§ Blog

Architecture, cloud & security notes

Writing on platform design, delivery choices, security decisions, and product-building patterns.

05 postsLatest first
AI Systems/2026-07-05/6 min

Grounding Incident Diagnosis With a GraphRAG Copilot

This project pairs a service dependency graph with semantic search so an on-call copilot can name a likely root cause and its blast radius from evidence, not from a plausible-sounding guess.

AI SystemsPlatform EngineeringReliability
Read note
Security Architecture/2026-06-23/6 min

What This Agentic IaC Security Reviewer Says About My Architecture Style

This project shows how I turn noisy infrastructure security findings into an explainable, remediation-focused workflow by combining proven scanners with bounded agent reasoning.

Security ArchitecturePlatform EngineeringAI Products
Read note
AI Product Engineering/2026-04-17/7 min

Building AI PDF Reader as a Real Product, Not Just an AI Demo

The difference between an AI demo and an AI product is everything around the model: UX, retrieval quality, runtime setup, packaging, trust, and documentation.

AI EngineeringProduct ThinkingTechnical Leadership
Read note
Software Architecture/2026-04-17/6 min

Architecture Lessons from AI PDF Reader

AI PDF Reader brings together product architecture, privacy, retrieval quality, and delivery discipline in one local-first system.

Architecture ReviewsSoftware ArchitectureAI Products
Read note
Security Engineering/2026-04-17/6 min

Threat Modeling a Local-First AI Desktop App

Local-first AI products feel safer by default, but they still need careful threat modeling around files, models, prompts, packaging, and desktop boundaries.

Threat ModelingDesktop SecurityLocal AI
Read note