THE BUILDING PRIMED ARCHIVE
Building Primed
Behind the scenes on our LLM-first architecture, solo founder journey, and building an adaptive endurance engine.
10 articles in Building Primed
What If the Smartest Part of an AI Coach Never Spoke?
We have early access to TypeSafe's new Jev model. It doesn't chat, write training plans or explain itself, which is exactly why I think it could be interesting for Primed.
IFA 2026: Fitness Tech Is Moving Beyond the Screen
Screenless bands, sensing necklaces and bedside radar point to a new fitness challenge: making sense of health data across devices, training and everyday life.
Why Your AI Coach Shouldn't Change Personality Mid-Season
An AI coach should adapt to the athlete without changing its identity, evidence standards or safety boundaries. New robot-persona research shows why that distinction matters.
Primed is live on the App Store
After nearly two years of building and testing, Primed is now available on iPhone, iPad and Mac. Here is what I have been trying to build, what it does today, and where it still needs to improve.
Primed has changed direction
Primed has shifted focus over the past few months, moving away from its original positioning as a productivity tool and towards something much more specific. It is now being built as an AI system for endurance training.
The Next Step: From LLM-First to Context-First
When we first started building Primed, our focus was on one idea: make the language model the heart of the system. But as AI systems became more capable and complex, prompts weren't enough. That's where context engineering comes in.
Starting Up Then and Now: 20 Years of Change
Twenty years ago I co-founded my first startup, Recommendation Ventures. Out of that came Scouta, a personalised media recommendation app that was ahead of its time. Looking back at how the startup landscape has been reshaped by technology, capital, and now AI.
Our App's AI: A Deep Dive into the "LLM-First" Strategy with Primed
At its core, Primed operates on a fascinating and powerful principle: an LLM-first strategy. Instead of using a Large Language Model as just a feature, the app puts it in the driver's seat — making its own decisions about how to best handle your training requests.
The Story Behind the Name: Primed
When I started building Primed, I wanted a name that captured both the creativity of artificial intelligence and the sense of being ready for what's next. The inspiration came from one of the most famous moments in AI history: Move 37 by AlphaGo.
Behind the Build: Why I Created Primed (and What I've Learned So Far)
About six months ago, I started a side project in my spare time. Not to launch a new company, but to go deeper into something I believe is going to reshape how we work: AI.
FROM READING TO TRAINING
Your next session.
A clearer direction.
Bring your training, recovery and how you feel to a conversation with your coach.
