EXPLORATION ยท IN PROGRESS
Trusted Cart: AI agents that shop for you
TL;DR
In progress ยท Research phase
An autonomy ladder for AI agents that shop and pay
Visa, Mastercard, and American Express have each launched programs that let AI agents pay on a shopperโs behalf, but the controls serve banks and merchants, not yet the person whose money is on the line. Iโm designing how people set an agentโs limits, see what it did, and take back control. The core idea is an autonomy ladder, where each kind of purchase earns its way from Suggest to Autopilot. A clickable prototype of a household shopping agent is built, and research starts next.
MY ROLE
Self-initiated ยท End-to-end product design
TEAM
Solo, with research participants starting soon
TIMELINE
8 weeks ยท 2026
TOOLS
OVERVIEW
The rails are built.
The human experience isnโt.
Between March and April 2026, Visa, Mastercard, and American Express each launched programs that let AI agents pay on a shopperโs behalf. None of them gives an agent unrestricted access to an account. Each relies on scoped credentials, spending limits, and merchant rules.
Designing for
Households handing off routine shopping ยท Travelers who need help fast
THE CHALLENGE
Controls built for banks, not yet for people
Those controls serve banks and merchants well, but not yet the person whose money is on the line. Whatโs still missing is a clear way for people to set those limits, see what an agent did, and take back control when something goes wrong. Thatโs the problem Iโm working on.
THE APPROACH
Working draft
An autonomy ladder
Each kind of purchase sits on its own rung, and an agent earns its way up through consistent good choices.
1 ยท Suggest
The agent finds options.
You pick and buy.
2 ยท Prepare
The agent fills the cart.
You review and pay.
3 ยท Ask, then buy
The agent buys after your one-tap yes.
You approve or skip.
4 ยท Autopilot
The agent buys within your limits.
You can always undo.
Each step up hands the agent more of the work. A category climbs only after a run of good orders.
KEY DECISIONS SO FAR
Three decisions shaping the ladder
These are working decisions and may change as research comes in.
Earn trust per purchase
Each kind of purchase has its own rung. Trust earned on groceries doesnโt carry over to flights.
Step down when unsure
When the agent is unsure, or a rule would have to bend, it steps down a rung and asks instead of guessing.
Test opposite ends
Groceries show when an agent can move up a step. Flights show when it should step back and ask.
HOW IโLL TEST IT
Two scenarios, two ends of delegation
If the ladder holds at both extremes, it should hold for most purchases in between. Iโve built a clickable prototype of the household scenario to start research. A version with a real AI model comes next. The goal is calibrated trust: people should trust the agent more when itโs reliable, and less when it isnโt.
Keep us stocked
A household agent that keeps groceries and supplies on hand, under $200 a month.
STAKES
Low ยท Weekly
TESTS
Standing rules ยท Budget pacing ยท Substitutions
Rebook me
An agent that rebooks a canceled flight within rules the traveler sets.
STAKES
High ยท Rare ยท Time-pressured
TESTS
Speed ยท Explaining a choice ยท Undo and refunds
The prototype
A clickable research prototype of Keep us stocked, showing the four moments itโs built to test.
Detergent costs $4 more than usual, so the agent waits for an OK.
Home
- Pantry$29.24
- Paper$36.97
- Cleaning$7.99
- Produce$36.40
Needs you
4The store brand is out, and you asked to OK price increases over 10%.
WHAT SUCCESS LOOKS LIKE
Signs of calibrated trust
Calibrated trust means people trust the agent as much as it deserves, no more and no less. In testing, Iโll look for these signs.
01
Trust grows with a track record
People move an agent up a rung after consistent good choices, not on day one.
02
Mistakes lower trust, briefly
After an error, people tighten limits, then loosen them again as the agent recovers.
03
Control stays clear
People can say what the agent did and undo it without help.
04
Stakes change behavior
People give the grocery agent more freedom than the flight agent.
RISKS AND OPEN QUESTIONS
What I havenโt solved yet
These are the hard problems the ladder has to hold up against. I donโt have full answers yet, and research will shape them.
When itโs confidently wrong
An agent can be certain and still wrong, like reordering the wrong size without hesitation. Every purchase has to be easy to spot and undo, even when the agent didnโt flag it.
Whoโs accountable
If an agent makes a bad purchase within limits a person set, who pays: the person, the merchant, or the agentโs maker? Limits need to be clear enough that people know what they agreed to.
Fraud and misuse
Agents with payment access are a new target. Scoped credentials and spending limits help, but people still need a fast way to notice something odd and shut it off.
WHATโS NEXT
Follow along
Research starts now, with a clickable prototype of the household scenario. Next come the framework, the key flows, and a working version with a real AI model. When the work is done, a full case study with test results will replace these notes.
Want to talk about it? Iโd love to hear from you at lynngee@gmail.com.








