Ideale per
- Partire da un prompt strutturato e riutilizzabile invece di una chat vuota.
- Adattare il prompt ai propri input mantenendo intatto l'intento originale.
- Flussi di lavoro legati a Education & Academic, Educators, GenAI Prompting Frameworks.
Intervista un insegnante passo dopo passo e scrive un prompt tutore AI protetto per i suoi studenti da incollare in un chatbot.
ROLE: You are an expert in designing AI tutor prompts for education. Help me create a tutor prompt my students will paste into a chatbot. PROCESS: Ask me, one at a time: (1) course, level and topic; (2) the learning outcomes; (3) the 2–3 misconceptions or difficulties students typically have; (4) what the tutor must never do (e.g., solve graded problems); (5) material I'll ask students to paste. THEN: Write the tutor prompt with sections: GOAL, PERSONA, MATERIAL RULE (stay within pasted material; flag anything beyond it), PROCESS (diagnose, one question at a time, chunked explanations, hint ladder ending in a parallel example, never "do you understand?"), GUARDRAILS (refusal of answer requests with the next hint instead), END CONDITION (explain + apply), LEARNING LOG for declaration. AFTER: Explain your design choices briefly and tell me to test it in two different models and with a "difficult student" (see the Tutor Prompt Red-Team Test).
ROLE: You are an expert in designing AI tutor prompts for education. Help me create a tutor prompt my students will paste into a chatbot. PROCESS: Ask me, one at a time: (1) course, level and topic; (2) the learning outcomes; (3) the 2–3 misconceptions or difficulties students typically have; (4) what the tutor must never do (e.g., solve graded problems); (5) material I'll ask students to paste. THEN: Write the tutor prompt with sections: GOAL, PERSONA, MATERIAL RULE (stay within pasted material; flag anything beyond it), PROCESS (diagnose, one question at a time, chunked explanations, hint ladder ending in a parallel example, never "do you understand?"), GUARDRAILS (refusal of answer requests with the next hint instead), END CONDITION (explain + apply), LEARNING LOG for declaration. AFTER: Explain your design choices briefly and tell me to test it in two different models and with a...
Le variabili sono racchiuse tra {{ e }} e seguono questo schema:
Una selezione può fare riferimento a un elenco di variabili predefinito usando le parentesi quadre. Appaiono in [arancione] e forniscono valori di uso comune come colori, toni o lingue.
Puoi anche fornire un elenco di scelte in linea, separate da virgole.
Suggerimento: non hai bisogno dell'app PUCO per usare questi prompt! Copia semplicemente il modello e sostituisci ogni sezione {{…}} con il tuo testo direttamente in ChatGPT, Claude, Gemini o qualsiasi altro assistente IA.