Inspiration## Inspiration
Logistics in emerging markets, specifically in Colombia, faces a massive challenge: high failure rates in last-mile delivery and poor customer communication. We were inspired to build an AI-native solution that doesn't just track packages, but proactively resolves delivery exceptions and explains complex routing decisions to dispatchers in natural language.
What it does
LIS SAS (Logistics Operating System) is an end-to-end logistics platform. It features an AI Copilot powered by Gemini that can:
- Act as an autonomous customer service agent to reschedule failed deliveries.
- Analyze and explain VRP (Vehicle Routing Problem) optimization outputs to human operators.
- Track fleet operations in real-time.
How we built it
We are building the frontend with Next.js and React, relying on Supabase for our real-time database and auth. The core AI features are powered by the Gemini 1.5 Flash API, which processes operational logs and customer queries. The routing and heavy processing backend will be deployed on Google Cloud Run to ensure high availability and scalability.
Challenges we ran into
Integrating deterministic routing algorithms (VRP) with generative AI explanations, ensuring the AI agent doesn't hallucinate delivery status, and setting up a secure real-time sync between the database and the frontend dashboard.
What it does
How we built it
Challenges we ran into
Accomplishments that we're proud of
What we learned
What's next for LIS SAS - AI-Native Logistics Operating System
Built With
- gemini-api
- google-cloud
- next.js
- python
- react
- supabase
- tailwind-css
- typescript
Log in or sign up for Devpost to join the conversation.