Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal The Eastasouth Journal of Information System and Computer Science
Chukkapalli, Divya
Unknown Affiliation
Computer Science & IT

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
APEX: Adaptive Personal EXperience Agents A Cost-Efficient, Privacy-Preserving Architecture for Scalable AI Assistants Pareek, Abhishek; Misra, Udit; Chukkapalli, Divya
The Eastasouth Journal of Information System and Computer Science Vol. 3 No. 03 (2026): The Eastasouth Journal of Information System and Computer Science (ESISCS)
Publisher : Eastasouth Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58812/esiscs.v3i03.935

Abstract

Personal AI agents deployed on user devices operate under fundamentally different constraints than shared cloud services. These systems must maintain conversation context across extended periods, function efficiently despite irregular usage patterns, handle complex requests, allocate computation intelligently, and protect sensitive data. We present APEX, an architecture addressing these five challenges through integrated design. APEX comprises five technical contributions: (1) a hierarchical memory system achieving 84% storage reduction through progressive compression; (2) a predictive activation mechanism reducing per-user compute costs by 73% while maintaining sub-5-second startup latency; (3) a task decomposition engine with 94% end-to-end accuracy; (4) a cost-aware routing layer reducing API consumption by 61%; (5) federated personalization enabling on-device learning while preserving privacy. Six-month production deployment reduced per-user monthly costs from $156 to $42 with positive user satisfaction scores, demonstrating practical efficiency at scale.
Co-Authors Misra, Udit Pareek, Abhishek