Metraipolis › archive › dc_2b5504802406
Let the Agent Do It? How Software Practitioners Understand and Make Permission Decisions in Agentic AI Assistants — arXiv:2610.06047
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.06047
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:32:46.009Z
- SHA-256 of the archived text
636da4e27dc0d5a3e02b6de48913c3e9a30aa1da94d69490e232eb5a851933f1- Stable URL of this page
https://metraipolis.com/documento/dc_2b5504802406
How to cite
Let the Agent Do It? How Software Practitioners Understand and Make Permission Decisions in Agentic AI Assistants — arXiv:2610.06047 — arXiv, https://arxiv.org/abs/2610.06047 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2b5504802406 (Metraipolis archive dc_2b5504802406, sha256 636da4e27dc0d5a3e02b6de48913c3e9a30aa1da94d69490e232eb5a851933f1)
BibTeX
@misc{dc2b5504802406,
title = {Let the Agent Do It? How Software Practitioners Understand and Make Permission Decisions in Agentic AI Assistants — arXiv:2610.06047},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.06047},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2b5504802406; sha256 636da4e27dc0d5a3e02b6de48913c3e9a30aa1da94d69490e232eb5a851933f1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.06047. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic AI assistants increasingly act on developers' behalf by modifying files, executing commands, and accessing external resources. These actions often require permission, yet little is known about how practitioners make permission decisions while still benefiting from agent autonomy. To address this gap, we conducted a sequential mixed methods study, interviewing 18 practitioners who use AI agents and then surveying 115 practitioners based on the interview findings. We find that practitioners often understand agent behaviour through what they can directly observe and review, while decisions, data use, and other activity behind the scenes remain less clear. This uncertainty also shapes permission decisions, which depend on the scope and risk of an action, whether it fits the task, familiarity with the agent, and the environment in which it operates. Practitioners respond by adjusting how closely they oversee agents, from setting limits in advance to monitoring execution and reviewing work afterwards. How much scrutiny they apply depends on factors such as trust, task importance, time pressure, and the consequences of an action. Our findings suggest that permission systems should make consequential actions easier to review, distinguish what an agent is allowed to do from what the user intended, make reversibility clearer, avoid treating repeated approvals as stable preferences, and distinguish rejecting a single action from rejecting an entire approach. Tema degli esploratori: calcolo e infrastrutture (elenco arXiv cs.SE, nuovi lavori del giorno). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2610.06047 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-06T05:27:20.411Z dalla pagina https://arxiv.org/list/cs.SE/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).