JENNIFER
HULL
About
Work
Blog
Practice
CV
☀
☾
Menu
← All posts
Honest Failure.
4 posts
Sort
Newest first
All
11
Agent Experience
7
Build Log
4
Honest Failure
4
Neurodivergence
4
Design Systems
3
Extended Mind
2
Tech Culture
2
04 Nov 2026
7 min read
My agent rules got a perfect score, and I'm still not convinced
An eval is a repeatable test that scores what an AI model produces. I wrote one for the rules my design system gives AI agents, expected a mountain of problems, and learned how easily a result can fool you.
Agent Experience
Design Systems
Build Log
Honest Failure
Views
—
Likes
—
21 Oct 2026
5 min read
My workflow keeps my AI honest. And me.
Wrong AI output looks just as finished as right output. Why I stopped reading everything my agents write and started asking them for proof.
Honest Failure
Agent Experience
Views
—
Likes
—
14 Sept 2026
5 min read
A source of truth is whichever file something checks
Putting your tokens in JSON doesn't make them true. I found a dead brand colour in eight files of my own kit, and the two files a script reads were the only ones that stayed right.
Design Systems
Honest Failure
Agent Experience
Views
—
Likes
—
14 Aug 2026
4 min read
The paste is the review step
dx-grid-inspector reads real DOM tokens and hands you a prompt for your own agent. No embedded model, on purpose: the clipboard hop is where a wrong value gets caught.
Agent Experience
Honest Failure
Build Log
Views
—
Likes
—