NOTES / IDEAS FROM THE WORK
Behind the build.
Between the lines.
Architecture decisions, lessons from delivery, and practical thinking about engineering with AI.
· AI / Agents
Designing AI Systems That Know When to Ask for Approval
Human approval is not a weakness in agentic systems. It is the control layer that makes AI useful for high-stakes workflows.
· AI / IoT
Why IoT App Discovery Needs More Than Vector Search
Lessons from building HEDGE ExpertAI: vector search is powerful, but domain discovery improves when semantic retrieval, keyword scoring, and ontology signals work together.
· AI / Industrial
What Production-Ready AI Means in Industrial Software
Production-ready AI is less about impressive prompts and more about data contracts, observability, reliability, human workflows, and deployment discipline.
· AI / Development
Why I Build With AI Agents (Not Just AI)
The difference between using AI as a tool and orchestrating AI agents as collaborators — how agentic development workflows changed how I ship production software.
· Industrial / IoT
Building Industrial Energy Management Systems — Lessons from the Field
What I learned deploying energy management systems in real manufacturing facilities and FabLabs — from sensor hardware to production Docker stacks.