Can preferences travel without being exposed?
A shopper’s sizes and tastes could follow them between stores. How do we let that happen only with their consent, and without stores seeing each other?
What we measure while building Concierge: what worked, what didn’t, and the questions we haven’t answered yet.
Why Concierge never lets a language model be the source of truth for a price, a stock level or a cart, and what that split made possible.
Read the paperWhy most websites get a solid strip behind the iPhone status bar and Dynamic Island in iOS 26, tested one change at a time, and how we designed around it.
How a store learns what shoppers want without ever seeing one shopper’s conversation.
Why we stopped trusting unit scores for an agent, and started grading real shopper outcomes instead.
Teaching an agent that keeps watching after the shopper leaves to only speak when something really changed.
When the data an agent sees contradicts its rules, rewriting the rules is wasted work. Fix what it sees.
Taking apart a first answer, millisecond by millisecond, and what we could and couldn’t make faster.
Designing memory a shopper can read, correct and take back, and why consent has to be part of the design.
A shopper’s sizes and tastes could follow them between stores. How do we let that happen only with their consent, and without stores seeing each other?
More shoppers will arrive through AI assistants. How does a store give those assistants the same checked truth it gives a person?
Helping a shopper across many stores means being clear about where every fact came from, and whose store it is.
Watching a price is easy. Deciding when to message, or change a cart, is about permission, evidence and trust.
These are research directions, not products.
No schedule and no filler. Just an email when we publish something worth reading.