期刊論文
| 學年 | 115 |
|---|---|
| 學期 | 1 |
| 出版（發表）日期 | 2026-10-15 |
| 作品名稱 | Trust, Gating, Delegation, and Identity: Human-Factor Dynamics in a 16-Month Single-Developer Trace of Generative-AI-Assisted Development |
| 作品名稱（其他語言） | |
| 著者 | Chen-Chung Chi |
| 單位 | |
| 出版者 | |
| 著錄名稱、卷期、頁數 | Information and Software Technology 201, p. 108351 |
| 摘要 | Context: Generative-AI coding assistants have moved rapidly into software development practice, raising human-factor questions about trust, usability, and responsible adoption that lab studies and surveys do not fully answer; sustained turn-by-turn production traces remain rare. Objective: This study examines four human-factor dimensions of sustained generative-AI-assisted development — trust calibration, developer gating, delegation-related prompt dynamics, and authorial identity — in a real production setting. Methods: Longitudinal autoethnography of a 16-month single-developer construction of a cloud-native institutional service at a Taiwanese university (424 git commits, Dec 2024–Apr 2026), with two prompt corpora across two IDE-mediated assistants used in succession: 172 user prompts plus 2777 assistant turns from CursorIDE (Sep–Dec 2025), and 50 user prompts from Claude Code CLI (Apr 2026). Per session formal indicators (Eqs. (1)–(5)), an analysis of a pre-stated directional prediction (Section 5.3), and triangulation with a companion architectural analysis (Chi, 2026) constrain interpretation. Results: (T) Trust calibration — in the trace-documented stuck-loop episode, the developer escalated model tier rather than revising specification (a capacity-oriented escalation). (G) Gating — the agent iteration ratio rises with task ambiguity, consistent with reduced developer gating of the agent loop when prompting is under- specified. (D) Delegation — within the Cursor window, prompt length compresses by up to 98.7% within a session (first to last third) while rewrite signals do not consistently decline, and prompt-skill improvement is not measurable under the study’s indicators, a pattern interpreted as consistent with a shift from prompting towards delegation rather than a direct measurement of it; in the later Claude Code window, 33 of 50 prompts are follow-ups (66%), a cross-tool observation reported descriptively. (I) Identity diffusion — authoring voice in commit messages converges towards the assistant’s register. Conclusion: Engineering throughput appeared to decouple from the developer-side communication indicators across the period; potential developer-side effects of sustained AI assistance may not register in conventional engineering metrics, supporting a cautionary reading for human-factor aware adoption. All quantitative magnitudes reported are observations from one case; the four dimensions are offered for analytical generalisation, as hypotheses for multi-developer studies to test, not as evidence of general developer behaviour. The article closes with responsible-adoption implications for IDE-assistant design. |
| 關鍵字 | Generative AI; Software engineering; Human factors; Trust calibration; Developer-side indicators; AI-assisted programming; Responsible adoption |
| 語言 | en_US |
| ISSN | 0950-5849 |
| 期刊性質 | 國外 |
| 收錄於 | SCI |
| 產學合作 | |
| 通訊作者 | Chen-Chung Chi |
| 審稿制度 | 否 |
| 國別 | USA |
| 公開徵稿 | |
| 出版型式 | ,紙本 |
| 相關連結 |
機構典藏連結 ( http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/129983 ) |