Back to Publications

Engineering Cross-Compatible Personalization for Interactive AI-driven Services

Florian Müller, Andrii Matviienko, Alessandro Bozzon, Carmen Santoro, Larbi Abdenebaoui, Andrea Lavazza, Andreas Komninos, Nicolas Sklavos
EICS · Companion Proceedings of the 18th ACM SIGCHI Symposium on Engineering Interactive Computing Systems · 2026
PDF DOI
TL;DR
What we did: We conducted a workshop aimed at engineering cross-compatible personalization for interactive AI-driven services.
What we found: We discussed that creating user-sovereign representations and interoperable protocols can enhance user control over their digital self-representations in AI systems.
Takeaway: Our work contributes to establishing a framework that enables users to inspect, edit, and share their AI-driven profiles, addressing privacy concerns and fostering interoperability.

Abstract

AI-driven services continuously infer “models-of-users” to personalize content, automate decisions, and optimize interaction. Yet, most user models remain opaque, fragmented across platforms, and hard to correct, transfer, or revoke. As a result, personalisation in AI-driven services is commonly experienced as a trade-off between privacy and platform lock-in. Users must stay loyal to platforms if a model of adequate utility is to be built around them. This tension is sharpened by emerging regulatory obligations around transparency and user oversight (e.g., GDPR and the EU AI Act). We propose a full-day EICS 2026 workshop that focuses on \ emph engineering cross-compatible personalization : a vision for future interactive systems in which users can make their digital self-representations \ emph inspectable\textbraceright, \ emph editable\textbraceright, and \ emph selectively shareable\textbraceright. The workshop brings together researchers and practitioners from interactive systems engineering, HCI, AI/ML, and security/privacy to (1) map the design and engineering space of user-sovereign personalization; (2) derive reusable artifacts for the EICS community, such as a reference architecture, protocol sketches, and a pattern language of interaction techniques; and (3) seed a community around building interoperable toolchains for AI personalization that is not only accurate, but also controllable, auditable, and context-adaptive.