AGENTIC AI FOR PERSONALIZED INTELLIGENT WORKFLOW MANAGEMENT: LOW CODE AI APPROACH

Abstract

Nowadays, the use of AI has become essential for enhancing adaptability and efficiency. This study contributes to this objective by proposing an agentic AI system based on a Low Code and No Code (LCNC) approach for personalised intelligent workflow management. The developed agentic AI integrates Large Language Models (LLMs) with personalised diary tools using a low-code development platform, enabling intelligent workflow management and task creation through visual interfaces. The system consolidates user tasks from multiple platforms into a single interface. Leveraging LLM-based reasoning capabilities, it detects scheduling conflicts, evaluates contextual factors such as urgency and priority, and autonomously selects appropriate actions without requiring manual intervention. The use of a LCNC platform simplifies system development and improves accessibility for non-technical users, bridging the gap between personalised user needs and technical execution. Preliminary results indicate that the proposed system can accurately handle diverse scheduling scenarios and make human-like decisions in real-world contexts.

This document is currently not available here.

Share

COinS