Occasional long posts on knowledge systems, enterprise search and AI engineering.https://olhapi.com/https://olhapi.com/blog/scaling-coding-agents-past-one-machine/https://olhapi.com/blog/scaling-coding-agents-past-one-machine/One MacBook capped me at two projects with coding agents and a full disk. Agents on a homelab VM and a PC, one client everywhere, took that to five.Wed, 23 Sep 2026 00:00:00 GMTaiworkflowhttps://olhapi.com/blog/ai-coding-20x-productivity-frontend-developers-guide/https://olhapi.com/blog/ai-coding-20x-productivity-frontend-developers-guide/Faster delivery with AI coding tools without shipping insecure code: foundations, prompts, security scanning, feature flags and MCP for React and TypeScript.Sun, 13 Jul 2025 00:00:00 GMTaillmagentshttps://olhapi.com/blog/run-personal-llm-on-laptop/https://olhapi.com/blog/run-personal-llm-on-laptop/Five 7B–13B language models that run offline on a laptop: Qwen2.5, Gemma 2, Mistral 7B, Xwin-LM and DeepSeek-R1 Distill, with sizes, hardware and licenses.Wed, 26 Mar 2025 00:00:00 GMTaillmhttps://olhapi.com/blog/css-in-js-is-dead/https://olhapi.com/blog/css-in-js-is-dead/Runtime CSS-in-JS slows React apps down. Why teams are moving to zero-runtime options like Vanilla Extract and Tailwind, and what they gain.Mon, 10 Mar 2025 00:00:00 GMTfrontendcssstylingjsreacthttps://olhapi.com/blog/search-evolution-from-lexical-to-semantic-to-rag/https://olhapi.com/blog/search-evolution-from-lexical-to-semantic-to-rag/How search moved from keyword matching to embeddings, and how retrieval-augmented generation pairs that retrieval with LLMs for context-aware answers.Mon, 03 Mar 2025 00:00:00 GMTsearchllmrag