Writing
Notes on AI agent infrastructure — MCP, context engineering, retrieval, orchestration. Production-grounded, not theoretical.
2026
-
Infrastructure for solo AI builders: why I split one server into three
Running your own AI agents and GenAI tools? Here's the three-tier setup I landed on — dev, production, and a shared AI + data tier — and the three principles behind it.
Running AI in Production infrastructureai-agentsself-hosting -
Embedding choice for production: when bge-m3 beats OpenAI
Why I run bge-m3 locally for daily workloads even though OpenAI's text-embedding-3-small is faster and cheaper at scale — a production decision framework.
Context Engineering embeddingsragproduction -
minghsuanlee.net is Live
announcementmilestone