From Challenge to Change: Design Principles for AI Transformations

TL;DR

This paper introduces a human-centric framework based on behavioral principles to guide software engineering organizations through early AI adoption, emphasizing strategy, collaboration, and up-skilling.

Contribution

It presents a novel, actionable framework informed by behavioral insights, literature review, and practitioner input to support human-centered AI integration in software engineering.

Findings

Organizations prioritize strategy design and up-skilling in early AI adoption.

Current practices focus more on procedural elements than human-centered guardrails.

Practitioner feedback highlights the need for real-world grounded guidance.

Abstract

The rapid rise of Artificial Intelligence (AI) is reshaping Software Engineering (SE), creating new opportunities while introducing human-centered challenges. Although prior work notes behavioral and other non-technical factors in AI integration, most studies still emphasize technical concerns and offer limited insight into how teams adapt to and trust AI. This paper proposes a Behavioral Software Engineering (BSE)-informed, human-centric framework to support SE organizations during early AI adoption. Using a mixed-methods approach, we built and refined the framework through a literature review of organizational change models and thematic analysis of interview data, producing concrete, actionable steps. The framework comprises nine dimensions: AI Strategy Design, AI Strategy Evaluation, Collaboration, Communication, Governance and Ethics, Leadership, Organizational Culture, Organizational Dynamics, and Up-skilling, each supported by design principles and actions. To gather preliminary practitioner input, we conducted a survey (N=105) and two expert workshops (N=4). Survey results show that Up-skilling (15.2%) and AI Strategy Design (15.1%) received the highest $100-method allocations, underscoring their perceived importance in early AI initiatives. Findings indicate that organizations currently prioritize procedural elements such as strategy design, while human-centered guardrails remain less developed. Workshop feedback reinforced these patterns and emphasized the need to ground the framework in real-world practice. By identifying key behavioral dimensions and offering actionable guidance, this work provides a pragmatic roadmap for navigating the socio-technical complexity of early AI adoption and highlights future research directions for human-centric AI in SE.