# Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering arXiv: https://arxiv.org/abs/2607.01087 ยท HTML: https://mlsanity.com/paper/2607.01087/ ## Key facts - Cited by 2 papers in the map (data through 14 Oct 2026). - Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. - Builds on 40 of its 89 references that are in the map. - First posted on arXiv 1 Jul 2026. ## Placed in - LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/) ## Builds on (most cited first, 30 of 40) - [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023) - [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023) - [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023) - [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023) - [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024) - [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023) - [CodeAgent: Enhancing Code Generation with Tool-Integrated Agent Systems for Real-World Repo-level Coding Challenges](https://mlsanity.com/paper/2401.07339/) (2024) - [SWE-Bench Pro: Can AI Agents Solve Long-Horizon Software Engineering Tasks?](https://mlsanity.com/paper/2509.16941/) (2025) - [AutoCodeRover: Autonomous Program Improvement](https://mlsanity.com/paper/2404.05427/) (2024) - [An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation](https://mlsanity.com/paper/2302.06527/) (2023) - [Trace2Skill: Distill Trajectory-Local Lessons into Transferable Agent Skills](https://mlsanity.com/paper/2603.25158/) (2026) - [Measuring AI Ability to Complete Long Software Tasks](https://mlsanity.com/paper/2503.14499/) (2025) - [LLM-Based Multi-Agent Systems for Software Engineering: Literature Review, Vision and the Road Ahead](https://mlsanity.com/paper/2404.04834/) (2024) - [ProSA: Assessing and Understanding the Prompt Sensitivity of LLMs](https://mlsanity.com/paper/2410.12405/) (2024) - [Agentic Harness Engineering: Observability-Driven Automatic Evolution of Coding-Agent Harnesses](https://mlsanity.com/paper/2604.25850/) (2026) - [A Survey on Code Generation with LLM-based Agents](https://mlsanity.com/paper/2508.00083/) (2025) - [The Illusion of Diminishing Returns: Measuring Long Horizon Execution in LLMs](https://mlsanity.com/paper/2509.09677/) (2025) - [Exploring LLM-based Agents for Root Cause Analysis](https://mlsanity.com/paper/2403.04123/) (2024) - [AgentRx: Diagnosing AI Agent Failures from Execution Trajectories](https://mlsanity.com/paper/2602.02475/) (2026) - [ProgramBench: Can Language Models Rebuild Programs From Scratch?](https://mlsanity.com/paper/2605.03546/) (2026) - [Evaluating Agent-based Program Repair at Google](https://mlsanity.com/paper/2501.07531/) (2025) - [What Prompts Don't Say: Understanding and Managing Underspecification in LLM Prompts](https://mlsanity.com/paper/2505.13360/) (2025) - [Vibe coding: programming through conversation with artificial intelligence](https://mlsanity.com/paper/2506.23253/) (2025) - [From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws](https://mlsanity.com/paper/2606.06324/) (2026) - [The Current Challenges of Software Engineering in the Era of Large Language Models](https://mlsanity.com/paper/2412.14554/) (2024) - [Runtime Governance for AI Agents: Policies on Paths](https://mlsanity.com/paper/2603.16586/) (2026) - [What Do We Mean by "Accessibility Research"? A Literature Survey of Accessibility Papers in CHI and ASSETS from 1994 to 2019](https://mlsanity.com/paper/2101.04271/) (2021) - [Context Engineering for AI Agents in Open-Source Software](https://mlsanity.com/paper/2510.21413/) (2025) - [A Study on Developer Behaviors for Validating and Repairing LLM-Generated Code Using Eye Tracking and IDE Actions](https://mlsanity.com/paper/2405.16081/) (2024) - [AI IDEs or Autonomous Agents? Measuring the Impact of Coding Agents on Software Development](https://mlsanity.com/paper/2601.13597/) (2026) ## Built on by (most cited first, 2 of 2) - [Specification-first convergence with an AI coding agent: a case study of dismantling a core architectural invariant across 189 files in a 717k-line codebase with no test oracle and no human code review](https://mlsanity.com/paper/2608.12440/) (2026) - [From Agent Output to Authorized Transition](https://mlsanity.com/paper/2609.28216/) (2026) ## Abstract (arXiv) 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. We 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.