Build logs, technical notes, industry reactions, and research spotlights. What is happening in the work right now.
-
Prompt optimization as a first-class engineering discipline
I have been building a prompt optimization framework for about three months. It started as a quick utility and grew into something I now treat as core infrastructure. The observation that drove it: prompts are code.…
-
Kubernetes for a three-node personal cluster
I have been running a three-node Kubernetes cluster at home for about a year. The unglamorous take: it has been worth it, but not for the reasons I expected going in. What I thought I would…
-
RAG vs. direct context: when each one wins
A question that keeps coming up in my work: when should a system use RAG (Retrieval-Augmented Generation), and when should it just put the relevant content directly in the prompt? After about six months of building…
-
Running GPUs in a home lab: the unglamorous parts
Everyone posts about their home-lab GPU setup. Almost nobody posts about the operational reality of running one. A few notes from my own, in the spirit of transparency. Heat is the constraint. A single workstation GPU…
-
Multi-agent orchestration: what worked and what didn’t
I have been running multi-agent orchestration experiments for about four months. The short list of observations, in order of usefulness: Specialization beats generality, almost always. A single agent with a broad prompt and many tools is…
-
n8n as infrastructure for business process intelligence
I have been running n8n for internal workflow automation for about six months. The short version: it is the least hyped and most useful piece of my personal tooling stack. The setup: self-hosted on a modest…
-
Zero-trust identity for AI agents: working notes
I have been prototyping a zero-trust identity model for AI agents for about two months. The question: how do you give an agent access to what it legitimately needs without exposing what it should not see?…
-
Fine-tuning Llama on the home lab: first pass notes
Running a LoRA fine-tune on a consumer GPU at home turns out to be more forgiving than the AI Twitter discourse would suggest — and more informative about what actually matters for production than a cloud…