Capturing my thoughts on the go
I needed a way to capture my thoughts when out and about. This is the overview of how I did it.
Read EntryVersion 1.3
/Shared Trajectories
Direction, velocity and meaning in progress.
Skills were always prototypes
The models are absorbing what we used to write down, which is exactly what a good prototype is for.
Read Entry
Interview Yourself For Context
Interview Yourself First. The gap that slows down most agent work isn't the agent's understanding. It's mine, before I've even started typing.
Read Entry
A Well Thought Out Harness Can Substitute Anything
It doesn't need a new interface built around it. It just needs a good enough one already doing the thinking.
Read Entry
Make Every Team Member the Best Version of Themselves
The best team I can build with AI isn't ten people plus ten bots. It's ten people who each operate like a small team, with one human accountable for all of it.
Read Entry
This is the Claude Code setup behind my personalized workflow
I run a three-layer agent architecture in Claude Code — one layer inlined as my digital twin, two on demand when needed. Here's what each layer does, why it is beyond solid, and how I've built a skills library on top of it.
Read Entry
/Manifest: The Missing Step in Any Workflow
The step between a finished session and something you can actually hand to someone.
Read Entry
Building myself a go-to startup kit
Socratic Agentic Workflow v0.4.0: same interview, but the scaffold it hands you is no longer a guess from whenever I last wrote it down.
Read Entry
Putting my /skills to use
From first question to a system that runs every morning.
Read Entry
How I build design tools - and why process is the product...
I recently spent a day building a structured AI tool for Apple platform design. What surprised me wasn't the outcome, but the ease of decision making along the way.
Read Entry