#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.

·16 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, CLAUDE.md rules trimmed 60 percent without losing coverage, hooks that enforce guardrails at zero token cost, and the context tricks that keep long sessions from derailing. Here is what stuck.

·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.

·10 min read

Building ThoughtForge with Claude Code: What Actually Works

ThoughtForge was built almost entirely with Claude Code. Making AI reliable enough to ship a real product taught me more than the Rust and Tauri learning did.

·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.

← back to all posts