A comprehensive survey on AI-powered desktop automation (COSMO)

This paper presents an overview of AI-powered desktop automation and its evolution toward intelligent assistants capable of performing real-time tasks using natural language interaction. COSMO (Conversational Smart Machine Operator) is a lightweight desktop assistant designed to execute system-level operations, manage files, interact with external APIs, and enhance user productivity. Existing intelligent assistants, RPA tools, and NLP-driven automation systems are reviewed to identify persistent challenges such as UI variability, noise, and dependence on cloud APIs, and to motivate COSMO's design choices that favor local execution, privacy, and modularity.