The Expert Validation Framework (EVF): Enabling Domain Expert Control in AI Engineering
Paper in proceeding, 2026

Generative AI (GenAI) systems promise to transform knowledge work by automating a range of tasks, yet their deployment in enterprise settings remains hindered by the lack of systematic quality assurance mechanisms. We present an Expert Validation Framework that places domain experts at the center of building software with GenAI components, enabling them to maintain authoritative control over system behavior through structured specification, testing, validation, and continuous monitoring processes. Our framework addresses the critical gap between AI capabilities and organizational trust by establishing a rigorous, expert-driven methodology for ensuring quality across diverse GenAI applications. Through a four-stage implementation process encompassing specification, system creation, validation, and production monitoring, the framework enables organizations to leverage GenAI capabilities while maintaining expert oversight and quality standards.

domain expert control

quality assurance

AI engineering

expert validation

GenAI

Author

Lucas Gren

Getinge Group

Chalmers, Computer Science and Engineering (Chalmers), Software Engineering (Chalmers)

University of Gothenburg

Felix Dobslaw

Mid Sweden University

Proceedings 2026 IEEE ACM 5th International Conference on AI Engineering Software Engineering for AI Cain 2026

304-308
9798400724756 (ISBN)

5th IEEE International Conference on AI Engineering - Software Engineering for AI, CAIN 2026
Rio de Janeiro, Brazil,

Subject Categories (SSIF 2025)

Computer Sciences

Security, Privacy and Cryptography

Artificial Intelligence

DOI

10.1145/3793653.3793796

More information

Latest update

10/12/2026