A Python-Based AI Virtual Assistant for Task  Automation

Author(s)	Priyanka Lanjewar, Ankita S. Nathe, Dhanshri Lanjewar, Vaishanavi Biradar, Ananta Gole, Nikhil Gade
Country	India
Abstract	Recent advances in Artificial Intelligencehave enabled the widespread adoption of voice-basedvirtual assistants for desktop automation and human–computer interaction. However, most existingassistants rely heavily on continuous internetconnectivity, raising concerns related to latency, privacy,and reliability in low-connectivity environments. Thispaper presents Cosmo, a Python-based AI virtualassistant that employs an adaptive hybrid architecturecapable of dynamically switching between online andoffline processing modes. In online mode, Cosmoleverages large language models (LLMs) through cloudAPIs for complex conversational tasks, while in offlinemode it utilizes lightweight local speech recognition and text-to-speech engines to ensure uninterruptedfunctionality. Experimental evaluation demonstratesthat the proposed hybrid approach improves responsereliability and reduces average task latency duringnetwork failures while maintaining acceptable accuracy.The results indicate that Cosmo provides a practical,privacy-aware solution for desktop automation,education, and productivity applications.
Keywords	AI Virtual Assistant, Hybrid Architecture, Offline Speech Recognition, Desktop Automation, Human–Computer Interaction, Privacy- Aware Systems
Published In	Volume 7, Issue 3, May-June 2026
Published On	2026-05-22

About AIJFR Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us		+91-9898-79-39-59	editor@aijfr.com

Advanced International Journal for Research