Swastue Hackathon
Overview
The Tech Builder Program Hackathon Submission · Predictive Academic Planning with Multi-Agent Simulation · v3.5
The Challenge
University students face a critical challenge: they make major academic decisions (course load, study strategy, time allocation) with incomplete information about workload sustainability and burnout risk. Current tools—syllabi, course schedules, calendar applications—provide no predictive insight into whether a chosen study approach will succeed or lead to burnout. Key Pain Points: Impact: Over 60% of university students experience significant academic stress and burnout during their studies.
System Architecture
The Solution
SwastueAI addresses this problem through a multi-agent AI simulation platform that predicts academic outcomes and recommends optimal study strategies. Core Approach Three Independent AI Agents: Each agent models a distinct study strategy and simulates the entire semester independently: Automated Syllabus Intelligence: The platform uses LLM-powered parsing to extract course structure, assignments, deadlines, and workload distribution from PDF/CSV syllabi in seconds. No manual data entry required.
Key Features
- 1Consistent Agent
- 2Intensive Agent
- 3Balanced Agent
- 4GPA trajectory (cumulative grade impact)
- 5Stress levels (workload intensity, deadline clustering)
- 6Sleep hours (cognitive performance indicator)
Siap untuk memulai
proyek berikutnya?