Articles

Notes from building real things

Web, React and Next.js, AI and RAG, and mobile. Written from production work, not tutorials about tutorials.

On-Device or API? Shipping Structured Extraction With Apple 3rd-Gen Foundation Models vs a Cloud LLM

Apple's 3rd-gen on-device Foundation Models let mobile teams run classification, routing, and structured extraction for free, on-device, and offline. Here is the decision framework I use to choose on-device vs a cloud LLM, where on-device tops out, and the hybrid fallback pattern that sends only the hard cases to a paid API.

Jul 9, 2026· 8 min read

apple foundation modelson-device aistructured extraction

AI Product Engineering

GPT-5.2 Strict Mode vs Claude Tool Use: Which Gives More Reliable JSON in Production

I benchmarked GPT-5.2 Strict Mode against Claude tool use on 200 messy extraction documents. GPT-5.2's CFG token masking guarantees valid JSON and hit ~92% semantic correctness; Claude won on tool orchestration and clean refusals. Here's how to pick, with the refusal-as-error pattern that keeps either one reliable.

Jun 19· 8 min read

Building something similar?

I take on a few projects at a time: web apps, AI features, and mobile. Tell me what you are working on.

Start a conversation