Blog
Notes on software engineering, SEO, AI and freelance craft
Apr 21, 2026 · 9 min read
RAG in production — what actually breaks, and why retrieval matters more than the prompt
A practical look at retrieval-augmented generation beyond the demo: chunking trade-offs, hybrid search, reranking, eval harnesses, and the cases where RAG is the wrong tool.
- #RAG
- #Claude
- #LLM
- #Retrieval
- #Vector Search
- #Production
Apr 20, 2026 · 8 min read
Cutting Claude API costs 40-70% with prompt caching (and when it doesn't help)
A practical guide to Anthropic's prompt caching — what actually hits the cache, cost math with real examples, and the cases where caching does nothing or even hurts.
- #Claude
- #Anthropic
- #LLM
- #Prompt Caching
- #Cost Optimization
Dec 13, 2019 · 1 min read
Docker Compose Error
docker-compose version discrepancies
- #WordPress
- #Docker