--- title: "AI Coding Assistant · AI Fault Line" url: https://aifaultline.com/research/p/doi-10-5281-zenodo-23686381/ description: "AI Fault Line is a neutral, evidence-cited field guide to why experts looking at the same developments disagree about AI's effect on productivity, jobs, inequality, regulation and the pace of change." --- [Research](https://aifaultline.com/research/) # AI Coding Assistant DEEPAK N · Zenodo (CERN European Organization for Nuclear Research) · 27 Oct 2026 [Read original source](https://doi.org/10.5281/zenodo.23686381) Open access Where this sits in the debate - [Will AI actually boost productivity and growth?](https://aifaultline.com/debate/productivity/) · its finding: it depends ([why studies differ](https://aifaultline.com/debate/productivity/#why)) Direction of the finding as read from the abstract by an AI model ([AI-written](https://aifaultline.com/about/)). ## Abstract Artificial Intelligence (AI) coding assistants are transforming software development by helping programmers generate code, identify errors, debug programs, and improve development efficiency. Tools powered by large language models can provide real-time code suggestions, explain complex programming concepts, and automate repetitive coding tasks. However, their actual impact on software development productivity, code quality, and debugging efficiency requires careful evaluation. This research aims to examine the influence of AI coding assistants on software development productivity by considering factors such as programming task completion time, code correctness, maintainability, debugging effort, and developer experience. It explores the potential benefits and limitations of AI-assisted programming, including inaccurate code suggestions, security vulnerabilities, overreliance on generated code, and the need for human verification. The study will review existing research on AI-assisted software development and propose a comparative evaluation framework for traditional programming and AI-assisted programming. Relevant performance metrics and experimental procedures will be identified to assess productivity and code quality objectively. Where empirical data are available, the study will analyze the results to determine the conditions under which AI coding assistants may provide meaningful benefits. The findings are intended to support students, software developers, educators, and software engineering teams in understanding the effective and responsible use of AI coding assistants. The research will also identify limitations and opportunities for future investigation in AI-powered software development. ## About this publication **Preprint.** A preprint — posted publicly before or without journal peer review; findings may still be revised. Published 2026 (recently) Citations 0 (OpenAlex) 0 citations recorded by OpenAlex — too few 2026 papers in this collection for a fair comparison. [Chart: published 2026] ## More on this topic Related by theme, not necessarily by method or conclusion. - [Navigating the Jagged Technological Frontier: Field Experimental Evidence of the Effects of AI on Knowledge Worker Productivity and Quality](https://aifaultline.com/research/p/doi-10-2139-ssrn-4573321/) SSRN · 2023 - [Generative AI at Work](https://aifaultline.com/research/p/doi-10-1093-qje-qjae044/) The Quarterly Journal of Economics · 2025 - [The Impact of AI on Developer Productivity: Evidence from GitHub Copilot](https://aifaultline.com/research/p/doi-10-48550-arxiv-2302-06590/) arXiv · 2023 - [The Productivity J-Curve: How Intangibles Complement General Purpose Technologies](https://aifaultline.com/research/p/doi-10-1257-mac-20180386/) American Economic Journal Macroeconomics · 2020 Overview assembled automatically from collected metadata. [How this site is built](https://aifaultline.com/about/).