Article citationsMore>>

Patrick, L., Ethan, P., Aleksandra, P., Fabio, P., Vladimir, K., Naman, G., Heinrich, K., Mike, L., Wen-tau, Y., Tim, R., Sebastian, R. and Douwe, K. (2021) Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks.
https://arxiv.org/pdf/2005.11401

has been cited by the following article:

• TITLE: From Simple Apps to Systems: A Practical Framework for AI-Driven Software Development

  AUTHORS: Eliel Mathe, Benedict Mukanirwa

  KEYWORDS: Artificial Intelligence, Vibe Coding, Agentic AI, Software Development

  JOURNAL NAME: Journal of Computer and Communications, Vol.14 No.2, February 28, 2026

  ABSTRACT: This article examines the integration of artificial intelligence (AI) tools into software development, with a focus on optimizing workflows for computing professionals. Amid the rapid evolution of AI technologies, we review recent innovations—notably large language models (LLMs), neural networks, and transformers—along with their practical applications. We propose a structured methodology for incorporating these tools into software projects, addressing two primary challenges: managing costs associated with token consumption and enhancing context to reduce errors, commonly referred to as “hallucinations”. Approaches such as Retrieval-Augmented Generation (RAG) and the Model Context Protocol (MCP) are detailed for optimizing interactions with LLMs. Intended for developers, researchers, and novices alike, this work provides an overview of available tools and best practices for building robust, efficient applications, while emphasizing the importance of standardized project structures and team collaboration.