# Bridging GenAI policy and practice: Brief instruction improves learning-oriented prompting in an introductory programming course

DevFeed: [Bridging GenAI policy and practice: Brief instruction improves learning-oriented prompting in an introductory programming course](<https://devfeed.tech/articles/bridging-genai-policy-and-practice-brief-instruction-improves-learning-oriented-prompting-in-an-introductory-programming-course-131885.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2602.16033>)

Author: Ruiwei Xiao, Runlong Ye, Xinying Hou, Jessica Wen, Harsh Kumar, Michael Liut, John Stamper

Published: 2026-11-13T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Learning](<https://devfeed.tech/topics/learning.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [classroom](<https://devfeed.tech/tags/classroom.md>), [course](<https://devfeed.tech/tags/course.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-hc](<https://devfeed.tech/tags/cs-hc.md>), [education](<https://devfeed.tech/tags/education.md>), [genai](<https://devfeed.tech/tags/genai.md>), [higher-education](<https://devfeed.tech/tags/higher-education.md>), [learning](<https://devfeed.tech/tags/learning.md>), [policy](<https://devfeed.tech/tags/policy.md>), [programming](<https://devfeed.tech/tags/programming.md>), [prompting](<https://devfeed.tech/tags/prompting.md>)

## AI overview

In a randomized trial with 431 students in an introductory programming course, four instructional approaches--from a two-sentence reminder to a multi-step constructive task--improved learning-oriented GenAI prompting. Gains persisted at a six-week follow-up and ranged from 8 to 51 percentage points, increasing with the approaches' designed engagement level. Students in all conditions reported continued voluntary use, and confidence grew alongside prompting skill. Final exam performance did not differ across conditions, so the reported gains did not translate into detectable achievement differences in this study.

## Source excerpt

arXiv:2602.16033v2 Announce Type: replace-cross Abstract: Generative artificial intelligence (GenAI) is now commonplace in higher education, yet unguided use can harm learning. Universities have responded with policies asking students to use GenAI for learning, not solutions, but how to translate these policies into classroom instruction remains untested. Here we report a randomized controlled trial with a six-week, end-of-semester follow-up (N = 431) in an introductory programming course comparing four instructional approaches, from a two-sentence reminder (Condition 1) to a multi-step constructive task (Condition 4). We found: (1) all four approaches produced learning-oriented prompting gains that persisted six weeks later and scaled with the designed engagement level, from 8 to 51 percentage points; (2) students in every condition self-reported sustained voluntary use, and confidence grew in step with skill; and (3) final examination performance did not differ between conditions, placing the possible boundary of the effects at the pathway from prompting skill to achievement. These findings provide instructors with an empirically calibrated set of options for translating GenAI-use policies into classroom practice.