Insights
Field notes from production
If it's here, it's because I used it, tested it, or watched it fail and wanted to write down why.
VideoWatch the video20 min watchKarpathy's LLM Knowledge Base, Wired Into a Real Agent
How to build Karpathy's LLM knowledge base into a production AI agent using Claude Code plan mode, an Obsidian vault, and a local LLM.
claude-codeskillsplan-mode
ArticleRead more12 min readGoverning AI Agents Without Killing Them: What Actually Works in Production
Most AI agent governance advice targets boards, not builders. Three failure patterns, real TypeScript examples, and what a CTO should do Monday morning.
ai-agentsagent-architectureproduction-ai
VideoWatch the video22 min watchThe Quality Loop Your AI Agent Is Missing (Evals + Tracing)
Add an LLM-as-judge scorer to a Mastra agent, catch a fabricated action item your tests would never flag, and fix the prompt — no custom infra.
evalsobservabilityagent-quality
ArticleRead more12 min readAdding Audio Narration Revealed the Bugs in My Writing
How I added ElevenLabs TTS audio narration to my Hugo blog, cloned my own voice, and discovered my writing had patterns no voice model could read.
elevenlabstext-to-speechhugo
VideoWatch the videoThe Observability Layer Your AI Agent Is Missing
Logs tell you what happened. Traces tell you why. The three layers of agent observability, and where silent failures actually live.
observabilityagent-architectureproduction-ai
VideoWatch the videoAI Agent Evals: The 4 Layers Most Teams Skip
Most teams evaluate AI agents by vibes. Here are the four layers of evals you actually need to ship agents with confidence.
evalsagent-architectureproduction-ai- ArticleRead more10 min read
Shrinking a Production Prompt by 28% With Autonomous Optimization
How I used autoresearch to run 65 autonomous prompt optimization iterations on a production LLM agent, cutting it 28% while retaining 98% output quality.
ai-agentsproduction-aievaluation 
VideoWatch the videoI Gave My AI Agent Access to My Second Brain
What happens when you wire an AI agent directly into your Obsidian vault? Here's the setup I use to turn notes into real leverage.
obsidianagent-architecturememory-systems- ArticleRead more14 min read
Four Dimensions of Agent-Ready Codebase Design
AI agents produce better output when the codebase is ready for them. Here are the four dimensions of codebase readiness that account for most of the gap.
ai-agentscodebase-readinessclaude-code
Nothing matches those filters.