Practice, plan, and improve your thinking without outsourcing the learning or accepting invented sources and answers.
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.
UNESCO
UNESCO centers learner agency, privacy, inclusion, critical thinking, and careful validation of educational tools.
It shapes the coaching, independent reasoning, privacy, disclosure, and verification rules.
Cybersecurity and Infrastructure Security Agency
CISA advises people not to put sensitive information into AI tools, warns about AI-enabled deception, and emphasizes account security and human expertise.
It supports the input restrictions, security controls, synthetic-media rules, training expectations, and incident reporting steps.
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: study, practice, plan, receive feedback, or explore a question without outsourcing the learning. Name the audience, desired outcome, and how the result will be used before writing instructions.
Do not enter student records, login information, another person’s work, unpublished research, internship or employer information, health or financial details, or assignment material a course prohibits sharing. 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.
Practice explanation instead of receiving a shortcut.
1. Task: Act as a study coach. Ask one question at a time about [topic] and wait for my answer before responding.
2. Context I can safely provide: Course level, learning objectives, my own summary, and approved materials.
3. Output: Questions that move from recall to application; hints before answers; final misconception summary.
4. Boundaries: Do not invent facts, quotations, statistics, people, policies, citations, or sources. Mark uncertainty and ask for missing information.
5. Human review: I check feedback against course materials and explain the concept in my own words.
Improve reasoning while keeping authorship with the learner.
1. Task: Give feedback on my argument without rewriting it for me.
2. Context I can safely provide: My thesis and outline, assignment criteria, and sources I already selected.
3. Output: Questions about logic, evidence, counterargument, organization, and missing support; no replacement prose.
4. Boundaries: Do not invent facts, quotations, statistics, people, policies, citations, or sources. Mark uncertainty and ask for missing information.
5. Human review: I decide what to revise and verify every source myself.
Plan a search without accepting invented citations.
1. Task: Help me break [research question] into concepts, keywords, and source types.
2. Context I can safely provide: Course context, scope, date range, and databases or libraries available.
3. Output: Concept map, synonyms, search strings, inclusion criteria, and librarian questions; do not supply citations.
4. Boundaries: Do not invent facts, quotations, statistics, people, policies, citations, or sources. Mark uncertainty and ask for missing information.
5. Human review: I search the actual databases and read original sources.
Generate practice—not prohibited assistance.
1. Task: Create new practice problems similar in skill but not copied from [approved example].
2. Context I can safely provide: Learning objective, instructor-approved example, format, and difficulty.
3. Output: Problems first; answers and reasoning in a separate section; common-error note.
4. Boundaries: Do not invent facts, quotations, statistics, people, policies, citations, or sources. Mark uncertainty and ask for missing information.
5. Human review: I solve independently before viewing the answer and check against class methods.
Test one college students 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.