Case
Studies

Real systems. Real constraints.
Documented from problem through solution.

AI-Powered Individual Contribution Scoring for Team Software Projects | Final Year Research

Research · deep dives

AI-Powered Individual Contribution Scoring for Team Software Projects | Final Year Research

In team based software projects, every member usually receives the same grade regardless of who actually did the work. Instructors do not have time to manually review hundreds of commits, cross reference Scrum board activity, and judge code quality for every student in every sprint across ten or more teams. As a result, effort goes unmeasured and hard working students are graded the same as free riders.

An AI system that gives instructors a fair, evidence backed starting point for grading team projects in seconds instead of hours, while flagging at ri...
Building an AI Summarized Email Alert Workflow with Gmail, Gemini, and Telegram

Architecture · deep dives

Building an AI Summarized Email Alert Workflow with Gmail, Gemini, and Telegram

Important emails, like the Q3 Client Dashboard update shown in the New Event alert, get missed or read late when they sit in an inbox alongside routine messages. Checking Gmail manually does not scale, and a plain forwarding rule does not help either, since it copies the raw email without surfacing what actually matters in it. The goal for this specific workflow was to catch a new email the moment it arrives, extract the actual substance of it, and push that summary to the channels that get attention immediately, while still keeping a permanent record of what happened.

Since being built, this flow has executed 57 times with per run tracking, including a visible instance of the New Event alert firing correctly for an ...
When One Service Fails, the Rest Keep Running: The MediCare Architecture

Microservices · deep dives

When One Service Fails, the Rest Keep Running: The MediCare Architecture

Healthcare workflows span domains with very different failure tolerances. A payment failure needs careful, non silent handling, while a symptom checker being briefly unavailable is a minor inconvenience. Building this as a single application would mean every domain shares the same deployment cycle and the same blast radius when something breaks, so an outage in telemedicine could end up slowing down or taking down unrelated things like appointment booking or patient records.

The AI Symptom service can have its underlying third party provider swapped without touching any other service, and telemedicine session handling can ...
AI-Generated 3D Solar System

Python · deep dives

AI-Generated 3D Solar System

Representing multiple known objects (planets) with correct relative order and rough scale relationships, without manual placement.

The generated model came out mostly correct, with accurate planet ordering and reasonable relative scale, though not scientifically precise. It's curr...