In SDPBL with SDD introduced, AI usage varies greatly by team and phase, with all teams using AI in Implementation and Debugging but large team differences in Investigation and Planning¶
Claim · All claims
Evidence · 1 study · designr2·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? All teams used AI to some extent in Implementation and Debugging phases, while Investigation and Planning AI use differed greatly by team and student. → Hidetake Tanaka 2026
Evidence¶
Hidetake Tanaka 2026¶
Hidetake Tanaka, Hiroshi Igaki, Kazumasa Shimari, Kiyoshi Honda, and Naoki Fukuyasu. (2026). Practical Implementation Report on Introducing Spec-Driven Development Using AI Agents in Software Development PBL. https://arxiv.org/abs/2608.30572 doi:10.48550/arxiv.2608.30572
q2 · i? · design · r2
Weekly self-report survey analysis (RQ1) of students' AI use on a 0–4 scale aggregated by team across lectures, shown in Figure 4. The authors report that "all teams used AI to some extent" in Implementation and Debugging, with large between-team differences elsewhere.
"These results show, in the Implementation and Debugging pha ses, which re- late to source code generation and understanding, all teams used AI to some extent. However, in other phases, there are large difference s in AI use between teams."
Discussion¶
Related Claims¶
- Team code comprehension dropped in lec09 when Implementation-phase AI usage peaked, and recovered in lec10 following instructor intervention — related
- Students who implemented code without AI (usage level 0) maintained consistently high code comprehension, while level-3 AI users showed very little comprehension in the Mid period — related
- Students' implementation throughput (added LOC per lecture) increased in 2024–2025 cohorts relative to 2022–2023, temporally corresponding with LLM proliferation — related
- Across the student body as a whole, no clear statistical trend was confirmed between AI usage levels and code comprehension — related
- Self-reported LLM usage collapses at the first team milestone and recovers only partially on later coding-heavy team tasks — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
ai-usage-varies-by-team-and-phase-sdpbl-sdd |
title |
In SDPBL with SDD introduced, AI usage varies greatly by team and phase, with all teams using AI in Implementation and Debugging but large team differences in Investigation and Planning |
description |
In SDPBL with SDD introduced, AI usage varies greatly by team and phase, with all teams using AI in Implementation and Debugging but large team differences in Investigation and Planning |
status |
review |
evidence_strength |
moderate |
newest_evidence |
2026 |
generated |
by process:wiki-ingest on 2026-10-11 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — hidetake-tanaka-2026 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.