CHOICEFLOW · AI AGENT UX · CONCEPT 2026

The Receipt Before AI Acts

ChoiceFlow explores the pause before AI acts: what it understood, assumed, changed, avoided, and needs permission to do next.

ROLE

Sole Product Designer

Team

Design (Solo)

focus

AI UX · Interaction Model · Prototype

Timeline

2026

PRODUCT RISK

The Pause AI Was Missing

As AI products move from recommending to acting, the risk shifts. Users need to understand not only the output, but what the system understood, what it inferred, and what will happen if they approve it.

I used meal ordering as a test case because a single request can contain ambiguous constraints around preference, budget, timing, and memory. It created a contained way to explore consent before an agent takes action.

PROBLEM

Four questions users can't answer in most AI flows.

When these questions stay unanswered, users have to choose between trusting the system blindly or interrupting the flow to regain control.

01
What did it actually understand?

The output is visible, but the system's interpretation of the request often isn't.

02
What did it assume about me?

Inferences can shape the result without showing users what was understood versus assumed.

03
Can I adjust without starting over?

Corrections often require restarting instead of preserving what the system already understood.

04
What happens when I confirm?

The action, memory, and consequences of confirmation are often bundled into a single ambiguous step.

design question

How might an AI flow let users understand, refine, and approve a recommendation before the system acts?

INTERACTION MODEL

Say · See · Steer · Sign Off

I structured the flow around four beats. Intent comes before interpretation, interpretation before refinement, and refinement before commitment. Memory is approved rather than assumed.

Say

The user expresses intent naturally. No menus, no filters, no perfect prompt. Vague is valid input.


TRUST CHECKPOINT
See

The system reflects what it understood as editable criteria. Correction happens before the recommendation gets specific, while it is still cheap.

Steer

The user adjusts without restarting. Every change preserves prior context and explains what shifted and why.

TRUST CHECKPOINT
Sign Off

Before anything is ordered, saved, or remembered, the user reviews the Decision Receipt: what the AI understood, assumed, and is about to do.

PROTOTYPE

Testing the model through one ambiguous request.

I applied the four-beat model to meal ordering: a familiar task where preference, budget, timing, and memory can all require interpretation before an agent acts.

SCREEN 01 · SAY · VAGUE CRAVING INPUT

Uncertainty is the starting state, not a problem.

The user can begin with an incomplete request. ChoiceFlow extracts workable constraints without requiring a perfectly structured prompt upfront.

SCREEN 02 · SEE · UNDERSTOOD AS
9:41
c_
understood as
tap to edit or remove
warm / comforting
lighter meal !
no recent repeats
budget
$25
keep it under
ready in ~25 min
remember these preferencesoff
that's not what I meant
Screen 02 · See · Understood as

The cheapest moment to fix a misunderstanding.

Before recommending anything, the system exposes what it understood as editable criteria. Correcting an interpretation here prevents the wrong recommendation from carrying downstream.

SCREEN 03 · ONE FOCUSED RECOMMENDATION

Decision support means narrowing the choice.

Instead of returning a grid of options, the agent commits to one recommendation while preserving the information and controls needed to evaluate or change it.

9:41
c_
miso vegetable noodle soup, cucumber side
$22.40~24 minmatch · strong
steer it
more filling
why this?
warm, lighter, under budget, no repeats
$22.40Review order
Screen 03 · One focused recommendation
SCREEN 04 · THE "WHY THIS? LAYER
9:41
c_
why this order
You said
Comforting, not too heavy, under $25, ready soon
I matched
Warm meal · balanced portion · fast prep · within budget
I assumed
Dinner · medium hunger · no strict dietary restriction
I avoided
Heavy fried food · recent repeats · higher-cost options
Screen 04 · The “why this?” layer

Separating what you said from what it guessed.

The rationale separates explicit input from matched criteria, assumptions, and avoided options. Users can see which parts came from them and which came from the system.

SCREEN 05 · STEER · REFINE WITHOUT RESTARTING

Refine the decision without restarting it.

A correction updates the recommendation in place while preserving previously established context. The system also explains what changed and why.

9:41
c_
chicken & ginger rice bowl
total$23.80
ready in~25 min
steeredundo
more filling
over lighter
changed because: you prioritized satisfaction. still warm, still under $25, still on time
$23.80Review order
Screen 05 · Steer · Refine without restarting
WORKING PROTOTYPE

Don't take my word for it. Try it.

I built the flow as an interactive browser prototype to test the four-beat model end to end. Nothing is ordered, saved, or remembered.

DEEP DIVE

The Decision Receipt took three versions.

The Decision Receipt is the final trust checkpoint before action. I iterated on how much information users needed to review without turning confirmation into another wall of complexity.


VERSION 1 · THE LEGAL DISCLAIMER
9:41
c_
order summary & disclosures
Input: comforting, not too heavy, under $25, ready soon
Criteria: warmth 0.8, lightness 0.6, budget $25, time 25m, novelty pref
Inferences: meal=dinner, hunger=medium, party=1, diet=none, spice=med
Excluded: 14 items over budget, 9 heavy/fried, 3 recent repeats, 2 slow prep
Ranking: weighted match 84% vs alternates 71%, 68%, 64%
Memory: session prefs may inform future ranking unless disabled in settings
Action: confirming adds 3 items to cart, est. total $22.40 + tax
Confirm

Honest and unreadable. Everything was exposed, but the hierarchy made critical information difficult to scan. Transparency without prioritization became noise.

VERSION 2 · THE OVER COMPRESSION
9:41
c_
ready to order?
OrderMiso noodle soup · $22.40
Details
Assumptions
Memory & data
Confirm

Scannable, but it buried the two things users most need at the point of commitment: Collapsing assumptions and memory improved scanability, but hid exactly the information that required explicit review.

VERSION 3 · THE RECEIPT
9:41
c_
before i act
You asked for
Comforting, not heavy, under $25, soon
I chose
Miso veg noodle soup · cucumber side · $22.40
I assumed
Dinner · medium hunger · no dietary restriction
You changed
More filling over lighter
I avoided
Heavy fried food · repeats · pricier options
I will remember
Nothing unless you confirm
Confirm · Add to cart
Don't remember this

The receipt. The final version separates the request, recommendation, assumptions, changes, and memory into a scannable record immediately before confirmation.

THE RECEIPT AS A SYSTEM COMPONENT

The receipt needed to work beyond one scenario.

I documented the Decision Receipt as a reusable component with defined anatomy, states, and rules of use. The goal was to preserve the same trust checkpoint as actions, assumptions, and memory states changed.

DECISION RECEIPT · ANATOMY
your words anchor the top
inference, visually distinct from fact
what was ruled out, and why
9:41
c_
before I act
You asked for
Comforting, not heavy, under $25, soon
I chose
Miso veg noodle soup · $22.40
I assumed
Dinner · medium hunger · no dietary restriction
You changed
More filling over lighter
I avoided
Heavy fried food · repeats · pricier options
I will remember
Nothing unless you confirm
$22.40 Confirm
the decision, stated plainly
your steering, acknowledged
memory is an opt-in line item
STATE · HIGH CONFIDENCE
Compact by default

Assumptions remain available without competing with the primary decision.

STATE · LOW CONFIDENCE
Leads with uncertainty

The system surfaces what it is unsure about before presenting a recommendation.

STATE · CONFLICTING CONSTRAINTS
Make the tradeoff explicit

When every constraint cannot be satisfied, the receipt identifies what changed and why.

STATE · MEMORY MOMENT
Memory requires permission

Anything the system proposes to remember is separated from the immediate action and explicitly approved.

STATE · POST EDIT
Preserve what changed

After refinement, the receipt distinguishes the updated decision from the user's original request.

Rule of use: the receipt appears at any boundary where the system transitions from suggesting to acting: ordering, saving, remembering, spending.

EDGE CASES

Designing the hardest moments first.

The interaction model also needed rules for moments when the system was wrong, uncertain, or unable to satisfy the request.

01

The AI gets it wrong

If the system misreads “comforting,” the interpretation surfaces before recommendation as an editable criterion. Correction happens before the error compounds downstream.

02

Confidence is low

When intent is genuinely ambiguous, the system asks one targeted clarifying question rather than presenting uncertain inference as fact.

03

Constraints conflict

When every constraint cannot be satisfied, the system names the tradeoff, identifies which constraint it relaxed, and offers an alternative.

04

Safety-adjacent assumptions

Safety-critical information is never inferred from behavioral patterns. Dietary restrictions, allergies, and similar constraints require explicit user input before they influence an action.

pattern transfer

The trust checkpoint extends beyond ordering.

The Decision Receipt is designed around the boundary between recommendation and action, making the pattern applicable wherever an agent can create a consequential change.

Benefits Enrollment

Surface assumptions before a consequential selection is submitted.

Travel Booking

Show what was optimized and what changed before money moves.

Agentic Checkout

Review the action, assumptions, and memory before purchase.

Subscriptions and Finance

Show what changes, what persists, and what can be reversed before confirmation.

WHAT'S NEXT

The model still needs to earn its friction.

01 · CORE TRADEOFF

Transparency has a cost.

Every checkpoint adds friction. The open question is how much visibility users need before an action, and when that visibility can safely stay one tap away.

02 · INTERACTION RISK

Reflection can feel like latency.

The “See” step creates a deliberate pause before recommendation. I’d test whether that pause increases confidence enough to justify the added time.

03 · NEXT TEST

Put the model in front of users.

The next step is testing where people hesitate, what they skip, which assumptions they correct, and whether the Decision Receipt changes confidence before action.

As AI moves from answering to acting, the interface's job shifts from presenting results to earning the right to act. ChoiceFlow is my exploration of what that permission could look like.

Let’s build something thoughtful

ceciliafiore.designer@gmail.com

BACK TO TOP

Designed + Coded by Cecilia

© Cecilia F. Lopez 2026. All rights reserved
Let’s build something thoughtful

BACK TO TOP

Designed + Coded by Cecilia

© Cecilia F. Lopez 2026. All rights reserved
Let’s build something thoughtful

ceciliafiore.designer@gmail.com

BACK TO TOP

Designed + Coded by Cecilia

© Cecilia F. Lopez 2026. All rights reserved