AI-supported project-based learning at YCHS produced authentic student-designed products through iterative prompting and refinement¶

Claim · All claims
Evidence · 1 study · design r2 · q1
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q1 i? In an environmental-impact project, students used AI tools to generate draft images, suggest layouts, and shape content through iterative prompting, then analyzed and refined the outputs into authentic student-designed products such as children's books, social media campaigns, and short-form videos. → Schiner 2025

Evidence¶

Schiner 2025¶

Schiner, N. (2025). Empowering the future: powerful technology for powerful AI teaching and learning [Project report]. Digital Promise. https://doi.org/10.51388/20.500.12265/261

q1 · i? · design · r2

Qualitative case description of Andrea Stanczyk's classroom project on environmental impact at YCHS, where students explored local issues and created awareness or solution products. The report describes the process narratively; no outcome measures are printed.

"Throughout the process, AI tools supported their work through generating draft images, suggesting layout options, and helping the students shape content through iterative prompting. Students would then analyze, revise, rethink, and refine what was generated and make it their own."

Discussion¶

Related Claims¶

• AI-driven situated learning reshapes education by enhancing authenticity and transforming evaluation into assessment woven into the learning process — a broader claim this one bears on
• Embedded AI assistance enabled a novice student to troubleshoot in real time and stay in creative flow — related
• Teachers find ChatGPT a creative, fast, iterative brainstorming partner that adds specific numbers and details when posing math questions from photos — related
• Students' main AI challenges are content reliability and depth, and most expect AI to serve as tutor, creative partner, and critical thinking partner rather than mere content generator — related
• Attendees correctly identified AI-generated images in 82% of polling responses, and polling served as a scaffold for discussion rather than a measurement tool — related
• AI-driven PBL environments enhance educator and student collaboration via real-time feedback, intelligent scaffolding, and data-informed instructional decisions — related
• AI-supported design iteration consists of generation, selection, evaluation, and revision rather than one-off generation — a broader claim this one bears on
• Teachers treated AI as a provisional thinking partner whose outputs required iterative adaptation rather than automatic adoption — related
• Instructors engage LLM-generated suggestions as a controllable refinement process — related
• Active engagement with AI outputs (cross-verifying, refining prompts, revising) supports productive learning and depends on learners' prior knowledge — a broader claim this one bears on