Blog

Writeups

How the AI systems on this site actually work, and the reasoning behind them.

An MCP server for ATS resume scoring, with no UI
ATS Resume Review MCP · 2026

An MCP Server for ATS Resume Scoring, With No UI

One tool, analyze_resume, meant to be called by an agent, not a person. The deterministic/LLM scoring split, and how it stays prompt-injection safe.

Verbatim
Verbatim · 2026

Someone asked Jinnah how big his pp was. Here is what a month of real questions taught me.

805 real conversations, 16 countries, and one bug I only found because I sat down and actually read the logs.

MediaPipe pose tracking driving a Unity Humanoid avatar
MediaPipe + Unity · 2026

Driving a Unity Humanoid Avatar with MediaPipe, No Depth Camera Required

Retargeting MediaPipe’s 3D pose landmarks onto a Humanoid Animator with Quaternion.FromToRotation, running entirely on-device through Unity Sentis. The approach, the calibration trap, and setup steps.

Keystone
Keystone · 2026

The Numbers in a Private Equity Deal Get Tested Systematically. The Reasoning Never Has.

Private equity has spent decades scrutinizing the model and waving the argument underneath it through. Large language models are the first thing capable of testing that reasoning with the same rigor.

Claude-e-Azam
Claude-e-Azam · 2026

I built an AI that answers as Muhammad Ali Jinnah, using only his own words.

Most of the work went into making sure it can't lie about him.