top of page


What nobody tells you about leading AI experiments
There is a part of this work I had not named in the previous articles. It is not technical. It is the feeling of moving forward without knowing exactly where to.
john morais
Jul 53 min read


What the token foundation hid: closing Milestone 1 of the Harness Design System
The estimate was to finish the tokens in one week, and it did not happen. Creating the token was the easy part; migrating the system to them in production took longer.
john morais
Jul 16 min read


The first result: how we defined the token governance for the Harness Design System
In three days we defined the governance process and the way to create, edit, and update tokens, in Figma and in code, so the team can keep maintaining them afterwards.
john morais
Jun 227 min read


How the mistakes are guiding the Harness Design System
The mistakes Claude Code made in earlier experiments showed us the map of what we needed to document in the Harness Design System.
john morais
Jun 134 min read


Before AI-first, human-first
Before choosing the first component of the Harness Design System, I had to decide what comes before the components: the order between humans and AI.
john morais
Jun 65 min read


Harness Design: the discipline that will redefine product design
How AI is changing product design work at Prolog, and why I call the discipline of giving AI context and criteria Harness Design.
john morais
May 236 min read
bottom of page