Insights

Field notes on building AI automation and technical systems that hold up.

Original architecture notes, decision frameworks, and implementation lessons from Janna Wong — focused on reliability, maintainability, and the operating reality around the tools.

Automation ArchitectureReliability EngineeringIdempotency

Your Automation Isn’t Reliable Until It Can Safely Run Twice

A practical architecture for building retry-safe workflows that recover from timeouts, duplicate events, and partial failures without duplicating business actions.

7 min readRead →

n8nMakeAutomation Architecture

n8n vs Make vs Custom Code: How I Choose an Automation Layer

A systems-first framework for deciding between n8n, Make, and custom code based on workflow complexity, control, reliability, hosting, and maintenance.

7 minRead →

AI AutomationReliabilityArchitecture

AI Automation Reliability Checklist: 10 Things I Check Before Production

A practical reliability checklist covering triggers, idempotency, authentication, retries, rate limits, structured output, human review, observability, escalation, and documentation.

8 minRead →

AI Systems ArchitectureAI AutomationTechnical Strategy

What Does an AI Systems Architect Actually Do?

A practical explanation of AI systems architecture and how it differs from prompt engineering, automation implementation, AI engineering, and fractional technical leadership.

6 minRead →