This thread runs from drafting care plans with AI in 2022, where knowing how far to trust the draft was the real work, to Fold dropping allergy data rather than making a safety claim it couldn't back. For governance at the scale of an organisation, see emilysas.com.
Designing for trust
How do you design AI that people trust exactly as much as they should?
human-in-the-loop · trust calibration · provenance · consent
Builds
- EXP-009Building
Mullo
The best page, the worse journey: when an AI tool's quality isn't worth the effort
An AI that draws my notes as an illustrated page. Against a general-purpose tool it made the better page but took far more effort, so I'm redesigning it around what only it does.
- EXP-006Building · Pilot
Fold's review panel
Never mark your own homework: independent AI reviewers for a solo builder
Independent AI reviewers for an app I was building faster than I could read its code. They caught bugs that had passed the tests, and one finding changed what Fold is.
- EXP-005Building · Pilot
Fold
Cheap to build, hard to stop: when AI builds faster than you can learn
A recipe app for vegetarian households with a vegan at the table, built for my own family's needs; once I saw its wider potential, I added a fair amount of complexity without checking whether it was warranted.
- EXP-000Parked
Ambient care-plan scribe
Before care had scribes: drafting care plans with AI in 2022
An AI that drafts a care plan while the assessment is still happening, begun in late 2022. Getting it to write was easy; knowing how far to trust the draft wasn't.
Notes
- Diverse by prompt, biased by role: how AI illustration passes society's stereotypes onhuman-in-the-loop · trust calibration · provenanceNote
- A recipe for honest pictures: how to avoid AI image slop without copyright troubleinference cost · unit economics · token budgetsNote
- Satirical Startups & French Pirate Founders: How Launchling Handles Absurdity by Designadversarial testing · red-teaming · edge cases2025 post