Convert authentic professional evidence into a bounded decision case without exposing sensitive details. 제공할 내용: Professional source material, Learning design, Adaptation and ethics constraints. 예상 결과: A teachable case with evidence packet, decision task, facilitator guide, and source-change ledger.
1
맥락 추가
텍스트는 이 브라우저에 유지됩니다. AILesson Prompts는 이를 모델이나 서버로 보내지 않습니다.
2
프롬프트
채워지지 않은 필드는 플레이스홀더로 표시되므로 프롬프트를 복사하고 편집할 수 있습니다
Turn the supplied professional material into a classroom case grounded in its evidence.
Facts, artifacts, timeline, decisions, data, roles, outcomes, sources, and confidentiality:
[material]
Learner level, objectives, prerequisites, time, assessment, and decision complexity:
[learning]
Permissions, anonymization, accessibility, invention boundary, language, format, and instructor needs:
[constraints]
Inventory source facts before adapting. Separate retained fact, anonymized detail, simplified structure, composite element, pedagogical assumption, and omitted information. Do not invent a real person's quotation, motive, wrongdoing, protected trait, result, or confidential operational detail. If fictional bridging is permitted, label it clearly and ensure it cannot be mistaken for evidence. Preserve material uncertainty, competing interests, constraints, and at least one reasonable alternative; do not make the instructor's preferred answer inevitable.
Create learner-facing title, context, timeline, roles, evidence packet, decision point, task, deliverable, criteria, and staged disclosure. Include only information learners need and provide accessible equivalents for visuals/tables. Then create a separate facilitator guide with objectives, preparation, likely approaches, misconceptions, probing questions, evidence-based analysis, multiple defensible decisions, debrief, extension, and assessment rubric. Add a source-to-case change ledger, privacy/licensing check, and validation questions for a subject expert.
기본적으로 비공개프롬프트 구성은 브라우저에서 로컬로 이루어집니다. 조직에서 허용하지 않는 한 기밀 정보를 AI 서비스에 입력하지 마세요.
입력에서 결과까지
적용 예시
구체적인 맥락이 이 레시피를 바로 사용할 수 있는 결과로 바꾸는 방법을 확인하세요
실제 입력
Professional source material
Internal library reminder pilot: 214 opted-in adults over six weeks; 61% collected before expiry versus 54% among 198 in prior six weeks; non-randomized and seasonal mix differed. Eleven opt-outs, three late-message reports, staff handled replies ~25 min/day. Operations considered a randomized follow-up but had no approved sample rationale, owner, budget, privacy/accessibility review, or stop thresholds. No rollout decision. Aggregate facts may be taught; library, staff, dates, systems, and patron details must be anonymized. Internal report licensed only for instructor use.
Learning design
Graduate public-service management course. Objectives: distinguish descriptive from causal evidence, identify operational/ethical guardrails, and make a proportionate decision under uncertainty. Students know basic percentages but not trial design. Fifty-minute case discussion; team memo of 300 words assessed on evidence, alternatives, and conditions.
Adaptation and ethics constraints
English learner packet with plain-language table and text alternative. No invented quotes. Fictional organization name allowed and labeled. Learners may choose design, refine, or decline a test; permanent rollout is outside decision authority. Facilitator needs timed plan and rubric.
예시 출력
Learner case—“The Cedar Service Reminder Decision” (Cedar is a fictional name; aggregate evidence comes from an anonymized real pilot). A public service asks whether to spend limited design capacity on a stronger reminder test. Evidence packet: prior six weeks 107/198=54%; pilot six weeks 131/214=61%; periods not randomized and seasonal mix differed; 11 opt-outs; 3 late reports; about 25 staff-minutes/day. Text alternative states every value and denominator. Missing by design because genuinely unknown: sample rationale, owner, budget, privacy/accessibility review, stop thresholds.
Decision: recommend Design, Refine before design, or Decline; do not authorize rollout. Submit 300 words stating claim boundaries, two alternatives, affected groups, three conditions/guardrails, and evidence that would change the recommendation. Stage 1 gives outcome data; after 12 minutes Stage 2 reveals operational signals so students may revise. Criteria: uses denominators/non-randomization correctly; weighs service, access/privacy, and staff implications; compares alternatives; makes proportionate conditional decision.
Facilitator: 0-5 individual claim; 5-15 teams inspect Stage 1; 15 reveal Stage 2; 15-30 option analysis; 30-40 challenge from patron/staff/governance lenses without inventing their views; 40-47 decisions; 47-50 debrief. Probe: “What can 61 versus 54 establish?” “Which missing gate matters before design versus before launch?” Defensible outcomes include bounded design with gates, refinement to add accessible channels/ownership, or decline if capacity threshold is explicit. “Pilot worked” is a misconception.
Rubric 0-2 each: evidence fidelity, alternatives, guardrails/equity, decision proportionality, revision after disclosure. Ledger: all numbers/limits retained and anonymized; Cedar is labeled fiction; dates/systems omitted; no quotes or outcome invented. Validate with subject expert: whether 107/198 and 131/214 match report after exclusions, whether aggregate teaching permission covers the derived percentages, and whether operational details remain non-identifying.
효과가 있는 이유
1
A change ledger protects authenticity by showing exactly where teaching needs altered the source
2
Multiple defensible choices make learners reason from evidence instead of guessing the instructor's answer
결과 확인
Can every case fact be traced to the source or a clearly labeled permitted adaptation
Are privacy, permissions, uncertainty, trade-offs, and reasonable alternatives preserved
Do the learner task, evidence packet, guide, and rubric align with the learning objectives
안심하고 사용하세요
자주 묻는 질문
이 레시피를 언제 사용해야 하는지, 무엇을 제공해야 하는지, 그리고 어떤 부분에서 사람의 검토가 여전히 중요한지에 대한 실용적인 답변
What should I prepare before using “Turn professional material into a classroom case”?
For “Turn professional material into a classroom case,” prepare Professional source material, Learning design, and Adaptation and ethics constraints. Replace placeholders only with information you can verify. If a detail is unknown, preserve that uncertainty explicitly instead of asking the model to infer it.
When is the “Turn professional material into a classroom case” result not ready to use?
The result is not ready if it does not yet deliver the stated outcome—A teachable case with evidence packet, decision task, facilitator guide, and source-change ledger—from the supplied evidence, or if it relies on unresolved assumptions, missing approvals, or invented details. Use the checks as release gates: revise the source inputs or assign a named, authorized reviewer instead of polishing an unsupported output.
Which AI tools have recorded tests for “Turn professional material into a classroom case”?
The published test record for “Turn professional material into a classroom case” lists ChatGPT as of 2026-08-28. This confirms recorded runs, not guaranteed compatibility or identical results in later product versions. For another tool or version, keep every constraint visible and repeat the result checks before use.
ChatGPT
