System-driven Cloud Architecture Design Support with Structured State Management and Guided Decision Assistance

TL;DR

This paper introduces CloudArchitectBuddy, a system that supports cloud architecture design through structured state management and guided decision-making, improving usability and understanding for practitioners.

Contribution

The paper presents a novel system combining structured state management with guided decision assistance for cloud architecture design, validated through industry practitioner feedback.

Findings

Participants rated the system higher for usability.

The system helped understand architectural relationships.

Participants wanted more user-initiated interactions.

Abstract

Cloud architecture design is a complex process requiring both technical expertise and architectural knowledge to develop solutions from frequently ambiguous requirements. We present CloudArchitectBuddy, a system-driven cloud architecture design support application with two key mechanisms: (1) structured state management that enhances design understanding through explicit representation of requirements and architectural decisions, and (2) guided decision assistance that facilitates design progress through proactive verification and requirement refinement. Our study with 16 industry practitioners showed that while our approach achieved comparable design quality to a chat interface, participants rated our system higher for usability and appreciated its ability to help understand architectural relationships and identify missing requirements. However, participants also expressed a need for user-initiated interactions where they could freely provide design instructions and engage in detailed discussions with LLMs. These results suggest that integrating a chat interface into our structured and guided workflow approach would create a more practical solution, balancing systematic design support with conversational flexibility for comprehensive cloud architecture development.