DevCoach is presented as a reference architecture built on the Model Context Protocol to make GenAI assistance more lifecycle-aware, governable, and inspectable in organizational settings and reframes GenAI integration as a software engineering design and governance problem rather than a prompt-level optimization problem.
Abstract
The rapid, often unstructured adoption of Generative AI (GenAI) in software-intensive organizations creates a socio-technical challenge. While GenAI can accelerate individual tasks, these gains are often offset by added coordination, verification, and governance effort across the software development lifecycle (SDLC). This paper presents DevCoach as a reference architecture built on the Model Context Protocol (MCP) to make GenAI assistance more lifecycle-aware, governable, and inspectable in organizational settings. DevCoach treats model outputs as proposals rather than authoritative actions, and couples generation to lifecycle-scoped retrieval, bounded tool use, deterministic validation, and provenance-linked audit artifacts. Its core mechanism is two Context Refinement Loops (CRLs): CRL 1 stabilizes user intent into an explicit retrieval contract, and CRL 2 performs bounded retrieval, evidence verification, and provenance construction to produce a verified context pack. The contribution is therefore architectural and design-oriented rather than a benchmarked implementation study. In this way, the paper reframes GenAI integration as a software engineering design and governance problem rather than a prompt-level optimization problem.
API performance testing is often introduced informally and remains dependent on individual expertise, which limits reuse and makes results difficult to repeat. This paper presents a lightweight framework and repository approach. It helps organizations establish a repeatable API performance testing process and capture knowledge for reuse. Using a Design Science Research (DSR) approach, a Knowledge-Centric API Performance Testing Framework with six components was developed: Scope & SLOs, Environment Setup, Data Preparation, Execution & Metrics, Analysis & Reporting, and Knowledge Capture & Sharing. A key distinguishing feature of the framework is its explicit inclusion of non-technical roles (e.g., Business Analysts and Product Owners), enabling them to contribute to performance testing through structured involvement in scope definition, governance, and knowledge capture. The framework was applied in a global IT organization during an initiative to validate API performance after a data source change. The case shows that a structured workflow and shared artefacts reduce repeated effort and support cross-functional collaboration. The paper contributes (1) a practical framework for organizations introducing API performance testing from scratch and (2) a knowledge management framing that treats performance testing outputs as reusable organizational assets.
Inga Zilinskiene· European Conference on Knowl...· 0 citations
: Industrial cyber-physical systems rely on structured safety lifecycle in which hazards, risks, requirements, architecture, and verification activities are related across defined phases. In practice, these elements are distributed across heterogeneous documents, making structural consistency and traceability difficult to maintain. This paper presents an approach in which lifecycle elements are encoded as structured documentation artifacts with explicit types and relations. From a data-centric perspective, these artifacts are treated as structured data objects whose relations form a constrained graph representation of lifecycle information. A controlled vocabulary and constrained relations define a consistent representation of lifecycle data. The artifacts are processed through a documentation build workflow that acts as a deterministic data processing and validation pipeline, automatically generating traceability views and completeness checks. Structural constraints over artifact relations cover verification, evidence linkage, SIL allocation, and hazard coverage. The approach is demonstrated on a reproducible IEC 61508 SIL 2 Emergency Stop example, with an open demo site and repository that provide all sources and build scripts. Violations introduced by removing required relations are detected as non-empty coverage tables. The results show that lifecycle integrity can be evaluated as a structural property of the artifact graph, enabling early, machine-checkable detection of missing relations.
Padma Iyenghar, Christopher Zimmerman, C. Gregorio· Proceedings of the 15th Inte...· 0 citations
User experience (UX) evaluation is central to software quality, yet it remains difficult to integrate into software engineering workflows in a systematic, explainable, and early-stage manner. This paper presents TraceUX, a framework for operationalizing UX heuristics and design guidance into a rule-based static evaluation pipeline that combines machine-interpretable formalization, executability-aware assessment, context-sensitive scoring, and actionable reporting. The framework is instantiated using Apple Human Interface Guidelines, Swift abstract syntax trees, and mobile games, and implemented in a proof-of-concept tool named TraceHIG. Evaluation was conducted in four layers: analysis of the full rule repository, controlled synthetic validation with injected violations, baseline assessment of 12 public Swift game projects, and a case study on one project. The full repository contained 206 rules; after excluding non-iOS yet platform-specific rules, 193 rules were retained for the downstream experiments. In controlled validation, 216 injected violations yielded 99.2% precision, 61.6% recall, and an F1-score of 0.760. In baseline analysis, overall project scores ranged from 41.6 to 88.0, reflecting rule-conformance spread under the instantiated rule base rather than direct measures of UX quality. The case study demonstrated that profile-aware scoring can yield materially different UX assessments for the same codebase under different game configurations, highlighting the importance of app profiling in static UX evaluation. These findings show that a meaningful subset of UX knowledge can be operationalized into explainable, context-aware static analysis that provides structured and actionable decision support while complementing, rather than replacing, manual and empirical UX evaluation.
Large language models are increasingly used to review, clarify, rewrite, and trace software requirements. These applications create a governance problem that output-quality assessment alone cannot resolve: a fluent proposal may rely on inadmissible evidence, alter stakeholder intent, introduce unsupported specificity, or imply an organizational commitment that the model has no authority to make. Existing work on retrieval-augmented generation, controlled natural language, formal verification, human oversight, and AI governance supplies relevant controls, but it does not specify the procedural status of an individual LLM proposal relative to a controlled requirements artifact. This article develops an artifact-centered, human-in-the-loop framework in which the permitted influence of a proposal is the primary object of governance. The framework combines five governance functions—governed evidence, bounded context construction, controlled LLM analysis, pre-commit verification, and accountable human approval—with four artifact-influence states: A0 advisory observation, A1 evidence-linked candidate, A2 verified recommendation, and A3 approved and committed change. Its central theoretical claim is that output quality, evidential legitimacy, verification status, and authority to commit a change are distinct properties and should not be collapsed into a single confidence judgment. Seven falsifiable hypotheses translate the model into measurable comparisons involving source admissibility, context leakage, unsupported specificity, semantic drift, reviewer agreement, unreviewed changes, governance cost, and organizational maturity. Human review is treated as both a necessary decision boundary and a potential source of automation bias, anchoring, and fatigue. The framework is conceptual rather than empirically validated and provides a basis for controlled experiments, field studies, and longitudinal evaluation.
Chuanjin Zhu· Advances in Engineering Inno...· 0 citations
The increasing adoption of hybrid and remote work has reshaped how software teams communicate, collaborate, and make design decisions. Our prior study showed that hybrid setups often result in missed discussions, fragmented understanding, and limited documentation of design rationale. At the same time, Generative AI (GenAI) tools–such as GitHub Copilot and ChatGPT–are becoming embedded in development workflows, providing support in code generation. While GenAI’s role in software development is gaining attention, its impact on early-stage design ideation activities and collaboration in hybrid teams remains underexplored. This paper builds on earlier findings to propose a forward-looking vision of GenAI as an instant, readily available co-developer in hybrid software design. We revisit documented challenges from our earlier study on hybrid collaboration and outline how GenAI could address these issues by facilitating asynchronous participation, surfacing undocumented rationale, and preserving design continuity. We present a conceptual framing of GenAI-supported collaboration and propose a research agenda to guide future studies on integrating GenAI into hybrid settings.
Mahum Adil, I. Fronza, T. Mikkonen et al.· International Conference on...· 0 citations
Enterprise front-end development at scale is characterized by a persistent tension between the need for organizational consistency and the demand for product-team autonomy. Left unresolved, this tension produces fragmented codebases, duplicated infrastructure decisions, inconsistent security postures, and compounding onboarding costs. Application generators address this problem by encoding architectural standards, security defaults, and delivery contracts directly into the project creation process. Rather than relying on documentation and developer discipline to propagate platform conventions, generators make correct behavior the automatic outcome of project initialization. This article examines application generators as first-class platform infrastructure across their full operational lifecycle. The scope covers scaffold design and baseline contract definition, governance and security enforcement through generated defaults, extensibility architecture that preserves product-team autonomy without sacrificing platform coherence, pipeline and observability integration, developer experience as a technical requirement, shared asset distribution, and the governance models required to prevent generator sprawl. The article further addresses the implications of AI-assisted development for generator design, arguing that embedded static analysis and dependency governance become especially critical as AI-generated code enters enterprise codebases at an increasing rate. The article establishes that generator value is not realized at project creation alone. It builds up over time through consistent delivery pipelines, less time spent on compliance remediation, faster onboarding, and measuring at the portfolio level. Sustaining that value requires treating the generator as a versioned, owned, and actively maintained platform product, governed by the same rigor applied to the applications it produces.
Anilraj Chennuru· International journal of com...· 0 citations