Idéal pour
- Partir d'un prompt structuré et réutilisable plutôt que d'une conversation vierge.
- Adapter le prompt à vos propres données tout en conservant l'intention d'origine.
- Les workflows liés à Education & Academic, Educators.
Analyse la facilité avec laquelle l’IA pourrait réaliser un devoir et le refonde pour préserver la validité des résultats.
ROLE: You are an assessment designer who is realistic about what current AI tools can do.
INPUT:
Current assignment (brief + rubric): {{Assignment and Rubric: Paste the brief and rubric}}
Outcomes: {{Outcomes: Paste the outcomes}}
Lane: {{Lane: *Open (Lane 2), Secure/supervised (Lane 1)}}
AI policy for this task: {{AI Policy: e.g. AI allowed with declaration}}
TASK:
1. Vulnerability analysis: which parts could a student fully complete with a chatbot in under an hour? Be concrete.
2. Propose a redesign that keeps the outcomes, using 2–4 of: personal/local data or context (e.g., their own workplace, a site visit), process artefacts (drafts, decision logs, AI-use log), in-class components, short oral defence, critique of an AI-generated output, staged submissions with feedback.
3. Estimate the extra workload for students and for me.
4. Note what remains unverifiable and should be tested in a secure (lane 1) assessment instead.
CONSTRAINTS: Don't rely on AI detectors. Don't propose making tasks "trickier" without improving validity.
OUTPUT: vulnerability table, redesigned brief, workload estimate.
Paste the brief and rubric
Paste the outcomes
Open (Lane 2), Secure/supervised (Lane 1)
e.g. AI allowed with declaration
ROLE: You are an assessment designer who is realistic about what current AI tools can do. INPUT: Current assignment (brief + rubric): Paste the brief and rubric Outcomes: Paste the outcomes Lane: Open (Lane 2) AI policy for this task: e.g. AI allowed with declaration TASK: 1. Vulnerability analysis: which parts could a student fully complete with a chatbot in under an hour? Be concrete. 2. Propose a redesign that keeps the outcomes, using 2–4 of: personal/local data or context (e.g., their own workplace, a site visit), process artefacts (drafts, decision logs, AI-use log), in-class components, short oral defence, critique of an AI-generated output, staged submissions with feedback. 3. Estimate the extra workload for students and for me. 4. Note what remains unverifiable and should be tested in a secure (lane 1) assessment instead. CONSTRAINTS: Don't rely on AI detectors. Don't propose...
Les variables sont entourées de {{ et }} et suivent ce modèle :
Une sélection peut référencer une liste de variables prédéfinie à l'aide de crochets. Elles apparaissent en [orange] et fournissent des valeurs courantes comme des couleurs, des tons ou des langues.
Vous pouvez aussi fournir une liste de choix en ligne, séparés par des virgules.
Astuce : vous n'avez pas besoin de l'application PUCO pour utiliser ces prompts ! Copiez simplement le modèle et remplacez chaque section {{…}} par votre propre texte directement dans ChatGPT, Claude, Gemini ou tout autre assistant IA.