software engineeringAI
AI Products Don't Fail Loudly — They Fail Quietly
February 2, 2026
4 min read
Why debugging AI systems is less about fixing errors and more about auditing decision-making.
Read moreWhy debugging AI systems is less about fixing errors and more about auditing decision-making.
Read moreWhat I learned designing an agentic AI system to help prioritize and forecast future spending—with guardrails that keep it explainable, auditable, and context-aware.
Read moreExploring the tradeoff between single-prompt convenience and step-based control when designing LLM-powered features.
Read moreA look back at the AI side projects I built in 2025 and the technologies that shaped how I think about shipping AI into production.
Read more