
Product Intelligence for CPG & Retail
Differentiated attributes. Differentiated opportunities.
The pack, the listing, the reviews. Every product in your category, described the same way.
An animated example. A fictional product, Kestrel Kitchen chili lime tortilla chips, is described in eight places: two retailer listings, a raw retailer title, a product description, a listing path, a distributor item, a review and a nutrition panel. The hierarchy says where it sits. Its retailer title yields 5 attributes. The full set holds 13: seven Core attributes, four Contextual from the description and reviews, and two Custom defined with you.
KESTREL KITCHEN TORTILLA CHIPS CHILI LIME 7.5OZ BAGKestrel Kitchen Chili Lime Tortilla Chips, 7.5 ozBold, zesty heat from real chili and lime.Snacks › Chips › TortillaKSTRL KTCHN TORT CHP CHLI LIME NONGMO 7.5OZITEM 0526-75 KK TORT CHIP CL“The crunch is unreal.”Fiber 3g · Sodium 115mgHierarchyGrocery › Snacks › Tortilla chipstells you where it sits.
What is this product?
KSTRL KTCHN TORT CHP CHLI LIME NONGMO 7.5OZ
One product, described in full.
tortilla chips
- Bold, zesty heat from real chili and lime.
- Kettle cooked in small batches.
- A party-size bag, made for sharing.
Kestrel Kitchen is a fictional brand.
Joined to your sales data, the same attributes carry four analyses on the Insights Platform.
Where demand runs ahead of what the shelf carries, with a number against it.
See it → Competitive benchmarkingHow you compare against the set that competes with you, defined by attribute.
See it → Category trends and momentumWhich claims and occasions are rising, counted across every UPC in the category.
See it → Review and sentiment analysisWhat shoppers say, attached to the attribute they said it about.
See it →Trusted by leading CPG and retail teams















.png)

.png)
.png)
Where the opportunity shows up
You cannot size what you cannot describe.
Once every product carries the same attributes, the same sales answer three different questions. Nothing new was measured.
The same sales, cut by attribute instead of by brand.
Demand inside Zero-sugar seekers that your brands do not cover.
$74M
Your brands today
$412M
Demand your brands do not cover
$486M
The demand space, in total
Where each theme sits, and how fast it is moving.
Values are illustrative. Bubble size is dollar sales.
| Attribute | Dollar sales |
|---|
Watch one product gather everything said about it.
The pack, the listing and the reviews each add something different, and they keep adding. What the market says becomes an attribute, and an attribute is something you can size.
What is this product?
Harmonya
A taxonomy stops where the interesting questions start.
Category, sub-category, segment, brand. That schema was built for reporting, and it has no room for how a product tastes, who buys it or what it gets used for.
What it reports
The taxonomy
Six levels, and none of them describe the product.
What it is
The same product, described
A product is described in more than one format.
Some of it is structured data from the pack and the listing. The rest is the wild: what shoppers wrote, in their own words, after they bought it.
The pack
Manufacturer and brand, category, pack type and size, flavor and form, and what the label itself states.
The listing
How the product is titled, described and merchandised across the retailer sites we read, which is rarely how the manufacturer describes it.
The reviews
What people say about living with it: the benefit they got, the occasion they bought it for, how it tastes and who it turned out to be for.
- AcquireRead the pack, the listing and the reviews.
- HarmonizeMatch the same product across every source.
- ApplyThe same attribute model, the same way every run.
- VerifyCheck the result before it ships.
- MaintainRefresh on a schedule agreed with you.
Custom attributes do not come from any of these three: they are the ones you define, applied to your catalog the same way every run.
One product. Three ways to put its attributes to work.
Everything here runs on the same attributes, resolved once per UPC. A number in one view reconciles with a number in another because they are reading the same product.
Coverage is measured against your product list, not ours. We attribute the items you ask about, and we tell you where coverage is thin.
Insights Platform
Ask a question in plain language and get four reads on the same product set: what is growing, who is winning, where demand is going unmet, and what shoppers say.
Attribute Feeds
The same attributes delivered into your stack as a flat file, an API or a warehouse share, so every team and system is working from one vocabulary.
Harmonya MCP
Point Copilot, ChatGPT, Gemini or Claude at Harmonya and get answers built on the attributes, the reviews behind them and the sales data you already share with us. Coming soon.
What teams use it for.
The same attributes, pointed at the decisions your team already owns.
Shopper
Insights
Understand the product attributes driving consumer choice and track competitive shifts at the theme level.
Assortment Optimization
Decide which items to expand, delist, or localize based on the demand themes driving your category.
Brand Messaging
Shape packaging, PDP copy, and campaigns using the language shoppers use.
Promotion Planning
Decide which products to promote, where to activate, and when to spend based on real shopper signals.
Retail Media Optimization
Target retail media with attributes and themes built on real shopper language, so spend reaches the right products and audiences.
Product Dictionary
Give every team one consistent reference for product attributes and language, across systems and categories.
More on each part.
What it carries, how it reaches you, and what it gets used for.
The three layers
What a product carries, and where each part comes from.
How you take delivery
The same attributes, in whatever form your team works in.
Questions clients bring us
The work it is bought to do.
Getting the data right
What has to happen before any of it can be trusted.
What our customers are saying
“The relationship between Coca-Cola and Harmonya has truly felt like a partnership. We treat them as an extension of our team.”

Rylee Rogers
Fmr. Category Sales Advisor
“Before Harmonya, we couldn’t track competitor innovations online effectively. Now we can see how fast they’re scaling, just like we do in brick and mortar.”

Michael Mackezyk
Senior Manager, Data Capabilities
“Harmonya enables us to instantly analyze consumer reviews and sentiment to understand which ingredients matter most to shoppers, giving a new perspective on shopper priorities.”

Byron Ransom
Marketing Director - Positive Choice Brands Insight & Strategy
"Harmonya enables us to efficiently uncover deeper insights into consumer sentiment and product ingredient preferences, allowing us to identify actionable opportunities to meet shopper needs and enhance category shopability"

Kristina Foreman
Category Analyst
"Harmonya is elevating and enhancing the way we analyze and tell stories with data. The platform enables us to uncover deeper insights that have measurable impact. The team is collaborative, innovative, and truly invested in our success!"

Savita Kharbas
Senior Director of Category and Consumer Insights
“With Harmonya’s review data, we can quantify what customers are saying and compare which products meet their needs best—not based on what we say, but on what they say.”

Rylee Rogers
Fmr. Category Sales Advisor
"Working with Harmonya has been a game-changer – keeping us deeply engaged through new product releases while empowering us to turn complex data into clear, actionable insights."

Wendy Fan
Commercial Strategy Manager
“What Harmonya came up with was an AI-powered solution that helped us match 2,000 missing items. That gave us visibility into $1.7 billion in annual sales we were previously blind to.”

Michael Mackezyk
Senior Manager, Data Capabilities
"The Harmonya team has played a vital role in finding insights on texture, flavor, and nutritional content across our competitive set, identifying innovation whitespace, and sparking additional conversations as we develop concepts for our brands."

Bailey Harrison
Senior Associate Brand Manager
See your category, described.
Go from generic product data to decisions you can defend. See how we build the attributes and put them where your teams already work.

