Thoughts on AI cost management and building sustainable products.
Most AI apps handle monetisation badly. They block users who hit limits and those users churn. Here is what the full monetisation stack actually looks like in 2026, and why building it yourself takes longer than you think.
Read more →OpenAI and Anthropic have no native per-user cost controls. Here's the architecture that actually works — Redis counters, edge function intercepts, and fire-and-forget logging — plus how to handle streaming.
Read more →Request-count limits miss the point. Spend-based limits are what actually protect your margins. Here's how to implement them properly without building your own Redis infrastructure.
Read more →A practical breakdown of what GPT-4o, GPT-4.1, Claude Sonnet, and Claude Haiku actually cost at scale — and how to pick the right model for your app without getting surprised by the bill.
Read more →We built Nasca because we kept running into the same problem: one power user could burn through your entire monthly OpenAI budget overnight. Here's how we solved it.
Read more →