Designing reviewable human–AI workflows for professional safety decisions
Authors:
- Ederson de Almeida PedroEPEderson de Almeida Pedro
- Mateus PanizzonMPMateus Panizzon
- Carine G. WebberCWCarine G. Webber
Preprint
- 17 October 2026
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
,AI assistance in professional work requires interfaces through which people can examine recommendations, determine their disposition, and preserve a record of that decision. Evaluating these interfaces is difficult when ostensibly similar logged actions have different meanings across tasks. We report a design science study of reviewable human–AI workflows in a Brazilian industrial safety platform. Formative interviews with nine professionals contextualized the design of task-specific evidence displays, intervention controls, manual alternatives, and linked decision records. A naturalistic evaluation examined 2,012 records from 65 users across 64 client accounts and six workflows between 24 April and 9 July 2026. The records contained 1,940 approvals, 23 edits, and 49 rejections; 97.6% of outputs were retained unchanged or after modification. All registered edits occurred in the textual practical-recommendation workflow. An earlier interface illustrated a consequential measurement difference: an unchanged saved text indicated retention, whereas a non-edited record in the later interface could indicate either approval or rejection. A separate risk-rating analysis reconstructed one professional override but largely comprised approval-defined value pairs. The contribution is a situated design account connecting task evidence, professional intervention, and retrospective review, together with an evaluation approach that interprets action metrics through the controls and recording rules that produce them. The findings establish deployed intervention opportunities and recorded use; they do not establish appropriate reliance, independent decision quality, or improved safety outcomes.Keywords
This publication has 14 references indexed in Scilit:
- Designing for human-centered AI—Lessons learned from a case study in the clinical domainInternational Journal of Human-Computer Studies, 2025
- Contestable AI by Design: Towards a FrameworkMinds and Machines, 2022
- Meaningful human control: actionable properties for AI system developmentAI and Ethics, 2022
- To Trust or to ThinkProceedings of the ACM on Human-Computer Interaction, 2021
- Human-Centered Artificial Intelligence: Reliable, Safe & TrustworthyInternational Journal of Human–Computer Interaction, 2020
- Principles alone cannot guarantee ethical AINature Machine Intelligence, 2019
- Explanation in artificial intelligence: Insights from the social sciencesArtificial Intelligence, 2019
- FEDS: a Framework for Evaluation in Design Science ResearchEuropean Journal of Information Systems, 2016
- Using thematic analysis in psychologyQualitative Research in Psychology, 2006
- Beyond Accuracy: What Data Quality Means to Data ConsumersJournal of Management Information Systems, 1996