← Back
Redesigning MealMate with AI cover image showing phone mockups on a dark green background
What the brief missed

The brief was a meal-planning app. The real problem was a decision app.

I started the way you'd expect: mapping HealthifyMe, MyFitnessPal, and the rest. They were all the same shape: a library of meals, presented, then stepped away from. That gave me a hypothesis, not an answer.

Step 1

The brief

"Design a meal planning app." Broad, and not yet a real problem.

Step 2

Competitive scan

HealthifyMe, MyFitnessPal and the rest all shared one shape: a library of meals, presented, then stepped away from. Passive.

Step 3

First hypothesis

Passive libraries were the problem. A reasonable starting theory, and it turned out, not the real one.

Step 4 · the actual discovery

Mid-fi testing surfaces something else entirely

I wasn't testing for this. I was testing navigation with 4–5 people. But the pattern was consistent: people opened the app, looked at Home, and did nothing. Not confused. Not lost. Just not moving.

False lead

I assumed a findability problem

I pointed testers straight at the meal planner. They still stalled. That ruled out navigation as the cause.

The actual cause

Starting requires a decision the app hadn't earned

Starting a meal plan requires already knowing what you want to eat, which requires knowing your calorie target, which requires having thought about this before opening the app.

"The app was asking for a decision it hadn't earned yet."
What I can actually claim

This pattern held across 4–5 informal sessions with people I know. It's consistent enough that I redesigned around it. It is not a validated causal finding: a bigger, more diverse sample might surface a different reason for the same stall.

Three ways to solve it

AI wasn't the interesting option. It was the only one that addressed starting, not choosing.

Once "reduce the cost of the first decision" became the actual problem, there were at least three ways to attack it. I want to be honest about how seriously I weighed the two I didn't pick.

Swapped

Rule-based recommendations

"Users who ate X also liked Y," driven by time of day and static categories.

BenefitTransparent, offline-capable, easy to defend in a design review. Would have shipped fastest.

CostDoesn't adapt to an individual's goal or intake. Narrows options slightly without removing the burden of deciding.

Swapped

Meal templates

"High-protein week," "Quick meals for busy days." Pick a template, follow it.

BenefitFast to build, predictable, zero black-box risk.

CostDoesn't know what's in your fridge or where your calorie count sits today. Runs out of novelty within weeks. Solves the first session, not the pattern.

Kept

AI-driven planning

Personalized to goal, tracked intake, and available ingredients. Adapts over time.

Why chosenThe only option that makes a decision for the user rather than just narrowing their menu.

CostNeeds onboarding data before it's useful (cold start), and if the first suggestions feel wrong, that trust is expensive to earn back.

Being honest about the comparison

I didn't build working prototypes of the other two paths and test them head-to-head. This is reasoned elimination, not an experiment. If I were doing this with real engineering time, the rule-based option is the one I'd actually want to A/B against the AI version, because it's the cheapest to be wrong about.

Four decisions, told once each

Everything below happened as one continuous design pass.

Not a clean lo-fi → mid-fi → hi-fi progression. The fridge-scan pivot and goal-first onboarding both came out of testing sessions midway through, not the original brief. Each decision, once, with what it actually cost.

Home: from a competition to a hierarchy
Lo-fi wireframe → Hi-fi screen
Low-fi Home wireframe with competing carousel and grid
Lo-fi: carousel and grid, equal weightSwapped
Hi-fi Home screen with AI Daily Brief hero
Hi-fi: one hero, one actionKept
What broke

The lo-fi Home had a carousel and a content grid with equal visual weight. Nobody testing it had a reason to look at one before the other. This is where the "do nothing" stall was most visible.

What I chose

An AI Daily Brief card as a full-width hero, everything else pushed below the fold. One focal point, one suggested action.

What it costs

If the AI's suggestion is wrong or irrelevant that day, there's no visible alternative entry point without scrolling past it. Betting a wrong-but-present suggestion beats no suggestion. Haven't tested the miss case.

Onboarding: goal-first, one question per screen
Mid-fi flow → Hi-fi screen
Mid-fi onboarding asking for name and sign up before any value
Mid-fi: 10+ inputs before payoffSwapped
Hi-fi onboarding step 1 of 5, asking for main goal
Hi-fi: step 1 of 5, goal firstKept
What broke

The original flow put 10+ inputs in front of the user before any payoff, opening with "Diet Type," a clinical, low-stakes-feeling first question for someone who hasn't decided to commit yet.

What I chose

A 5-step sequence (Goal → Budget → Dietary needs → Allergies → Calorie target) with a progress bar and a skip option on every screen.

What it costs, honestly

The total information collected is probably similar either way. What changes is perceived effort, not actual effort: a real lever, but not a new insight. It does move value (a first plan) to after step one instead of after ten.

Meal Plan: from a display to an argument
Mid-fi (static) → Hi-fi (Keep / Swap) → the loop continues
Mid-fi meal plan with empty slots and choose meal buttons
Mid-fi: empty, manual, passiveSwapped
Hi-fi meal plan with Keep and Swap buttons and AI insight card
Hi-fi: Keep / Swap + reasoningKept
Swap Lunch screen showing AI-generated alternatives
The loop, one tap later
What broke

AI suggestions were visible in mid-fi but not interactive: no way to say "not that one," no explanation for why it was suggested. It read as an announcement, not a proposal.

What I chose

Keep / Swap on every meal, with a one-line reasoning card attached. Full reasoning is available on tap, not by default.

What it costs

Users who want the full "why" before trusting it get one sentence by default. Betting most people want speed over depth. Weak evidence, since nobody asked to expand the reasoning, but I didn't specifically test for that either.

Fridge input: scan, don't type
Concept correction → Hi-fi scan → confirmation step
Hi-fi fridge scan screen with camera CTA
Scan: zero typingKept
Detected ingredients confirmation screen
Confirmation before recipes generate
What broke

The earliest version assumed people would manually enter what's in their fridge. Nobody does this. People open the fridge and react to what's there.

What I chose

A photo scan with a confirmation step: detected items shown as a list, false positives removable, before any recipe generates.

A correction I need to make

An earlier draft of this case study stated a "30% error rate" as if it were a finding. It isn't. No CV model was built or tested. The confirmation step is the mitigation I'd want in place before finding out what the real error rate is, not proof that it works.

Between round one and round two

Two rounds, tested at two different fidelities, not a controlled comparison.

Round one was mid-fi testing. That's where the stalling pattern in Section 1 surfaced, along with the two pivots (fridge scan, goal-first onboarding) that came out of it midway through, not from the original brief. Round two was hi-fi testing, checking whether the redesigned entry points removed that stall. I don't have granular session-by-session notes comparing the two beyond what's already captured in the four decisions above. They tested different fidelities of the same problem, not a before/after of one fixed test, so I'm presenting them as one continuous thread rather than forcing a comparison that implies more rigor than there was. What follows is the tangible record of that thread: the same three screens, at each stage.

Home
Lo-fi
Mid-fi
Hi-fi
Meal Plan
Lo-fi
Mid-fi
Hi-fi
Preferences
Lo-fi
Mid-fi
Hi-fi
Honesty about impact

I could tell you completion went from 31% to 78%. I won't.

With 4–5 testers, those percentages would imply a sample I didn't have. 88% of 4 people isn't a real number.

What I won't claim
31% → 78%

A clean onboarding funnel, dressed up with percentage points from a sample of four or five people. It would look rigorous. It wouldn't be.

What I can actually say

In the original single-form onboarding, most of the people I tested with stalled before reaching a generated plan. In the redesigned version:

[ Kartik: insert your real count here, e.g. "4 of 5 reached a plan without a prompt from me" ]

That's a small, informal signal the goal-first pacing removed the specific stall I'd observed. It's not proof the approach scales.

Retention mechanics designed, not yet tested

Designed, not tested
Streak counter

Visible day count on Home. Cheap and common. Present because it's low-effort, not because I have evidence it drives return visits.

●●●●
Designed, not tested
Weekly planning prompt

A Sunday notification to confirm or adjust next week's plan. A low-effort recurring touchpoint, without demanding daily engagement.

●●●●
Designed, not tested
Fridge → recipe loop

The bet: reducing weekly decision fatigue drives more organic return visits than a notification does. The mechanism I'd measure first.

●●●●
Designed, not tested
Keep / Swap feedback loop

Every swap is a signal that could improve suggestion quality over time. The mechanism I believe in most, and the one that takes longest to prove.

●●●●
What I'm still not sure about

Three things this design bets on. None of them settled.

?

Is a one-sentence AI reasoning card enough to earn trust before a track record exists?

Early suggestions are the ones users are most primed to doubt. If the first few feel off, the one-liner may not be enough to keep someone from turning the feature off entirely.

MitigationSwap is always one tap away, and every swap feeds the model. That loop needs volume to work, though, and volume is exactly what's missing on day one.

?

Will the fridge scan be accurate enough, early enough, to survive its own first impression?

No CV model exists yet to know its real error rate. The confirmation-and-removal step is designed to catch misses before they become bad recipe suggestions.

LimitIt can't fix a scan that misses so often that reviewing it becomes its own chore.

?

Does weekly planning behavior form without a stronger habit design than what's here?

A streak counter and a Sunday notification are both passive. Neither is a strong mechanism on its own, and nothing is designed past week one for when the novelty of "the AI made this for me" wears off.

StatusThis is the least-finished part of the project, not because it looks unfinished, but because it actually is.

What I'd bet differently now

Testing didn't just confirm a problem. It told me the problem existed at all.

"It wasn't wrong information. It was the wrong order."

The first pass optimized for completeness: every input the app might eventually want, surfaced up front, "Diet Type" leading the way. I went in expecting a navigation issue and found a sequencing one instead, and only because testing forced the reframe, not because I named the constraint up front.

What I'd change about how I worked

I arrived at the real constraint (reduce the cost of the first decision) through iteration, several days in, rather than naming it before wireframe one. If I'd forced myself to state that north star earlier, I might have caught the Home hierarchy problem and the onboarding sequencing problem in the same pass, instead of finding them separately.

What I under-designed

Everything past week one. A streak counter is an easy default, not a real answer to why someone keeps opening the app once "the AI does this for me" stops being novel. That's the harder problem, and I ran out of the 7 days before I got to it properly.

If I did this again

I'd want a real sample before claiming any completion number to a hiring manager. And I'd pick a habit mechanism (probably the fridge-to-recipe loop, since it's tied to utility rather than a reminder) and design two or three weeks past it, not one.

Supporting flows

Four decisions carried the case for this redesign. The rest of the product had to exist around them.

Recipe: where a Swap or fridge match lands
Grocery: auto-filled, still editable
Nutrition tracker
Chatbot: fallback for the unplanned
Search & filter
User profile
Thank you for reading

If you made it this far, you read more of this than most reviewers will.

That's not a complaint, it's the point. This case study was built to be skimmed for decisions and read in full for the reasoning behind them. Either way, here's what I'd want you to leave with.

What I practiced

Naming a real constraint from messy signal, then designing every downstream decision around it instead of around a feature list.

What I'd repeat

Testing early enough that the reframe was still cheap. The Home hierarchy fix and the onboarding fix both trace back to the same four or five people.

What's next

Solving for week two and beyond, with a real habit mechanism, and validating the fridge scan and reasoning-card bets with more than four or five people.

Thanks for reading, Kartik