Home / Projects / Dispatch Planning & Warehouse Optimization
Dispatch Planning & Warehouse Optimization
Project Overview
AI-powered MVP that takes a raw CSV of warehouse product data (weight, dimensions, fragility, priority, destination) and turns it into an optimized storage layout, full dispatch route plan, live cost breakdown, and real-time fleet tracking — all in one system. Ranked Top 5 of 850+ projects in Intel's AI for Manufacturing Program.
Project_Type
AI_OPTIMIZATION_MVP
Entry_Year
2025
Target_Platform
WEB
Primary_Role
AI_ENGINEER
Deployed_Technologies
Color_Palette
Project Walkthrough
A closer look at the finer details of this case study. Explore the core features, thoughtful design decisions, and interactive moments that shape the user experience.
[ Page_Index ]
- 01 // The Challenge
- 02 // Interactive Gallery
- 03 // The Solution
01 // The Challenge
The Challenge
Warehouses run this whole process by hand and in pieces: figuring out where a product should physically go based on its weight, size, and fragility; planning delivery routes and vehicle loads separately; and only tallying up the real cost after the fact. Nothing talks to anything else, so space gets wasted, routes are inefficient, and there's no single place to see the true cost of a day's operations. The brief was to build one AI system that could take raw product data and handle all of it — placement, dispatch, tracking, and cost — together.
02 // Interactive Gallery
03 // The Solution
The Solution
Built an AI-powered MVP where you upload a single CSV of warehouse product details — weight, length, width, height, fragility, destination, priority, dispatch date — and the system takes it from there. A storage-optimization engine suggests where each product should go, respecting configurable constraints like max weight, fragile-on-top, and priority-first, and visualizes the result as both a 2D top-down layout and a rotatable 3D warehouse view. A dispatch-planning engine then builds full delivery routes across the fleet, complete with per-route distance, duration, cost, and stop-by-stop breakdowns. A dynamic-optimization layer lets the system react in real time as goods are added or removed from stock. And an analytics layer rolls everything — performance history, cost breakdown by driver/fuel/operating cost, fleet utilization, route maps, and delivery-density heatmaps — into one dashboard. This MVP was ranked Top 5 of 850+ projects nationally in Intel's AI for Manufacturing Program, and I presented it to Intel Global Leadership, the Asia-Pacific & Japan Director, GTU's Vice Chancellor, and other senior GTU/Intel representatives.
Key_Contributions
Designed and built the full MVP end to end as part of Intel's Digital Readiness Program internship: the CSV-driven product intake, the 2D/3D storage-optimization engine and constraint system, the dispatch route planner and cost-breakdown analytics, and the real-time dynamic optimization layer for simulating live inventory events. Represented and presented the system to Intel Global Leadership, the Asia-Pacific & Japan Director, GTU's Vice Chancellor, and other senior GTU/Intel representatives after it was ranked Top 5 of 850+ submissions nationally in Intel's AI for Manufacturing Program.
Next_Project
WhatsApp Lead Qualification Bot