Fredwork Lemmas
I'm Fred McDavid, and I write about practical AI engineering and infrastructure. This blog documents my work building local LLM systems, experimenting with RAG pipelines, and scaling AI capabilities on consumer hardware.
Recent focus areas include vector databases, prompt optimization, and multi-model orchestration. I share technical findings, implementation challenges, and architectural decisions from real projects.
Writing helps me think through problems and document what works and what doesn't.
Find me on
If you have any questions, please email me at fred@frameworklabs.us .