[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84611-en":3,"doc-seo-84611-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},84611,1649267921044,"Ava Thompson","https://us-avatar.wpscdn.com/avatar/1800007509477c92dfb?_k=1782875107921204101",8,"Research & Report","Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering","Generative AI shifts software engineering economics from scarce implementation effort to abundant, low-cost code production, changing the core challenge from code usefulness to organizing architectures, tools, evidence, and feedback loops so AI-mediated development stays inspectable, correctable, and maintainable. A 12-week first-person case study uses frontier AI coding agents to build a document accessibility remediation system. The study analyzes 88 field notes and large code and test corpora to propose a governance-conversion model linking failure discovery to durable governance mechanisms and testable research implications.","Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering  \nJames C. Davis  \nPurdue University [davisjam@purdue.edu](davisjam@purdue.edu)  \nPaschal C. Amusuo  \nPurdue University [pamusuo@purdue.edu](pamusuo@purdue.edu)  \nTanmay Singla Purdue University [tsingla@purdue.edu](tsingla@purdue.edu)  \nBerk C¸ akar Purdue University [bcakar@purdue.edu](bcakar@purdue.edu)  \nKirsten A. Davis Purdue University [kad@purdue.edu](kad@purdue.edu)  \narXiv :2607 .0 1087v2 [ cs . SE] 4 Jul 2026  \nAbstract—Generative AI is shifting software engineering from a practice organized around scarce implementation effort toward one organized around abundant, low-cost code production. This shift changes the central engineering problem: not whether AI can generate useful code, but how engineers organize architectures, tools, evidence, and feedback loops so that AI-mediated development remains inspectable, correctable, and maintainable.  \nWe study this problem through a first-person case study: a 12-week development effort in which a single expert software engineer used frontier AI coding agents to build a document accessibility remediation system. The empirical record comprises 88 contemporaneous field notes, 420 KLOC of production code, and 1.16 MLOC of tests, lints, supporting documentation, and agent tooling. From this record, we develop a candidate middle-range theory of governance conversion, expressed as a process model explaining how high-velocity agentic implementation becomes governable. The model explains how agentic implementation velocity surfaces recurring structural failure classes, and how engineering judgment sustains velocity by converting those failures into durable governance mechanisms. In contrast to existing governance models that derive controls from known obligations, governance conversion explains how controls are discovered from failures that become visible only during agentic work. We use our model to make testable predictions and to describe implications for software engineering research and practice.  \nIndex Terms—Agentic Software Engineering, Case Study  \nI. INTRODUCTION  \nGenerative AI is changing the economics of software engineering [1] . Recent coding agents let us trade human time for LLM tokens [2] . Software engineers must steer and validate unreliable, non-deterministic agents [3] . The central problem is identifying engineering methods to make AI-mediated implementation governable at speed.  \nPrior work on AI-assisted software engineering has largely studied models, agents, and tools on bounded tasks such as code generation [4], debugging [5], and repair [6] . These studies show that agents can perform useful programming tasks and reshape developer workflows but provide limited evidence about end-to-end agentic software engineering processes. Meanwhile, industry reports show that software engineers are using AI agents [7],[8], sometimes resulting in major production outages [9],[10] . Existing accounts do not explain how agentic development can sustain governable velocity: human-supervised workflows preserve oversight by making human attention the bottleneck, while multi-agent workflows accelerate implementation with underspecified quality control.  \nWe study this problem through a 12-week first-person case study [11], [12] of agentic development. Here, the phenomenon of interest is not only the code produced by AI agents, but the situated sequence of judgments, controls, failures, and feedback loops through which agent-produced work was accepted, rejected, redirected, or converted into changes to the engineering environment. During the study period, a single expert software engineer used frontier AI coding agents to build a document accessibility remediation system. The empirical record includes 88 contemporaneous field notes, as well as design records, deployment data, and repository history. We analyze this record to learn: Can AImediated implementation be converted into governable softw","cbCaitH9OQPvVfz1","https://ap.wps.com/l/cbCaitH9OQPvVfz1","pdf",442758,2,1,13,"English","en",105,"# Introduction\n## Motivation and Research Gap\n## Case Study Approach\n## Governance Conversion Theory\n# Contributions\n## Process Model and Propositions\n## Empirical Evidence and Governance Mechanism Catalog","[{\"question\":\"What does the paper argue is the central challenge in AI-mediated software engineering?\",\"answer\":\"The challenge is not whether AI can generate useful code, but how engineers structure architectures, tools, evidence, and feedback loops so development remains inspectable, correctable, and maintainable at speed.\"},{\"question\":\"How is the case study conducted in the paper?\",\"answer\":\"It is a 12-week first-person case where a single expert software engineer used frontier AI coding agents to build a document accessibility remediation system, supported by contemporaneous field notes and repository and deployment records.\"},{\"question\":\"What is “governance conversion,” and how does it relate to failures?\",\"answer\":\"Governance conversion is a process model where agentic velocity exposes structural failure classes, engineering judgment interprets those failures, and new governance mechanisms encode that judgment into the engineering environment to constrain future agent work.\"}]",1784197111,33,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"cheap-code-costly-judgment-a-case-study-on-governable-agentic-software-engineering","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/cheap-code-costly-judgment-a-case-study-on-governable-agentic-software-engineering/84611/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What does the paper argue is the central challenge in AI-mediated software engineering?","Question",{"text":75,"@type":76},"The challenge is not whether AI can generate useful code, but how engineers structure architectures, tools, evidence, and feedback loops so development remains inspectable, correctable, and maintainable at speed.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"How is the case study conducted in the paper?",{"text":80,"@type":76},"It is a 12-week first-person case where a single expert software engineer used frontier AI coding agents to build a document accessibility remediation system, supported by contemporaneous field notes and repository and deployment records.",{"name":82,"@type":73,"acceptedAnswer":83},"What is “governance conversion,” and how does it relate to failures?",{"text":84,"@type":76},"Governance conversion is a process model where agentic velocity exposes structural failure classes, engineering judgment interprets those failures, and new governance mechanisms encode that judgment into the engineering environment to constrain future agent work.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]