Projects
Tinkering log
Side projects born from real problems. Built to learn.
March 22, 2026/How do you evaluate a model that has no system prompt? I built an evaluation pipeline to find out.
ASR Evaluation Exploration
An evaluation framework for speech-to-text models and inference platforms, tested on code-mixed Indian banking audio across 7 providers and 4 deployment platforms.
March 1, 2026/Open-source ASR models hit 95%+ accuracy. So why does paid dictation software feel dramatically better?
Vox
A native macOS speech-to-text menu bar app, built to understand what makes great dictation software great.
February 22, 2026/Your AI conversations have a reasoning trace buried in them. What if you could go back and read it?
Claude QA Viewer
A zero-dependency tool that extracts AskUserQuestion interactions from Claude Code sessions and generates an interactive HTML visualization.
October 1, 2025/Manual ticket triage doesn't scale. What if an LLM could read every conversation thread for you?
Support signal
A Python tool that automates Zendesk ticket analysis using LLMs, turning weeks of manual triage into a 2-hour automated run.