AI Architect & Security Professional

Building Systems
That Survive Production

Notes on shipping AI Agents, RAG systems, and LLM applications for real-world use, plus some case studies from client work.

From the blog

All posts →

Designing for Offline-First Web Apps

Treating the network as an enhancement rather than a requirement changes almost every decision you make, from data storage to how you show errors.

Featured case study

All case studies →

Replaced a manual document-entry bottleneck with an extraction pipeline that routes uncertain fields to a human reviewer instead of guessing.

LogisticsDocument AIAutomation

~70% reduction

in manual re-keying time across the three highest-volume document types

Review queue, not black box

low-confidence extractions are still reviewed by a person before they hit billing

3 weeks to first production document type

shipped incrementally instead of waiting for full coverage

Read the full case study →

Also available for security and AI consulting

I take on a small number of engagements alongside the writing: security assessments and threat modeling, plus AI engineering work like RAG systems, agents, and evaluation.

See services →