A within-subjects pilot with 27 professional software engineers found statistically significant self-reported self-efficacy gains across all 10 assessed skill areas after completing the cc-self-train curriculum¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r? · q2 · i3 large
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i3 All 10 self-efficacy items showed statistically significant pre/post gains (p <0.001) with large effect sizes (Cohen's d range: 0.89–2.79) in a within-subjects pilot with 27 participants. → Zain Naboulsi 2026 q2 i? A Wilcoxon signed-rank test confirmed the overall gain, with 26 of 27 participants improving. → Zain Naboulsi 2026 (2)

Evidence¶

Zain Naboulsi 2026¶

Zain Naboulsi. (2026). Agentic Education: Using Claude Code to Teach Claude Code. arXiv. https://arxiv.org/abs/2604.17460 doi:10.48550/arxiv.2604.17460

q2 · i3 · causal · r?

Within-subjects pilot (n=27 professional software engineers from a single client organization) with pre- and post-training self-assessments on a 10-item 5-point Likert questionnaire, analyzed with paired t-tests. The article reports "All 10 items showed statistically significant gains (p <0.001)" with Cohen's d range 0.89–2.79.

"All 10 items showed statistically significant gains (p <0.001), with large effect sizes across the board (Cohen'sdrange: 0.89–2.79)."

Zain Naboulsi 2026 (2)¶

Zain Naboulsi. (2026). Agentic Education: Using Claude Code to Teach Claude Code. arXiv. https://arxiv.org/abs/2604.17460

q2 · i? · causal · r?

Non-parametric confirmation of the overall pre/post gain in the same pilot. The article reports "a Wilcoxon signed-rank test (W= 0.0,p <0.00001)" with 26 of 27 participants improving; no effect size is printed for this test.

"The overall gain was confirmed by a Wilcoxon signed-rank test (W= 0.0,p <0.00001), indicating that 26 of 27 participants improved (one advanced user scored at ceiling on both administrations)."

Discussion¶

Related Claims¶

• Proximal goals and ability attributional feedback for early learning raise self-efficacy more than distant goals and effort feedback, by a review's report of earlier studies — the general claim this finding bears on, with the studies behind it
• Pilot self-efficacy gains decreased with self-reported expertise: beginners gained most (+1.18), intermediates +0.94, and advanced users +0.46, all significant — a narrower finding that bears on this claim
• The largest self-efficacy effect sizes in the pilot appeared on advanced features such as setting up hooks and creating skills — a narrower finding that bears on this claim
• Self Assessment Improves Self Regulated Learning — a broader claim this one bears on
• In a randomized trial of SRL interventions in an online mathematics preparation course, group and time interacted significantly on SRL knowledge, self-efficacy and the SRL overall score, with Group TDP (training + diary + peer feedback) showing the most prominent gains — related
• Pilot studies in computing-related majors report measurable improvements in student engagement, self-efficacy, and learning outcomes — a broader claim this one bears on
• Teaching a ChatGPT agent improves students' self-regulated learning, specifically self-efficacy and use of cognitive strategies — related
• Students’ prompt self-efficacy increased significantly after the scaffolded GenAI course (t = 3.729, p < .001) — related
• An online PD program using unplugged explainable machine-learning activities increased K–12 educators' AI self-efficacy from below-moderate to above-moderate levels — related
• A professional development masterclass produces a 24% overall improvement in educators' AI utilization competence with large effect sizes — related
• The article is situated within research on self-regulated learning strategies in educational contexts — related
• All participants reported higher teaching self-efficacy after the teaching-simulation training — related
• Intervention-cohort students reported positive pre–post shifts in Innovation and Motivation and Self-Directed Learning Ability — related
• Improvements over baselines are statistically significant, with Cohen's d ranging from 1.2 to 1.8 for key metrics — related