Manual task assignment in organizations is time-consuming, inconsistent, and leads to unbalanced workloads as team sizes grow. This paper presents an AI-driven intelligent task allocation system that automates the entire assignment process by integrating WhatsApp as the task submission interface with a Discord bot and Groq LLM. When a task message is received, the LLM evaluates the content, assigns a priority level, selects the most suitable worker from the Experts table in Supabase, and writes the structured record — containing task, priority, worker name, and worker email — directly into the Task table without any manual intervention. When all workers are occupied, the system identifies the worker nearest to completing their current task and assigns accordingly. A React frontend delivers role-specific dashboards, task tracking, pie chart reports, and inter-role chat for Super Admin, Admin, and Worker roles, while completed tasks are automatically archived into the CompletedTask table.
Automated Task Allocation, Groq LLM, Discord Bot Integration, WhatsApp Task Pipeline, Dynamic Workload Balancing, Role-Based Access, Priority Classification, Expert Matching System.
IRE Journals:
Elumalai A, Dr. Ponmozhi K "AI-Driven Intelligent Automated Task Allocation System Using Context Aware Decision Modeling And Dynamic Workload Management" Iconic Research And Engineering Journals Volume 9 Issue 9 2026 Page 2101-2108 https://doi.org/10.64388/IREV9I9-1715447
IEEE:
Elumalai A, Dr. Ponmozhi K
"AI-Driven Intelligent Automated Task Allocation System Using Context Aware Decision Modeling And Dynamic Workload Management" Iconic Research And Engineering Journals, 9(9) https://doi.org/10.64388/IREV9I9-1715447