Skip to main content
41Photography

Fall Foliage

Fall foliage in Banff National Park.

PhotographyLast updated 2026.07.07

On engineering leadership, value-based care, and the craft of building.

A workout planner for endurance + weight training

Combining 8–10 hours a week on the bike with heavy lifting kept blowing up on me: I'd ride too hard, then be too depleted at the gym to lift anything worth lifting. So I built a weekly planner around Intervals.icu where every design decision exists to protect the plan from me. Then I pointed it at my own training log, and it caught me quietly skipping the hard parts.

Memory for AI Agents is a filing system, not a file

Every AI agent wakes up with amnesia. This post details the Kelp codebase which runs two completely separate memory systems, one for the coding agent and one for the product. I argue that truely useful AI memory is a real subsystem with tiers, citations, expiry dates, and garbage collection. The hardest part isn’t recall; it’s knowing what to keep, what to supersede, and when to throw something out.

An introduction to building software for value-based care

This post argues that building successful software for value-based care (VBC) requires a shift in mindset: create a Customer Relationship Management (CRM) tool, not just a better Electronic Health Record (EHR). VBC realigns healthcare incentives around long-term patient outcomes, succeeding through proactive, relationship-based care rather than transactional services. Technology's role is to support this relationship by helping care teams orchestrate interventions effectively. The most valuable tools are often simple and pragmatic, focusing on the unique, core needs of the care model and enabling proactive management of patient health.

Learnings from building Kelp: Getting people the information they need when they need it is hard!

Reflections on pausing the contextual recommendation tool, Kelp, concluding that its goal—getting people the right information at the right time—is nearly impossible for a third-party app to achieve. The core problem is technical: without deep, OS-level access to user data and behavioral signals, recommendations remain mediocre. True contextual help must be built into the operating system itself. The key business takeaway was the need to solve a highly specific, paying use case for a narrow audience before attempting a broad, cross-platform solution.

A selection of my favorites.

Isle of May Puffins
Isle of May Arctic Tern
Scotland Birds
Peru Small Birds
Peru Larger Birds
Flowers