People don’t decide the way classical economics assumes. They take mental shortcuts and follow seemingly irrational rules that were tuned for survival in the Paleolithic, not for pricing pages. This article distills the key behavioral economics findings into 50 design guidelines, plus two numbers worth memorizing: losses hurt about twice as much as gains please, and a nudge moves behavior by about 1.4 percentage points.

AI errors halve every 5 months on accounting tasks | Meta’s AI appliance, the Muse Charm | Synthetic users can revive participatory design and drive divergence in the exploratory design phase | Context changes what counts as usable, so test where the work happens | Synthetic users give too-nice feedback

Asking users to watch AI carefully is doomed to failure | Adaptive authoring of content that changes depending on the reader | A cluttered experience kills user focus | To predict patients’ treatment preferences, discussing medical dilemmas beat both survey responses and the patients’ own spouses | Measure outcomes, not vanity metrics | Spotlight the main features and keep specialized options backstage | Allow users to paste passwords | Ambient AI works in the background

Users judge your design against the version they imagined before first use. When the experience confirms expectations, they’re satisfied; when it falls short, the same product disappoints. And the bar never stops moving: every improvement you ship becomes the baseline users bring to the next release. Expectations also shape the work people attempt and the effort they devote to checking the result.

My 10 favorite UX slogans total a mere 40 words, yet they distill the most enduring lessons from my 43 years in usability. All the slogans also work for the coming era of superintelligent AI agents that run tasks for hours or days. What changes is where you aim them.

Vigilance fails in two ways, and UX must design against both. Watching: detection of rare signals drops 10–15% within 30 minutes of continuous monitoring. Answering: when the computer works alone and interrupts occasionally, scrutiny decays per decision rather than per minute. Human-in-the-loop fails on both loops unless you design short watches and rare, meaningful questions.

Most deskilling research studies the wrong condition | Speak the user’s language | Using AI increases people’s preference for AI | Interruptions cause stress | Experienced UXers give the most important findings the most attention | Keep paper prototyping for team building | Support scripts often leave users stranded | Allow users to resize screen areas

Current AI agents help blind users at least as well as screen readers in separate studies and may already do better | Decompose styles into elements you can choose and combine | Show users their options to spare them the burden of recall | AI-simulated users can help designers think through how people will use a design | Optimizing individual elements can undermine the whole user experience | Fail while design changes are still cheap | Before–after sliders