Discovery → Synthesis → Structure → System → Testing
Fintech · Mobile App · 2026Concept Project

Budgeting that
builds itself

A case study on designing Cairn, a budgeting and expense-tracking app. It turns transaction data into a visible trail of financial progress. Built for a 2026 world of AI-assisted, trust-first money management.

Role

Lead Product Designer

Timeline

10 weeks, end‑to‑end

Platform

iOS & Android

Tools

Figma · FigJam · Maze

Try the clickable prototype ↓
9:41●●● 5G 100%
Milestones
Emergency fund
9:41●●● 5G 100%
This week
Tue, Jul 28, your trail so far
Left to spend this week
₹6,140
Groceries
Dining
Transport

What is Cairn?

Cairn is a budgeting and expense-tracking app. It sorts spending into flexible categories and turns progress into a visible trail. It's built for people whose income doesn't arrive in tidy, predictable amounts. It's for people tired of red overspend banners that hide the real picture.

Underneath that trail is one simple idea. Every category and every goal is a stone in one ordered stack. They are not two separate features stitched together. Foundation stones are essentials, like rent and groceries. They sit at the base. Aspirational stones are savings and debt-payoff goals. They can only be added once the base is stable. Budgets and Milestones are just two views into that same stack.

The Problem

Most budgeting apps still ask people to behave like accountants. Log every purchase. Force spending into rigid monthly categories. Absorb red, judgmental warnings when life doesn't cooperate.

Research into 2026 fintech behavior shows something different. Users don't quit budgeting apps because they stop caring about money. They quit because the apps make caring feel like homework. AI-driven "insights" often feel like surveillance, not support.

The Goal

Design a budgeting experience with four goals. Remove manual tracking as the default. Explain every AI decision in plain language. Adapt to irregular income. Replace punitive spending alerts with a motivating, opt-in story of progress. Users still keep precise control over how much automation and personalization they want.

Why now (2026 context)

Three shifts define fintech UX this year. Explainable AI is table stakes now. It's no longer a way to stand out. Users will only link real accounts once trust is earned, before KYC. Financial wellness, more than transaction speed, is what keeps people coming back. Cairn was designed directly against these three shifts.

Explain, don't assume
Consent before automation
Progress over perfection
Calm over gamified
One stack, not two systems

How the Work Was Sequenced

A five-stage double-diamond process, run end-to-end with weekly syncs alongside one PM and two engineers.

Discovery

Research & competitive analysis

Synthesis

Personas & journey mapping

Structure

HMWs, IA & user flows

System

Wireframes to hi-fi UI

Testing

Usability testing & iteration

W1–2Research & interviews
W2Competitive analysis
W3Personas & journeys
W4HMWs & IA
W4–5User flows
W5–6Low‑fi wireframes
W7Style guide
W7–8Hi‑fi UI
W9Prototype
W10Usability testing

Where to Differentiate

Five opportunities emerged for differentiating Cairn against the current budgeting app landscape.

01

Automatic, editable categorization

Categorize spending by default. Let users correct it in one tap instead of building every category from scratch.

02

Explainable, consent-based AI

Every AI suggestion shows its confidence and its reasoning. Personalization is adjustable. It is never assumed.

03

Income-flexible budgeting

Rolling budget periods and income-smoothing built for freelance and gig-economy earners. Their income never matched the fixed-salary assumption most budgeting apps still make.

04

Progress that reads like a story

A visual trail of milestones replaces red over-budget banners with empathetic, judgment-free language.

05

Foundation before ambition

Most budgeting apps let you add a savings goal the moment you think of one. They don't check if your spending is under control. So the goal quietly gets abandoned the first time reality doesn't cooperate. Cairn works differently. It won't let a new goal sit above an unstable budget. Say you try to add Emergency Fund while Groceries is over budget. Cairn asks you to steady the base first. Or it flags the goal as at-risk from day one.

Stone 01

Discovery

Understanding why budgeting apps fail to retain users, and what trust actually looks like in an AI-assisted financial product.

Qualitative Research

1:1 moderated interviews to surface the emotional and behavioral reasons behind budgeting-app abandonment.

  • Objective: uncover trust barriers, effort tolerance, and what "progress" should feel like
  • Method: remote 1:1 interviews, 40 minutes each
  • Sample: 14 participants (salaried employees, freelancers, and gig workers), ages 23 to 41

Quantitative Research

A follow-up survey validated interview themes at scale.

  • Objective: quantify friction points and AI comfort levels
  • Method: online survey, 12 questions
  • Sample: 112 respondents across income types
What stops you from sticking with a budgeting app long-term?
Too much manual entry
44%
Categories don't fit real life
27%
Lost motivation over time
19%
Privacy / data concerns
7%
How comfortable are you letting AI auto-categorize and flag your spending?
Comfortable, if I can review
58%
Only for basic categorization
25%
Not comfortable at all
13%
What would keep you engaged with a budgeting app long-term?
Visible progress toward goals
49%
Personalized, plain-language tips
32%
Gamified rewards / streaks
15%

n=112 per question. These are single-pick responses, so figures don't sum to 100. The remainder chose "other" or left the question blank.

Competitive Analysis

A structured review of three category-leading budgeting products to map strengths, gaps, and openings for differentiation.

YBYNAB
MMMonarch Money
RMRocket Money
DescriptionManual, zero-based budgeting method for intentional spendersNet-worth & investment tracking with household collaborationBill negotiation and subscription cancellation, budgeting as add-on
StrengthsDeep methodology, strong community and financial educationPolished net-worth visuals, great for shared household financesEffortless setup, genuinely useful subscription and bill tools
WeaknessesSteep learning curve, entirely manual entry, no free tierPremium-only, overwhelming for budgeting beginnersUpsell-heavy UI, budgeting feels secondary to monetization features
AI & PersonalizationMinimal (manual control is the philosophy)Moderate (automated insights, limited explainability)Moderate (spend alerts, limited category flexibility)

Conclusion

The gap in the market isn't another budgeting method. It's an app that combines the best of three: YNAB's intentionality, Monarch's visual clarity, and Rocket Money's low-effort setup. It drops their weaknesses too: manual burden, beginner overwhelm, and upsell fatigue. Cairn's chance is automatic categorization the user can trust, explained in plain language, wrapped in a progress story that feels earned, not gamified.

Stone 02

Synthesis

Synthesizing research into shared patterns, then into two personas that anchored every design decision.

Affinity Mapping

Frustrations

Manual entry feels like a second job
Red "over budget" alerts feel like being scolded
Fixed categories don't match real spending

Needs & Wants

Automatic categorization I can still edit
Plain-language reasons behind AI suggestions
Budgets that flex with irregular income

Behaviors

Check the app in short bursts, several times a week
Abandon the app after one "bad spending month"
Rarely open budgeting apps for more than 30 seconds

Motivations

Wants to see visible progress toward a named goal
Wants control over how much AI does automatically
Wants reassurance the bank link is secure

User Personas

AR

Aditi Rao

26 · Freelance Content Strategist · Mumbai

"My worst month by the numbers was the month I turned down badly-paid work. The app doesn't know that."

Pain Points
  • Made ₹1.8L one month and ₹40K the next. A flat monthly budget calls one of those months a failure. Neither one actually was.
  • Still keeps her real budget in a color-coded Notes app. She retypes the same three numbers every Sunday. No app she's tried has earned enough trust to replace it.
  • Has been auto-categorized wrong by three different apps in the same month. A confidence badge alone doesn't move her.
Goals
  • A budget that judges her against her own quarter instead of a flat calendar month
  • Enough visible reasoning that she'd trust the app over her Notes-app spreadsheet
  • A read on progress that doesn't quietly punish a month she said no to bad-paying work
RM

Rohan Mehta

34 · Software Engineer · Bengaluru

"The app that gets close is the one that shows its work. The one that says 'trust us' is the one I delete first."

Pain Points
  • Wrote his own 40-line script to parse bank CSV exports. He's seen too many false-positive merchant matches in his own work to take an app's categorization on faith.
  • Deleted three budgeting apps within a week each. Not because they were slow. Each one silently miscategorized a transaction and never said so.
  • Reads the privacy policy before linking anything to his bank login. He has reported a real API leak before. This isn't theoretical for him.
Goals
  • Tracking that's automatic, but never silently wrong. Or at least never silently wrong twice.
  • Proof, not a promise, that his bank data is handled narrowly and can be revoked.
  • A 30-second weekly check-in that respects the fact he could build this himself, if he had the time.

Journey Mapping

Scenario: Rohan sets up Cairn and reaches his first savings milestone.

PhaseAwarenessDemo PreviewAccount LinkFirst WeekMilestone Reached
ActionSees Cairn recommended in a finance newsletterExplores the app with sample data, no account requiredLinks his bank once he sees the security explanationReviews auto-categorized transactions in under a minuteGets a quiet, tasteful notification: a stone added to his goal
Feeling🙂 Curious🙂 Reassured😌 Confident😊 Relieved🎉 Proud
OpportunityLead with outcomes, not features, in marketingLet value be felt before any personal data is requiredExplain exactly what is accessed and why, in plain languageDefault to automatic categorization with one-tap correctionCelebrate without gamified noise. No confetti overload.
Stone 03

From Insight to Structure

Reframing research insights as "How Might We" questions, then structuring the product around them.

Trust

How might we help users trust AI categorization without feeling surveilled?

→ Persistent "why we flagged this" explainability tags, visible confidence scores, one-tap confirm or correct.

Tone

How might we make budgeting feel like progress, not punishment?

→ Replace red over-budget banners with a trail-and-cairn metaphor and empathetic copy ("15% over on dining" instead of "You overspent").

Onboarding

How might we build trust before we ask for a bank login?

→ A demo-data preview mode lets users feel the product's value before any account is linked.

Flexibility

How might we support users with irregular income?

→ Rolling budget periods and income-smoothing suggestions instead of fixed calendar months.

Effort

How might we make a 30-second check-in feel worthwhile?

→ A single "this week" home card with one clear, prioritized next action.

Control

How might we give users granular control over personalization?

→ A settings panel that lets users dial automation from Manual to Assisted to Automatic.

Structure

How might we stop Budgets and Milestones from feeling like two disconnected apps stitched together?

→ One ordered stack of stones instead of two data models. Foundation-tier categories sit at the base. Aspirational-tier goals sit above. Goal creation is gated on foundation stability.

How the Confidence Score Works

The "Trust" HMW earlier in this list isn't just a design principle. It needed real decision logic underneath it before any screen could show a number. "92% confidence" isn't a black box borrowed from a model card. It's a weighted match against the user's own transaction history. Every part of it is designed to be argued with.

What generates the number

Merchant recognized from history
40%
Category consistency for this merchant
35%
Amount in typical range
15%
Similar transaction in last 30 days
10%

What the threshold does

ConfidenceBehavior
90–100%Auto-categorized with a one-tap Confirm. The user can raise or lower this line later. It's never fixed.
60–89%Suggested, but requires an explicit confirm before it's applied to the transaction.
0–59%Not guessed at all. Surfaced as "Needs your input" instead of a low-confidence label nobody trusts.

What happens after a wrong guess

01

First correction

Confidence for the old category drops for that merchant specifically. The corrected category becomes the new default, but starts fresh at 75% rather than snapping back to 92%. One correction isn't enough evidence to be that confident again.

02

Second correction in a row

Cairn stops auto-guessing that merchant entirely. Every future transaction from it is surfaced as a plain question. This continues until the user confirms the same category twice in a row. Three wrong guesses never happens, because the second one ends the guessing.

03

Scope of a correction

A correction only changes that exact merchant. Cairn never assumes that similar merchants, like other food-delivery apps, should change too. The user has to set a broader rule for that to happen. Past transactions are never silently recategorized. Only future ones are affected.

Information Architecture

Cairn: Bottom Navigation
Home
  • Weekly trail summary
  • Next best action
  • Recent transactions
Budgets
  • Foundation-tier stones
  • Rolling period view
  • Edit / merge categories
Insights
  • Spend trends
  • AI flags & explanations
  • Confidence & feedback
Milestones
  • Aspirational-tier stones
  • Cairn progress view
  • Milestone history
Profile
  • Linked accounts
  • Privacy & AI controls
  • Security center

Budgets and Milestones aren't two separate data models wearing the same nav bar. Both tabs filter one ordered stack of stones by tier. A category (foundation) and a goal (aspirational) are the same underlying object, just filtered differently. A goal can't be promoted into the Milestones view until the foundation stones beneath it are stable. See the flow below, and the "foundation unstable" screen in the Design phase, for how that plays out.

User Flows

Flow 1 · Reviewing an AI-flagged transaction

User opens Insights tab
↓
Sees transaction flagged with confidence badge and plain-language reason
↓
Does the category look right?
↓
Yes
Taps "Confirm." Category locked in.
No
Taps "Edit" and picks correct category
↓
Cairn learns preference for future transactions. End.

Flow 2 · Setting a savings milestone

User opens Milestones tab
↓
Taps "New milestone" and names a goal (e.g. Emergency fund)
↓
Are this goal's foundation categories stable (within budget)?
↓
Stable
Goal is added above the stack immediately
Unstable
Cairn explains which category is over, then offers "add anyway, flagged as at-risk" or "steady the base first"
↓
Is income steady or variable?
↓
Steady
Fixed monthly contribution suggested
Variable
Rolling, income-smoothed contribution suggested
↓
Goal confirmed. First stone placed on the trail. End.
Stone 04

Building the System

From low-fidelity structure to a visual language built around trust, calm, and quiet celebration.

From Sketch to System

Low-fi stayed loose on purpose. The goal was to test the weekly-summary-first layout against the old dashboard-first mental model, before spending time on visuals. Mid-fi locked the layout once that held up. Then it added just enough color to test the stone-trail metaphor for legibility. Only hi-fi introduces the real palette and type. That way, early feedback stayed focused on structure, before aesthetics had a chance to distract from it.

Low-fidelity
Mid-fidelity
Hi-fidelity
Left to spend this week
₹6,140
Groceries
Dining

A Direction We Explored, Then Cut

Not every idea survived contact with users. The gamified home screen below is the clearest example. The reasoning behind cutting it shaped Cairn's tone more than almost any other decision.

Cut after testing
9:41●●● 5G 100%
🔥 12-day streak
Rank #4 among friends this month
M
T
W
T
F
S
S

Don't break the streak. Log a transaction today!

🏅
🎯
💰
🔒
🔒
🔒
🔒
🔒
Sketch 2, Week 6: streaks, ranks, and a locked badge wall.

Why it looked right on paper

Gamified rewards weren't the top pick in the survey. Only 15% chose it, behind visible progress and personalized tips. But Revolut's savings-challenge streaks were a clear competitor benchmark. A daily streak plus a badge wall also tested well in isolation for "delight" during early sketch reviews.

Why it was cut

  • In moderated testing, 3 of 4 participants matching Aditi's profile said a broken streak felt like "one more way to fail." That's the exact shame spiral the whole project set out to remove.
  • Ranking users against friends assumes a stable, comparable income. It actively punished the irregular-income persona the app was designed to support.
  • It optimized for daily open rate rather than financial health. Engagement that isn't tied to an actual goal is the wrong metric for a budgeting app.

What replaced it

The cairn milestone system kept the "visible progress" insight that made streaks appealing. But it tied that insight to a user-chosen goal instead of daily login pressure. Progress can pause. It never resets to zero.

Visual Style Guide

Typography Scale

StyleSampleSize · Weight
DisplayReach the next stone42–80px · 460
Section headBuilding the System30–42px · 460
Card headingA direction we explored18px · 520
BodyYou're 15% over your dining budget this month.16px · 400
Data₹4,280.0018px · 600
CaptionLeft to spend this week11px · 700

Color Usage

Primary: Pine
60%#1F3A2E
30%#2F5443
10%#152A21
Secondary: Ochre
55%#C6862F
30%#E9C98A
15%#A66A1F
Neutral
50%#F1EFE7
35%#8C8570
15%#20241D
Rust: reserved, under 2% of surface area#A85A3E. Genuine warnings only, never routine spending alerts. That's how it keeps its meaning.
Iconography

Deep pine and warm ochre replace the typical blue-and-white fintech palette. They feel grounded, not corporate. The rust accent is reserved only for genuine warnings, never routine spending alerts. That's how it keeps its meaning. Icons use rounded strokes to match Fraunces' soft serif terminals.

Warm serif plus an earthy palette is a familiar move by now. Plenty of fintech case studies reach for it to signal "not corporate." The part that's actually load-bearing here isn't the color choice. It's that every stone on the trail is a slightly different, asymmetric shape, not a uniform pill. No two are cut from the same border-radius. A real cairn works the same way: no two stones are ever the same.

Key Screens

High-fidelity screens from the final prototype, each tied to a research insight above.

9:41●●● 5G 100%
This week
Tue, Jul 28, your trail so far
Scan
Add
Transfer
Left to spend this week
₹6,140
94% of your Dining budget spent, 9 days left.
Groceries
Dining
Transport
Home: a single weekly summary replaces a cluttered dashboard.
9:41●●● 5G 100%
Budgets
Rolling 30-day period · flexes with income
WeeklyMonthlyCustom
Dining₹8,420
₹8,420 of ₹9,000 · 94% used
92% match Confirm
Groceries₹6,110
₹6,110 of ₹9,000 · 68% used
Auto-categorized
Budgets: categories behave like adjustable stones, not fixed boxes.
9:41●●● 5G 100%
Why we flagged this
Swiggy · Jul 26 · ₹640
CategoryDining

Flagged because it matches 14 similar food-delivery purchases this month. Confidence: 92%.

Swiggy track record: 12/12 correct so far · overall accuracy 94% across 312 reviewed

Auto-confirm matches above 90%
Notify me for new merchants
Transaction detail: every AI decision is explained, never assumed.
9:41●●● 5G 100%
Milestone reached
Emergency fund · Stone 3 of 8

You've placed your third stone. You've saved ₹15,000. Five more to go.

Milestones: the aspirational tier of the stack. Quiet celebration, no gamified noise, no streak pressure.
9:41●●● 5G 100%
Settings
Your account, preferences, and security
AK
Alex Kumaralex@example.com
Manual: I categorize everything
Assisted: suggest, I confirm
Automatic: act on high confidence
Settings: personalization is a dial the user sets themselves.
9:41●●● 5G 100%
This week
Freelancer mode
Tue, Jul 28 · income, smoothed
Safe to spend today
₹1,850
Tax set-aside₹4,200
30% of this month's invoices
Groceries
Coworking
Software
Freelancer mode: this week's limit is a trailing average of the last 3 pay cycles, not a fixed monthly assumption.
9:41●●● 5G 100%
Choose your bank
Cairn reads transactions, never moves money
Read-only access

Cairn can see transaction history to categorize spending. It cannot initiate payments or transfers.

Choosing a bank: what Cairn can and can't do is stated before you connect a single account, not buried after.
9:41●●● 5G 100%
Ask Cairn
Plain language, not a dashboard to interpret
How much did I spend on dining this month?
₹8,420

That's 18% more than your 3-month average of ₹7,140. Mostly weekday lunches.

Based on 14 dining transactions, Jul 1–28
Am I on track for my emergency fund?
What changed since last month?
Ask Cairn: the same explain-don't-assume principle as the transaction screen, in a conversational shape.

Anatomy of the Home Screen

Every element on the flagship screen traces back to a specific research finding.

9:41●●● 5G 100%
This week
Tue, Jul 28, your trail so far
Left to spend this week
₹6,140
Groceries
Dining
Transport
1
2
3
4
5
1

A weekly frame, on purpose

Matches the 30-second check-in habit found in interviews. There is no full month of data to parse.

2

Progress rendered as a trail

Replaces a bare completion percentage with a visual trail so progress feels tangible rather than abstract.

3

Category order follows real spend

Highest-activity categories surface first, so the one thing worth reviewing this week is never buried.

4

Ochre used only where attention is earned

The one category running hot uses the accent color. Color signals a decision point instead of decorating the screen.

5

Bottom nav sits in the thumb zone

All five destinations are reachable one-handed. See the reachability study below.

Built for Everyone

Trust, Built In

2026 fintech UX is judged as much on who it excludes as on what it enables. Three checks ran alongside every screen.

Color contrast

Aa
Pine on PaperAAA9.1 : 1, body text & headings
Aa
White on PineAAA9.6 : 1, primary buttons & nav
Aa
Ochre, icons & large text onlyAA3.4 : 1, never used for small body copy

Dynamic type support

100%, default
You're 15% over your dining budget this month.
150%, accessibility size
You're 15% over your dining budget this month.
Hard reach
Stretch
Easy reach

One-handed reachability

Primary actions, the weekly summary card, and the bottom navigation all sit in the bottom two-thirds of the screen. That's the zone a thumb reaches without a grip shift.

Security you can verify, on the same screen

Before linking a bank account, Cairn shows read-only scope, encryption standard, and a revoke-access control on the same screen. None of it is buried in a settings menu three taps deep.

  Read-only access, bank-grade encryption
Hands on it

The Prototype, Live

This isn't a screenshot. It's a working slice of the actual flow tested in the study below. Tap the flagged transaction, then confirm or edit its category.

9:41●●● 5G 100%
Insights
3 new transactions this week
Swiggy₹640
92% match · Dining Review →
Amazon₹1,899
Auto-categorized
Why we flagged this
Swiggy · Jul 26 · ₹640
CategoryDining

Flagged because it matches 14 similar food-delivery purchases this month. Confidence: 92%.

Choose a category
Swiggy · Jul 26 · ₹640
🎉 Entertainment
👨‍👩‍👧 Family & shared
🍜 Dining (keep as is)
Got it

Noted for next time. Future Swiggy orders will be categorized the same way automatically.

Updated

Cairn will remember this correction and apply it to similar Swiggy orders going forward.

↑ Live demo: tap to interact
1

Browse this week's insights

Transactions the AI wasn't fully certain about surface first, with a confidence score attached.

2

Review the reasoning

Tap in to see exactly why a category was suggested. It's never a black box.

3

Confirm or correct in one tap

Either path teaches the model your preference for next time. No settings menu required.

Stone 05

Putting It in Front of Users

Moderated testing to validate whether the explainability and control mechanisms actually worked in practice.

Method

Round 1 tested 8 participants, 4 matching each persona, in moderated remote sessions via Maze. They worked through four core tasks. These were exploring the demo-preview flow, correcting an AI-categorized transaction, setting up an income-flexible savings goal, and adjusting the personalization level in Settings. After I shipped fixes for the findings below, Round 2 retested the same tasks with 11 new participants. This round ran unmoderated. It checked whether the fixes held up without me walking anyone through it.

Session recording · Task 2: correcting an AI-categorized transaction

● Rec: Participant 0603:41 / 07:52
Participant 06 · reacting to the confidence badge, 03:41 "Wait... ninety-two percent? Sure of what, though... oh, okay, I see, it's comparing it to my other Swiggy orders. Huh. That's actually kind of nice, ninety-two, not just 'trust me bro.' [laughs] Yeah okay, I'd confirm that one."

This reaction showed a pattern: relief once the number was explained, paired with an instinct to distrust an unexplained label. It showed up in 5 of 8 sessions and directly shaped Finding 03 below.

01

The explainability tooltip went unnoticed

6 of 8 participants didn't realize they could see why a transaction was flagged. The info icon only appeared on hover or long-press.

Made the confidence badge always visible instead of hidden behind an interaction.
02

"Budgets" and "Milestones" were confused

Several participants expected savings goals to live inside Budgets, since both showed progress bars that looked identical.

Gave Milestones a distinct cairn icon and stacked-stone visual language, separate from budget bars.
03

A promise of confidence wasn't enough: testers wanted proof

Testers trusted "92% match" more than a plain "auto-categorized" label with no number attached.

Added a numeric confidence score to every AI-categorized transaction rather than a plain badge.

Goal-setup task success

Round 1 (n=8, moderated)
63%
Round 2 (n=11, unmoderated)
91%

5 of 8, then 10 of 11. These are different participants, so treat this as directional, not a controlled A/B.

System Usability Scale (SUS)

Round 1 (n=8)
66.9
Round 2 (n=11)
81.6

Beyond the Happy Path

The 8 and 11 participants above tested the happy path in depth. But every fintech flow eventually breaks in ways a moderated session won't surface on its own. A bank link times out. The AI has no confident guess. A category runs over. A goal gets added on top of an unstable base. I checked these five screens by inspection rather than moderated testing. Each one tests whether the same principles hold up under actual failure: explain, don't assume; calm over gamified; verifiable security; foundation before ambition.

9:41●●● 5G 100%
Welcome to Cairn
Day 1, no stones placed yet
Left to spend this week
–

Link an account or add your first transaction manually. The trail simply starts empty.

Day-one empty state: a single stone-shaped placeholder stands in for the first transaction that hasn't happened yet.
9:41●●● 5G 100%
Couldn't connect
HDFC Bank · connection failed
No data was accessed

Your bank didn't confirm the connection in time. Nothing was read or stored. It's safe to try again.

Bank-link failure: leads with "nothing was accessed," and offers the demo preview as an escape hatch instead of a dead end.
9:41●●● 5G 100%
Needs your input
3 transactions couldn't be auto-sorted
UPI-8827x₹1,240
0% confidence · pick a category
Swiggy₹640
92% match
Low-confidence sync: a 0% guess is treated as a question for the user, never silently forced into the wrong category.
9:41●●● 5G 100%
Groceries
Your only tracked category · 30-day rolling
Groceries

₹1,860 over this month, still tracked in the same plain language. No rust in sight. That color stays reserved for account-security issues alone, even when this is the only category you have.

Single-category overspend: even at 140% of budget, the color language stays consistent with the rest of the system.
9:41●●● 5G 100%
Steady your base first
New goal · Emergency fund
Groceries is 24% over budget

Emergency fund would sit above an unstable foundation. Steady Groceries first, or add the goal anyway and we'll flag it as at-risk.

Foundation-gated goal creation: Milestones and Budgets share one stack, so an unstable base surfaces before a new stone gets added on top of it, not after.
What Held Up

Where This Landed

Validated through iterative usability testing ahead of a planned engineering handoff.

91%
Goal-setup task success in Round 2, up from 63% in Round 1
81.6
SUS score in Round 2, "Excellent" range, up from 66.9
7/8
Round 1 testers said they'd trust linking a real account after the demo preview
10/11
Round 2 participants correctly identified Milestones vs Budgets

What I learned

Explainability only works if it's impossible to miss. Hiding trust-building information behind a hover state defeats its purpose. I also learned how much tone matters in financial messaging. The same underlying alert can read as supportive or judgmental depending entirely on word choice, and users notice the difference right away.

Limitations & Next Steps

This is a self-initiated concept. Nothing here has shipped, so read the numbers above with that in mind. Participants were recruited informally through my own network, not a screened panel. The AI confidence-scoring in the prototype is simulated, not trained on real transaction data. Both testing rounds measured single-session comprehension, well short of the weeks of actual behavior change the app is designed to support.

Next, I want to test the rolling-budget model with a larger, more representative sample of gig-economy users. I also want to explore a lightweight voice interface for quick balance checks. Before any of this could ship, an engineer would need to validate the confidence-scoring model against real transaction data.