Blog
Three editorial pillars: how we think about mobile AI integration patterns, what we have learned running a founder-led services company, and the engineering details we wish more people wrote down.
Engineering
We categorized the AI features shipping in the most-used iOS apps of 2026 by type. Search, summarization, generation, voice, recommendations, and where each one runs.
Integration patterns
The concrete checklist for putting an LLM in a HIPAA-regulated mobile app. BAAs, PHI handling, which providers will contract, what to log, and what never leaves the device.
Engineering
A decision matrix for where an AI feature should run on a phone. Latency, privacy, cost, and model size, with the trade-offs we weigh on real mobile builds.
Integration patterns
A working formula and a worked example for forecasting monthly token cost on a mobile AI feature, so the model bill does not surprise your finance team in quarter one.
Engineering
The three production failures we have seen most often when teams wire an LLM into a React Native app. What goes wrong, why, and the engineering pattern that prevents each one.
Founder voice
Most agencies hide pricing and run bespoke proposals. We publish the menu. Here is what that costs us, what it earns us, and why we think it is the right call for a founder-led services company.
The audit is one week. Written, costed, and sized to fit on the desk of whoever is signing off.
Book your audit