SHAPR: Operationalising Human-AI Collaborative Research Through Structured Knowledge Generation

Abstract

SHAPR (Solo Human-Centred and AI-Assisted Practice) is a framework for research software development that integrates human-centred decision-making with AI-assisted capabilities. While prior work introduced SHAPR as a conceptual framework, this paper focuses on its operationalisation as a structured, traceable, and knowledge-generating approach to AI-assisted research practice. We present a set of interconnected models describing how research activities are organised through iterative cycles (Explore-Build-Use-Evaluate-Learn), how artefacts evolve through development and use, and how empirical evidence is transformed into conceptual knowledge. Central to this process are Structured Knowledge Units (SKUs), which provide modular and reusable representations of insights derived from practice, supporting knowledge accumulation across cycles. The framework introduces evidence and traceability as a cross-cutting mechanism linking human decisions, AI-assisted development, and artefact evolution to enable transparency, reproducibility, and systematic refinement. SHAPR is also positioned as an AI-executable research framework, as its structured processes and documentation can be interpreted by generative AI systems to guide research workflows. Simultaneously, SHAPR supports a continuum of AI involvement, allowing researchers to balance control, learning, and automation across different contexts. Beyond individual workflows, SHAPR is conceptualised as an integrated research system combining LLM workspaces, development environments, cloud storage, and version control to support scalable, knowledge-centred research practices. Overall, SHAPR provides a practical and theoretically grounded foundation for conducting rigorous, transparent, and reproducible research in AI-assisted environments, contributing to the development of scalable and methodologically sound research practices.

Figures (6)

• Figure 1: SHAPR Conceptual Foundation. This figure illustrates the conceptual foundation of SHAPR, where solo research practice integrates human-centred decision-making and AI-assisted development. These components converge to produce practice-based artefacts that contribute to structured knowledge generation, highlighting SHAPR’s emphasis on human accountability supported by AI-assisted development.
• Figure 2: SHAPR Iterative Cycle (ADR-Aligned). This figure presents the iterative cycle underlying SHAPR, aligned with the build–intervene–evaluate logic of Action Design Research. The cycle captures the continuous interaction between human decision-making and AI-assisted development, supported by iterative refinement, and highlights how SHAPR operationalises cyclical research practice in AI-assisted environments.
• Figure 3: SHAPR Conceptual Foundation. This figure illustrates the conceptual foundation of SHAPR, where solo research practice integrates human-centred decision-making and AI-assisted development. These two components converge to produce practice-based artefacts that contribute to structured knowledge generation. The model highlights SHAPR’s emphasis on maintaining human accountability while leveraging AI to support development and exploration.
• Figure 4: SHAPR Workflow from Workspace to Repository. This figure illustrates the operational flow of SHAPR from the chat workspace through the SHAPR cycle to artefact development and repository storage. The SHAPR cycle (Explore–Build–Use–Evaluate–Learn) drives artefact evolution, while outputs are systematically captured in a repository containing code, cycle records, and structured knowledge units (SKUs), supporting traceability and knowledge accumulation.
• Figure 5: Artefact-to-Knowledge Transformation in SHAPR. This figure illustrates how SHAPR transforms empirical evidence into conceptual knowledge. The upper layer represents empirical evidence generated through research artefacts, while the lower layer represents conceptual knowledge, including insights, structured knowledge units (SKUs), and design principles. The branching structure highlights that knowledge generation is non-linear and can occur at multiple levels of abstraction.