Case Study

Saarthi AI

Saarthi AI predicts commute risk using live traffic, weather, events, and route signals with an explainable departure recommendation.

Open Live Demo View Code
Saarthi AI interface preview

Problem

The challenge

Commute planning is usually reactive. People see delays only after they are already in motion, and the reason behind lateness risk is rarely explained clearly.

Solution

What I built

I built an agentic commute intelligence workflow that combines live traffic, weather, local events, and route-risk signals to recommend when to leave and explain why.

Architecture

How it works

  • Multi-agent orchestration coordinates data gathering, risk analysis, and user-facing explanation.
  • Model Context Protocol workflows connect real-time APIs with persistent commute state in MongoDB Atlas.
  • The interface presents departure-vs-arrival tradeoffs with a concise risk breakdown.

Implementation

Project highlights

  • Built an agentic platform that estimates lateness risk and recommends optimal departure times.
  • Integrated live traffic, weather, events, route-risk signals, and MongoDB Atlas state.
  • Shipped an explainable risk score with a why breakdown and deployed it on Hugging Face Spaces.