Vikrant Kaulgud

Priyavanshi Pathania, Rohit Mehra, Vibhu Saujanya Sharma et al.

Large Language Models are rapidly gaining traction in software engineering, yet their growing carbon footprint raises pressing sustainability concerns. While training emissions are substantial, inference quickly surpasses them due to the sheer volume of prompts processed. This shift underscores the urgent need for accurate, prompt-level carbon measurement during inference to enable informed, sustainability-focused decision-making. To address the limitations of existing approaches, in this paper, we outline the guiding principles for a novel reference framework for LLM inference carbon estimation that can guide the design of future tools and provide a systematic foundation for advancing sustainability research in this domain. We also introduce SEAL, an early embodiment of these principles that leverages a multi-benchmark-driven approach for per-prompt carbon estimation. Its initial validation shows promising results, positioning SEAL as a foundation for standardized sustainability assessment across the LLM ecosystem.

Rohit Mehra, Samdyuti Suri, Prithviraj K Tagadinamani et al.

AI coding agents are rapidly reshaping how software is built, with developers increasingly delegating substantial coding tasks to autonomous agents in pursuit of higher productivity. While these gains are real, they come at the cost of incidental learning. Developers historically acquired informal knowledge through effortful problem-solving, and this has long shaped how software engineering expertise develops. However, with over-reliance on agentic coding, unpracticed skills could atrophy silently over time. As this learning pathway is short-circuited, developers risk silently accruing Knowledge Debt, a developer-level analogue of Technical Debt, where changes the agent executes that the developer cannot fully understand accrue over time. In this paper, we argue that incidental learning will not re-emerge on its own and must be consciously designed back into developer-agent interactions, and propose six design principles to guide such systems. We then present "SHIELD", a multi-agent system grounded in the notion of "agents that teach", that operationalizes these principles by leveraging the AI coding agent's own reasoning to surface contextual, out-of-band learning moments without disrupting developer flow. Through this work, we envision a path toward learning-aware development environments where productivity and learning are complementary, not competing.

Rohit Mehra, Kapil Singi, Vikrant Kaulgud et al.

Prompt engineering has emerged as a critical yet undertaught skill for software developers, one that traditional learning approaches are ill-equipped to support given its evolving, interactive, and context-dependent nature. In this paper, we introduce Prompt Coach (PC), an agentic tutor that helps developers learn how to craft high-quality code-generation prompts through Socratic guidance embedded in-flow within their IDE. PC evaluates prompt quality across multiple dimensions and surfaces targeted questions to guide self-correction, grounded in the developer's codebase and the behavior of the target LLM. We present an early empirical study with 15 professional developers combining quantitative prompt quality scoring with qualitative perception measures. Participants showed statistically significant improvements after a single 60-minute session, with the largest gains across dimensions commonly overlooked by developers. They also reported strong trust, high adoption readiness, and unanimous agreement that PC improved their prompt-writing skills.

Janardan Misra, Vikrant Kaulgud, Adam Burden et al.

Build-versus-buy decisions remain a persistent challenge in enterprise software development, shaped by competing strategic, technical, cost, and risk considerations. The increasing availability of third-party solutions alongside the growing feasibility of custom development through cloud-native technologies, APIs, and low-code platforms has further amplified the complexity of these decisions. In practice, organizations often rely on fragmented expertise and informal reasoning, making it difficult to systematically analyze trade-offs or justify decisions over time. This paper presents a structured decision-support approach designed to augment build-versus-buy decision-making in such contexts. The approach is grounded in an ontology of decision factors spanning strategic considerations, application characteristics, cost and budget constraints, and risk dimensions. It combines this factor model with rule-based reasoning and reference-level matching to support decision-making even in cold-start scenarios where historical data is unavailable. The approach is implemented as a lightweight advisory artifact that enables users to evaluate relevant factors, explore trade-offs, and derive recommendations with transparent reasoning. The applicability of the approach is illustrated through a finance domain case, demonstrating how structured factor analysis can clarify decision rationale and highlight conditions under which decisions may change over time. The results suggest that making decision criteria explicit and systematically comparable can improve the quality, transparency, and auditability of build-versus-buy decisions in enterprise settings.

Samarth Sikand, Rohit Mehra, Vibhu Saujanya Sharma et al.

Software sustainability is emerging as a primary concern, aiming to optimize resource utilization, minimize environmental impact, and promote a greener, more resilient digital ecosystem. The sustainability or "greenness" of software is typically determined by the adoption of sustainable coding practices. With a maturing ecosystem around generative AI, many software developers now rely on these tools to generate code using natural language prompts. Despite their potential advantages, there is a significant lack of studies on the sustainability aspects of AI-generated code. Specifically, how environmentally friendly is the AI-generated code based upon its adoption of sustainable coding practices? In this paper, we present the results of an early investigation into the sustainability aspects of AI-generated code across three popular generative AI tools - ChatGPT, BARD, and Copilot. The results highlight the default non-green behavior of tools for generating code, across multiple rules and scenarios. It underscores the need for further in-depth investigations and effective remediation strategies.