# Where Accountability Lives: Mapping Human Responsibility to Workflow Artifacts in Agentic Software Development

arXiv: https://arxiv.org/abs/2608.15678 · HTML: https://mlsanity.com/paper/2608.15678/

## Key facts

- Cited by 1 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 16 of its 51 references that are in the map.
- First posted on arXiv 16 Aug 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, 16 of 16)

- [AIDev: Studying AI Coding Agents on GitHub](https://mlsanity.com/paper/2602.09185/) (2026)
- [Auditable Agents](https://mlsanity.com/paper/2604.05485/) (2026)
- [Automating Dependency Updates in Practice: An Exploratory Study on GitHub Dependabot](https://mlsanity.com/paper/2206.07230/) (2022)
- [An Empirical Study of Bots in Software Development -- Characteristics and Challenges from a Practitioner's Perspective](https://mlsanity.com/paper/2005.13969/) (2020)
- [Quality Gatekeepers: Investigating the Effects ofCode Review Bots on Pull Request Activities](https://mlsanity.com/paper/2103.13547/) (2021)
- [The Responsibility Vacuum: Organizational Failure in Scaled Agent Systems](https://mlsanity.com/paper/2601.15059/) (2026)
- [Accountable Agents in Software Engineering: An Analysis of Terms of Service and a Research Roadmap](https://mlsanity.com/paper/2605.04532/) (2026)
- [Proof of Execution: Runtime Verification for Governed AI Agent Actions](https://mlsanity.com/paper/2607.05397/) (2026)
- [On the Footprints of Reviewer Bots Feedback on Agentic Pull Requests in OSS GitHub Repositories](https://mlsanity.com/paper/2604.24450/) (2026)
- [Governed AI-Assisted Engineering: Graduated Human Oversight for Agentic Code Generation in Regulated Domains](https://mlsanity.com/paper/2606.22484/) (2026)
- [Quo Vadis, Code Review? Exploring the Future of Code Review](https://mlsanity.com/paper/2508.06879/) (2025)
- [Towards an Appropriate Level of Reliance on AI: A Preliminary Reliance-Control Framework for AI in Software Engineering](https://mlsanity.com/paper/2604.10530/) (2026)
- [From Trust to Appropriate Reliance: Measurement Constructs in Human-AI Decision-Making](https://mlsanity.com/paper/2604.23896/) (2026)
- [Rethinking Code Review in the Age of AI: A Vision for Agentic Code Review](https://mlsanity.com/paper/2605.17548/) (2026)
- [Redrawing the AI Map: A Theory of Accountability Boundaries in Agentic Ecosystems](https://mlsanity.com/paper/2605.23179/) (2026)
- [On Automated and Explainable Provenance of AI-Generated Code](https://mlsanity.com/paper/2608.02329/) (2026)

## Built on by (most cited first, 1 of 1)

- [From Traceability to Justifiability: Accountability Structures in Agentic Software Engineering](https://mlsanity.com/paper/2608.23610/) (2026)

## Abstract (arXiv)

Coding agents author commits, open pull requests and push code in production repositories. Responsibility is settled in two layers that do not refer to each other: platform controls gating what an agent may do, and provider terms allocating responsibility for its output. Objective: Where the two layers disagree at a workflow event, and what each states there about authority, execution, verification, consequence and record. Method: A qualitative document study of 121 items archived byte-exact: documentation for four agentic coding tools, the platform controls on their output, and eighteen policy documents from seven providers, read by deductive content analysis against an a-priori system of five dimensions and nine workflow events. An independent second coder blind-recoded the verification-mechanism classification, a complete enumeration and not a sample (Cohen's kappa 0.81, n = 13, on whether a mechanism compels; 0.75, n = 12, on who performs it). Results: Cursor's terms make the user responsible for evaluating the use of any suggestion; its documentation describes a product that performs that evaluation and records it as an approval. No collected artifact records that the verification the terms make the user's duty took place. At merge two tools compel a person, one documents an agent approving below a configured risk threshold, and one only advises. Six of the fifteen mechanisms that compel a check have a default the vendor states; nine have one this study inferred. Readers who had not made them refuted five of the eight absence claims; three survived, one materially qualified. Conclusions: The terms attach duty and consequence to output as a class, the platform records events, nothing records the duty discharged. One vendor documents a product that forms the approval judgement, and the terms allocate consequence against the artifact regardless.