#ai

4 posts

Applied AI engineering: agents, LLM integration, and RAG — and what actually holds up in production versus what only works in a demo.

A Good SKILL.md Is the Cheapest Reliability Upgrade You'll Make
·7 min read

A Good SKILL.md Is the Cheapest Reliability Upgrade You'll Make

SkillSpector tells you whether a Claude Code skill is safe. Nothing told you whether it was any good, or how much its prose was costing you. So I built the quality layer and benchmarked it: across Haiku, Sonnet, and Opus, a strict schema and one worked example moved structured-output correctness from 0% to 100%.

Claude Code Best Practices for Vibe Coders: Ship More, Burn Fewer Tokens
·9 min read

Claude Code Best Practices for Vibe Coders: Ship More, Burn Fewer Tokens

Vibe coding with Claude Code is fast until the token bill isn't. After a year of daily use, I found the habits that fix both sides: the explore-plan-code workflow, path-scoped rules that trim CLAUDE.md by 60%, deterministic hooks that enforce guardrails at zero token cost, and the context tricks that keep long sessions from derailing.

AWS Summit Hamburg 2026: The Year Agentic AI Went from Hype to Production
·13 min read

AWS Summit Hamburg 2026: The Year Agentic AI Went from Hype to Production

From automotive supply chain AI to a self-healing enterprise HR platform: real companies, real results, and the honest questions still left open.

turbovec: Local RAG Without the 60 GB Tax
·7 min read

turbovec: Local RAG Without the 60 GB Tax

float32 embeddings eat RAM fast. turbovec cuts a 10M-doc corpus from ~60 GB to ~7.5 GB at 4-bit, with no training pass and unbiased similarity scores.