AI Agent Context Files in Practice: One Repo, Five Agents
I wrote about managing AI context files across multiple agents in theory. Here's how it actually plays out in a real project — a Jellyfin plugin where Kiro, Claude Code, Copilot, Gemini, and Codex all need to know the same things.
Testing a Machine-Readable Resume Against ATS Systems and AI Agents
I built a machine-readable resume view with JSON-LD and semantic HTML. Now I need to verify it actually works — against Google's validators, ATS resume parsers, and AI agents that recruiters are starting to use.
Managing Context and Rules Across Multiple AI Coding Assistants
Every AI coding assistant has its own proprietary rules format. Here's how to maintain a single source of truth that works across Amazon Q, Claude Code, GitHub Copilot, Cursor, Windsurf, Gemini, and the rest.
AI Coding Agent Context Files: A Reference Guide
A practical reference for the context and rules files used by every major AI coding assistant — Amazon Q, Claude Code, GitHub Copilot, Cursor, Windsurf, Gemini, Cline, Aider, and Kiro.
ASR with PyTorch
Exploring whether modern PyTorch ASR pipelines expose phoneme-level representations, using Wav2Vec 2.0 to extract and visualize phoneme probabilities from speech.