AI-supported design iteration consists of generation, selection, evaluation, and revision rather than one-off generation¶
Claim · All claims
Evidence · 1 study · reviewr2·q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? AI-supported design iteration is a sequence of activities including generation, selection, evaluation, and revision, in which prompting becomes a way for students to organise ideas. → Yu J 2026
Evidence¶
Yu J 2026¶
Yu J, Liu L and Zhu Q (2026). Is hands-on learning still necessary in the age of AI? A thematic review. Front. Psychol. 17:1897168. https://doi.org/10.3389/fpsyg.2026.1897168
q2 · i? · review · r2
Cross-study thematic synthesis of studies of AI-mediated design learning processes; the review reports that prompting is "not simply the input of keywords" but a way for students to organise ideas and advance the design process.
"Together, these studies show that AI-supported design iteration is not a one-off act of generation, but consists of a sequence of activities including generation, selection, evaluation, and revision."
Discussion¶
Related Claims¶
- Interviewed students adopted an iterative upload–review–revise workflow and perceived the AI feedback as fair and highly useful, though some disregarded recommendations conflicting with their design intent — a narrower finding that bears on this claim
- Teachers treated AI as a provisional thinking partner whose outputs required iterative adaptation rather than automatic adoption — possibly the same claim (merge candidate)
- AI-supported project-based learning at YCHS produced authentic student-designed products through iterative prompting and refinement — a narrower finding that bears on this claim
- Active engagement with AI outputs (cross-verifying, refining prompts, revising) supports productive learning and depends on learners' prior knowledge — related
- Learner agency in GenAI-mediated learning is enacted through prompting, questioning, verification, comparison, revision, and disciplinary judgment — a broader claim this one bears on
- Language becomes an operational medium in AI-supported design, with risks of narrowing exploration — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
ai-iteration-generation-selection-evaluation-revision |
title |
AI-supported design iteration consists of generation, selection, evaluation, and revision rather than one-off generation |
description |
AI-supported design iteration consists of generation, selection, evaluation, and revision rather than one-off generation |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
generated |
by process:wiki-ingest on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — yu-j-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.