at the center of lesson and family communication tasks.
Choose one real task, replace the brackets with safe context, test the result against a clear standard, and keep the person doing the work responsible for every claim and final choice.
What specific task and audience should the output serve?
What information is genuinely necessary—and what must stay out?
What source, standard, or expert will be used to check the answer?
What decision must remain with a qualified person?
What would make a non-AI approach safer, faster, or more appropriate?
The source guidance emphasizes protected information, lived and professional context, verification, accountability, and the limits of generated content.
Mississippi Department of Education
MDE connects classroom AI with instructional purpose, policy, educator judgment, and student safeguards.
It shapes the learning-goal, approved-tool, educator-review, and family-communication patterns.
UNESCO
UNESCO emphasizes human agency, age-appropriate use, privacy, inclusion, and pedagogical validation.
It shapes safe inputs, learner agency, accessibility, non-AI alternatives, and source checking.
Sources and requirements can change. Check the publication date, read the original material, and confirm the rules that apply locally before making a consequential decision.
Use the task, audience, local conditions, constraints, output format, and review test that fit the work. The same prompt should not be copied into every classroom, business, campus, or community.
State the real purpose: advance a clear learning goal, help an educator prepare, or let students practice critique and responsible creation. Name the audience, desired outcome, and how the result will be used before writing instructions.
Do not enter student names, records, disability or behavior information, identifiable work, family information, credentials, or confidential school material. Use fictional, public, aggregated, or properly approved information instead.
Ask the system to separate facts from suggestions, identify uncertainty, avoid invented sources, and state what information it would need to improve the answer.
Check important facts in original sources, apply professional and community knowledge, revise for accessibility and context, and keep a person accountable for use.
✓ Creating a first draft from public or fictional information
✓ Generating questions, alternatives, or structures for a person to evaluate
✓ Reformatting text after accuracy, context, and accessibility review
× Uploading private, confidential, protected, or proprietary information
× Requesting a final consequential decision or professional judgment
× Publishing an answer, citation, statistic, translation, or claim without verification
Replace brackets with safe, relevant context. Each template states what the person using it must still know, check, change, and own.
Generate options an educator can align and revise.
1. Task: Suggest three ways students could practice [learning objective] without replacing the core reading, writing, calculation, or reasoning.
2. Context I can safely provide: Grade band, approved source material, time, available materials, and accessibility needs stated without student information.
3. Output: For each option: student action, educator role, evidence of learning, likely misconception, and non-AI alternative.
4. Boundaries: Do not invent facts, quotations, statistics, people, policies, citations, or sources. Mark uncertainty and ask for missing information.
5. Human review: The educator checks standards, content accuracy, age fit, accessibility, and local policy.
Turn an AI answer into a critical-literacy exercise.
1. Task: Create a short, clearly labeled sample answer about [topic] that includes claims students can verify.
2. Context I can safely provide: Only the supplied approved sources and grade-appropriate vocabulary.
3. Output: A sample, claim-check table, answer key tied to source locations, and discussion questions.
4. Boundaries: Do not invent facts, quotations, statistics, people, policies, citations, or sources. Mark uncertainty and ask for missing information.
5. Human review: The educator verifies every claim and source before students see it.
Create multiple explanations without profiling a learner.
1. Task: Draft three explanations of [concept] using different representations.
2. Context I can safely provide: Grade band, learning objective, allowed vocabulary, and general accessibility needs—not an individual student profile.
3. Output: Plain-language, worked-example, and analogy versions plus limits of each.
4. Boundaries: Do not invent facts, quotations, statistics, people, policies, citations, or sources. Mark uncertainty and ask for missing information.
5. Human review: The educator selects and adapts based on actual learner response.
Explain a classroom use plainly and respectfully.
1. Task: Draft a family notice for [AI-supported activity].
2. Context I can safely provide: Learning purpose, whether accounts are required, information used, alternatives, educator review, and contact route.
3. Output: A one-page notice with headings, plain language, and translation-review note.
4. Boundaries: Do not invent facts, quotations, statistics, people, policies, citations, or sources. Mark uncertainty and ask for missing information.
5. Human review: School staff confirm policy, privacy, accessibility, and translation accuracy.
Test one K–12 education prompt against a real quality standard without using sensitive information.
Choose a low-stakes task and record what a good result must contain.
Adapt one prompt template using fictional or public context.
Run it once and mark accurate, useful, missing, unsupported, biased, or unclear parts.
Change one instruction and test again against the same standard.
Verify important claims outside the tool and decide whether AI added enough value to keep using.
Which improvement came from clearer instructions, and which still required human knowledge, source-checking, or a different tool?
Share the plan with the people responsible for the work and the people who may be affected. Confirm local rules, protect private information, and name the person who can answer questions or correct a problem.