Tarun Upadhyay.

Projects

A few things I have built.

Some started with a work problem. Others started with a camera, a pillbox, or a student's question.

The projects here are the ones I return to. The rest of the code is on GitHub.

What I am testing

I care less about a demo than whether the software removes a real task.

Current experiments cover phone calls, email, reconciliation, travel policy, computer vision, and the points where a person needs to take over.

Travel and agents

Google Flights Policy Recommender

Prototype

A policy-aware flight-search MCP server.

It searches Google Flights, labels results as in-policy or out-of-policy, and ranks them by preferences such as nonstop travel, airline alliance, price, duration, and red-eye avoidance.

The hosted version returns ranked choices and sends the traveler to Google Flights. A browser-driven version stops at the payment step. It does not buy a ticket.

Traveler / Claude MCP server policy + preferences (Cloud Run) Google Flights search results Policy engine in / out of policy Ranked, labeled results → Google Flights to book
Repository

Computer vision and education

Pillbox

Student project

A Raspberry Pi camera and computer-vision system built with a student in the Up Robotics program.

A small CNN identifies which of 21 pillbox cells still contain pills: seven days, with morning, noon, and night for each day.

The project combines hardware, image capture, remote access, model inference, and a simple status interface.

Pi camera weekly pillbox photo, on demand CNN model on-device inference 7 days × 3 periods status grid, browser
Repository    Training data

Home systems

Network, cameras, and automation

My home network and cameras are useful because they fail in ordinary ways. I use them to understand what happens when several products, protocols, and failure modes meet.

The working code is on GitHub.