JinnByteCase study
Lootr

From scattered price research to one confident buy.

An AI shopping and price intelligence assistant for iOS and Android.

Industry
Retail and eCommerce
Year
2026
Platforms
iOS and Android
Engagement
Cross-platform mobile development
Lootr home screen inviting the user to describe a product or take a photo
Lootr chat showing the best deal for a requested product
Overview

Turning fragmented price research into one confident buying decision.

Lootr helps online shoppers find the best verified price without checking retailer after retailer themselves. We built the cross-platform mobile experience around one idea: whether someone starts with a question, a photo or a link, they should get from product intent to a clearer, safer decision in one place.

3Ways to start: ask, show or share
5Shopper questions each result answers
3Launch markets: UAE, KSA and USA
1Flutter codebase for iOS and Android
Lootr case studyOverview
The industry problem

More choice has created more decision friction.

The same product shows up across many stores at different prices. Titles vary, a lower price may come from an unfamiliar seller, and promotions change constantly.

The cost isn't only money. It's time, uncertainty and decision fatigue.

A shopper holding a smartphone and a payment card
One simple question"Am I getting a good price?"
Step 1Open several tabs
Step 2Compare listings
Step 3Check each seller
Step 4Confirm it's the same product
Step 5Hope the deal is real
Lootr case studyProblem
The challenge

Work from the way people actually come across products.

Rather than asking users to learn another comparison interface, every natural starting point had to lead into the same comparison experience.

1They know exactly what they want
2They describe it in their own words
3They see it and take a photo
4They already have a product page open
5They want to check if a price is fair
All leading toOne coherent comparison journey
Lootr case studyChallenge
Our approach

Designed around purchase intent, not search mechanics.

Product recognition, retailer matching, pricing data and ranking all happen underneath. The shopper never has to think about them. The interface stays focused on the questions they're actually asking:

Is this the right product?Where can I buy it?Which option is cheapest?Can I trust the retailer?Is this actually a good price?

Ask

Describe what you're looking for in a conversation.

Show

Upload or snap a photo of the product.

Share

Paste a link to a product you're already considering.

Lootr case studyApproach
The mobile shopping journey

One path from discovery to decision.

Every stage of product research happens in one continuous flow, inside one shopping context, until the user is ready to move.

1Product intent
2Product recognition
3Retailer comparison
4Deal context
5Decision
6Save or buy

The usual way

Search engine then marketplace tabs then retailer pages then back again

With Lootr

One conversation to a ranked, verified answer
Lootr case studyJourney
Ask: conversational discovery

Shopping starts with what people mean.

People don't always know the model number or the perfect search phrase. Lootr lets them describe what they want in normal language, then follows up to narrow a broad request down to the right product.

Natural language"A noise-cancelling headphone, cheapest price"
Follow-up questions"Which model are you looking for?"
Lootr chat while the assistant prepares an answer
Lootr chat with a best deal result card
Lootr case studyAsk
Home screen with a product name or link field and a Take A Photo button
Show and share

The product itself becomes the search.

Show: search with a photo

Start from something seen, without knowing what it's called.

In another appIn a storeOn social mediaAt a friend's homeIn an ad

Share: a second opinion before buying

Paste a product link and see how that price compares elsewhere. Useful right at the final decision point, without restarting the research.

Lootr case studyShow and share
Complexity kept out of sight

A lot happens between the question and the answer.

While the shopper waits a few seconds, the app shows clear progress. Everything the comparison engine does stays behind a simple, calm screen.

Product recognitionWhat is this, exactly?
Retailer matchingWho sells the same item?
Pricing dataWhat does it cost where?
Deal rankingWhich options matter most?
What the shopper sees"We're searching. Please wait!" and then the best deal
Processing screen showing search progress across stores and products
Lootr case studyProcessing
Intro screen showing a best deal marked cheaper than usual, with alternatives
Price intelligence

The lowest number only helps when you know what it means.

Lootr goes beyond a pile of listings. Results are ranked and explained, turning raw pricing data into something a shopper can act on.

Lowest verified priceThe strongest matched offer, up front
Alternative retailersOther ways to buy the same product
Usual price contextIs this meaningfully cheaper than normal?
Deal rankingThe most useful results first
Lootr case studyPrice intelligence
Trust alongside price

The cheapest listing isn't always the best deal.

Verified retailer badges and trust signals sit next to every price, so shoppers can see why a result deserves attention instead of just accepting an automated pick.

What is cheapest?
Where do I get the best mix of price and confidence?
Lowest price found

Unknown marketplace seller

AED 94
Unverified sellerListing title differs
Lootr's best deal

Established electronics retailer

AED 99
Verified retailerCheaper than usualExact product match
Alternative

Major online store

AED 112
Verified retailer
Illustrative example
Lootr case studyTrust
From one search to ongoing value

A shopping companion, not a one-off search.

Saved products and a wishlist keep track of what users are considering. Purchase history and savings tracking show the benefit of better decisions over time: a few dirhams on one order add up across many.

Saved productsWishlistPurchase historySavings trackingDeal monitoring
Your savingsThis year
Noise-cancelling headphonesAED 145
Running shoesAED 62
Coffee machineAED 210
Phone caseAED 18
Skincare setAED 44
Saved with LootrAED 479
Illustrative example
Lootr case studySavings
Designed for mobile-first shopping

Where product discovery already happens.

People find products while scrolling social media, messaging friends, seeing ads or shopping in other apps. Lootr lives on the same device where that intent starts.

One Flutter codebaseA consistent, native-feeling app on iOS and Android
Mobile-native patternsConversation, camera, links, saved items and history
Lootr launch screen
Lootr intro screen: Shopping made easy
Lootr case studyMobile first
The user impact

Less friction in one of shopping's most repetitive tasks.

Less manual research

No more opening retailer after retailer.

Faster decisions

Any starting point leads to one streamlined flow.

Price confidence

Context shows whether an offer is truly competitive.

Safer deals

Verification and trust signals beyond price alone.

Less overpaying

Alternatives are visible before the purchase.

Visible value

Saved items and savings history show the benefit.

Lootr case studyImpact
The outcome

From searching across stores to asking one shopping assistant.

Start with textDescribe it in your own words
Or an imageSnap or upload the product
Or a linkCheck a price you already found
Get ranked optionsVerified, contextualised buying choices

Online shopping that is faster, clearer and better informed, without adding research to the customer's day.

Lootr case studyOutcome
Solution experience

Five capabilities in one shopping app.

Conversational shopping

  • Natural-language search
  • Follow-up questions
  • Intent refinement

Visual and link discovery

  • Photo-based search
  • Visual product matching
  • Product-link recognition

Price intelligence

  • Price comparison
  • Lowest verified price
  • Alternative offers
  • Typical-price context
  • Deal ranking

Retailer trust

  • Verified retailers
  • Retailer badges
  • Trust indicators
  • Safer buying support

Personal shopping

  • Saved products
  • Wishlist
  • Purchase history
  • Savings tracking
  • Deal monitoring
Lootr case studyExperience
Technology behind the mobile experience

One app, both major platforms.

Our work focused on the shopper-facing app: the layer through which the wider product, pricing and retailer intelligence becomes easy to use.

Cross-platformFlutterOne codebase, consistent behaviour
PlatformsiOS and AndroidNative-feeling on both
DiscoveryChat, camera and linksThree inputs, one comparison flow
ResultsRanked comparison viewsBest deal, alternatives, trust signals
PersonalWishlist, history and savingsValue that builds over time
Lootr case studyTechnology
JinnByte
Launching first in the UAE, KSA and USA

Built by JinnByte.

Cross-platform mobile development for an AI shopping assistant that finds the best verified deals.

Productlootr.ai Built byjinnbyte.ai
Thank you
1 / 18