Technical deep-dives, nutrition research, and notes on building AI products.
Rebuilding AI context from conversation history on every session is expensive and fragile. Here's the architecture we built — storing context in a database and fetching only what's relevant — and what it actually cost us.
Most AI API costs come from unstructured use — long system prompts repeated on every call, context rebuilt from scratch each session, no reuse of prior work. Here's the architecture that changes that.
The monthly payment is only part of the story. Our mortgage calculator shows total interest, payoff timeline, and how extra payments change everything.
The FDA maintains one of the most comprehensive food product databases in the world. We made it searchable by allergen in under a second. Here's why that mattered.
That allergen disclaimer sign at your grocery store is one of the most honest things a retailer can say. Here's what it means, what it doesn't, and how to shop smarter.
How we built a machine-readable compliance library covering 40+ frameworks — NERC CIP, CMMC, NIST 800-171, HIPAA, GDPR — using the Regulatory Decomposition Framework.
How we built the food allergen screening engine behind fdsrch.com — data sources, index design, and why the FDA database is both excellent and frustrating.
A quick introduction to who we are, why we started, and what's coming.
