The Complete Guided Tour of the Storesight Platform

Join Storesight's Sales Leader, Billy Ruck, for an in-depth tour of Storesight's platform and capabilities, bringing clarity to CPG Professionals needing retail visibility at scale.

This demo shows how our always-on solution, fueled by millions of in-store images from our Field Agent network, transforms fragmented data into unified, actionable insights. We'll learn how to leverage AI Heat Maps, Share of Shelf analytics, and real-time pricing trends to proactively fix execution gaps, maximize retail revenue, and win key buyer meetings.

Transcript

Video Synopsis
This video demo introduces the Storesight AI-powered platform as the solution to a crucial gap in CPG retail intelligence: understanding the "why" behind sales performance, moving beyond just shipment and POS data. Viewers will learn how Storesight provides always-on, real-world retail visibility at scale using a proprietary network of over 3 million "Field Agents" (connected shoppers) who capture millions of shelf and display images monthly. This massive, unbiased data collection allows CPG teams to test hypotheses on retail execution, competitor activity, and merchandising, which is impossible with traditional, limited store visits. The video demonstrates the platform's core features, including virtually walking store aisles, zooming into high-fidelity shelf images, and leveraging AI tools like heat maps (showing shopper eye-gaze) and "Time Travel" (tracking planogram changes over time).

The demonstration further details Storesight's advanced analytics that transform visual data into actionable intelligence for category managers and sales leaders. Key features include AI-calculated Share of Shelf (by facing count or space), allowing users to accurately trend execution compliance against dollar share, and On-Shelf Availability (OSA) modeling. Additionally, the platform indexes text from packaging and price tags across all images to generate a Word Cloud feature, which helps marketing teams track competitive messaging trends like "Keto" or "Protein" over time. The video emphasizes the platform's utility in upleveling buyer meetings and internal collaboration by providing easily shareable, concrete, visual proof of in-store reality, ultimately enabling CPG firms to maximize retail performance, revenue, and profit.

Storesight Demo Transcript (Read Version)
Billy Ruck: I'm Billy Ruck from Storesight, and today I'm going to show you how we help CPG companies execute faster with always-on retail intelligence in store.

The problem that we solve is we know most of our customers have really good shipment data available. We also know that our customers have really good POS data to show what's scanned through the registers, either through third parties or from the retailers themselves. However, oftentimes, our customers aren't able to answer the why behind what happened in-store.

So, for example, the numbers might tick down on their POS data or a new product launch isn't hitting its goals. And there are a lot of hypotheses as to why that's happening. What we do is open up the black box of what's happening in retail execution today. You might go out and visit a few stores and you always find valuable insights, but typically it's the same three to four stores you're visiting. You're not able to zoom around the country and see at scale what's happening to test those hypotheses. What we do is open up the store at scale so that you can test those hypotheses around what is happening in-store with my competitors, how am I being merchandised, what's happening with pricing, and many other ways to test your data for what's happening in-store.

Now you might be wondering, how do we do that at scale? The answer is we have a crowd of 3 million connected shoppers. We call them Field Agents, and they are all over the map, able to go into pretty much every retail location. We go into a cluster of unique locations every month so that you get a really nice representative sample across the map, so that you can then see and zoom around the country to see what's happening with your retail partners as they're executing your plans for retail execution.

Next, I'll show you what the actual platform looks like for your category.

All right, so let's go do a basic store walk in the Storesight platform. Today, we're going to look at the crackers category. So, you can see I've filtered for the crackers category here. And what you'll notice is we just see a stream of nicely framed photos akin to your favorite social media network where you can virtually walk around stores and see what's happening both in display and in the main section.

And let's get into what this actually looks like and what's happening behind the scenes. So I'll just use an example and click on this Market Basket in Portsmith, New Hampshire. You'll see that I can go and zoom in to pretty high fidelity to see what's happening on the shelf, what are the product claims, what is the pricing and specials that we're seeing in this specific display. Also, we're capturing some metadata about where the agent was and at what time. So, this was November 7th at 11:19 AM. This is a suburban store. And in addition to that, we have our AI tagging the brands that it sees. So, for example, Pringles and Cheez-It are being tagged by AI here. And so there's a lot of data here that we're collecting in the background using AI.

Also, for every photo that shows up in the Storesight platform, we have some useful AI tools. Like, for example, the AI Heat Map will show you where does the human eyeball go across this photo. What is capturing the human eyeball's attention? For example, in this case, the clip strip here right next to this endcap, it's getting a lot of heat, so it's attracting the eyeball, and also a logo up here at the top of the display. And so what this is based on an open-source machine learning model that Microsoft and Meta published, and so it's thousands and thousands of hours of consumer research wearing these goggles helps us to at scale map where's the human eyeball going to go when they look across your shelves.

Now it's not just theoretical. We want to make all this data actionable for you. And so we make all of this sharable really easily. So if I wanted to go into a buyer meeting and talk about displays that I was seeing, I can pick examples from the stores and just select them like this. And if I'm preparing for my buyer meeting, I can export them to PowerPoint. We know that oftentimes getting ready for buyer meetings can be a heavy lift. And so exporting to PowerPoint is a really useful tool for enabling you to see and share easily what's happening.

Now that we've shown you a few of the navigation basics, let's go look at some planograms and see how your products have been executed.

So what we're looking at now is the Household Cleaning category in the Storesight platform. And instead of looking at just the main photos or displays, I'm going to look at planograms to see how is my product executed in the planogram. We know oftentimes the design of the planogram or the mod isn't always followed in retail execution, or you might have numerous mod designs across your store footprint. And so we want to be able to go and inspect at scale what's happening across retailers to see how is the execution going on that mod design.

And you might also want to be able to use some AI tools here. So I'll show you a few of the useful ones here. Let's pick this Vons, for example, in Clovis, California. Remember, I showed you the heat map earlier. This heat map can also be applied across the entire planogram to help you to understand where your shoppers' eyeballs are going. It's really useful for as you're thinking about designing those planograms in collaboration with your retailer. Helps you to map out where you might want to be, where you might not want to be, also helping you to think about brand blocking and packaging and that sort of thing as well. So it's a really useful way to look at the planogram.

Also, when our agents have been in a store more than one time, you'll see this Time Travel button appear. So, what we'll do with the Time Travel button is I'm going to visit this Vons store and I'm going to travel over time. This is Vons store 2701 in California, and we were there yesterday. This is what the planogram looked like yesterday. We can also travel and go back in time—two months ago, three months ago, six months ago, nine months ago, etc. This allows us to see what is evolving on this planogram. How has this changed over time? And as we build more and more data in our platform for your category, we're able to go back in time and see what this retailer has done before in the past. And over time, you'll be able to actually correlate those changes on the planogram to outcomes in your results, making you a much better collaborator and partner with your retail partners.

In addition to that, you'll see there's a share button. Any of the planograms or photos that you see in the Storesight platform are sharable with the click of a button. So, if you just click that right there, I can share this planogram out with my internal teams or my external teams as well. Even if they're not a subscriber, they'll be able to have access. The idea there is you want it to be much more collaborative to be able to agree on what's actually happening on the ground, instead of arguing about it, and then moving on to a more constructive conversation about what are we going to do about it? You know, how are we going to optimize in this category together?

Okay, one other thing here, you'll see is this button: we can expand the planogram and do essentially what looks like a virtual store walk right on the planogram. And so if you want to take that buyer on a virtual store walk, we make it really easy to do that, and convenient for you to be able to tell what's happening in-store, visit stores together in collaboration with internal teams via video calls just like this.

In addition to that, there's a lot of analytics that we have on the planograms, and we're building out more and more advanced analytics over time. So why don't we take you next to show you some of the advanced analytics that we're building in the platform, around planograms and beyond.

All right. Now I will show you how we navigate planograms and use some of our advanced analytics to help you up-level your game for buyer meetings or for internal purposes, too. Let's take a look at the yogurt category to show you how we do this. So you can see that I'm in the Storesight platform navigating to the yogurt category, and we're actually looking at Canada today. And so oftentimes what we hear from category leadership or sales leadership is they're writing retrospectives on what happened over the past quarter. And so we're in calendar Q4 now. And so maybe I want to go and inspect what happened in calendar Q3 with things like my Share of Shelf or how were things going across the retailers. What were we seeing across those planograms? So I'm going to filter for date is Q3 2025. And so now you'll see I'm flying across planograms for Q3 and checking out what was happening across those planograms.

Now, one thing that we should talk about is some of the AI features that we're building into the platform. So, I showed you Time Travel already and I showed you the Heat Map already. Another thing is Stock Levels. We've actually built an On-Shelf Availability model that enables you to see what are our percentage stock levels across planograms. We can show this on individual 4-foot sections or at the planogram level, or we can aggregate that up across the entire category filtering by retailer. But it's a good way to at a glance see what was happening with stock levels week by week over time.

In addition to that, we built more advanced analytics right into the planogram. So I'm looking at this store in Ontario, and let's say I want to understand what is my Share of Shelf across this individual planogram. Well, I can calculate that. Now, in the past, I would have to go through and look at the individual pictures and count up the number of facings that I see and then do some long division to kind of determine what is my Share of Shelf. And by the time I've done all that work, I've looked at one planogram. What we've done is trained our AI to calculate the number of facings that it sees. So in this particular planogram there's 1,243 facings. Most of them were identified by our AI, and here are all the brands that we spotted.

And we know that counting facings is really important, but also when it comes to Share of Shelf, what we heard from customers was we want to be able to understand the space allocation as well. Some SKUs are larger than others. Think of six packs of yogurt might be wider than the three individual tub facings. So, we can calculate Share of Shelf both by space or by facing count. That makes it really handy to be able to just swizzle back and forth. Or if you want to look at a brand, that's really important to be able to understand that. We can also aggregate it by manufacturer. This is super useful for if you're trying to understand at a macro picture my Share of Shelf or a micro picture. So, we're always building and adding more features. There's more to come here as we continue developing. And now I'll show you how we can look at this from more of a high level over time.

Also, while we're analyzing planograms, we also might want to see what our shoppers are seeing. And when it comes to doing a store walk, one of the things that's really important to observe are what are the product claims that our customers are seeing on pack and how are those claims changing over time. Since the Storesight platform is indexing all the text and all the numbers that it sees over time in every picture, what we can do is calculate that automatically. So what I'm going to do on this planogram is I'm going to click on our Word Cloud feature. So what this is doing is it's looking across that entire planogram and it's calculating all the words that it sees and creates a Word Cloud. Now this might be somewhat useful or interesting as sort of information on what words I'm seeing. But what's really powerful is if we can extract some data here. So what we automatically do is calculate what are the top 100 words that we're seeing across this planogram. And so for example, if "vanilla" is a popular flavor now, we might want to see, hey, is this trending versus last year? For example, if I selected 20 planograms from a particular retailer and I wanted to know, you know, how has "vanilla" or the word "protein" or the word "keto" or key trending words like that, have those words increased or decreased in appearance over time? And we can know that information just at the click of a button in just a couple of minutes. That's been really powerful for brand managers, for marketers in general as they're thinking about what are we going to put on pack and what product claims are our shoppers seeing today in our categories and in other categories.

Next, let's look at some of the more advanced analytics that we're building and the analytics that are available in the platform for our customers.

So once again, we're looking at the yogurt category in Canada, and I've navigated to the Analytics tab here. So, as you can see, we've oriented our analytics around the four P's: Product, Price, Place, and Promotion. And I wanted to show you one of our newer features that we built around Share of Shelf.

Oftentimes, our customers have asked us, what's your take on Share of Shelf? How do you measure it? We know that this can be an amorphous definition in the market nowadays. It's not a very well understood metric in terms of how should it be calculated. In other words, today there's not an industry standard for how Share of Shelf is measured. So what we attempted to do was by looking at all the facings and all the space that we see across our millions of store captures, how do we identify those individual facings and the space that they represent to calculate a true standardized Share of Shelf across a representative sample of the market. And so we do that in a couple of different ways. We can calculate it by facing count or by space. We can calculate it by brand or by manufacturer.

And so if I am a category manager and I want to go report on, hey, how was my Share of Shelf trending over Q3? So I'll pick July to September here to calculate my Q3 Share of Shelf and how it's trended. I just pick my time frame. I can pick my retailers below or my brands. And you can see that during Q3 we saw over 630,000 facings and counted and calculated what is the Share of Shelf over those 630,000 facings to be able to determine how is our Share of Shelf, not only that, but how is the Share of Shelf trended for a manufacturer across Q3. This is really important because the trend starts to matter over time as you determine with your retail partners how are we going to allocate Share of Shelf, and then was that Share of Shelf actually executed in the real world. You'll be looking at dollar Share of Shelf, but it's important to be able to contrast that with how is the physical Share of Shelf in the real world looking. So we have a couple of different ways to look at that. One is through just a simple pie chart, as I'm showing you here. Another might be on a line graph. So you can actually trend this over time and have high confidence, high fidelity data on what is my Share of Shelf and how is it trending over time.

We're always innovating and building more, and so stay tuned for more features to come on our Share of Shelf and other analytics features in the near future.

Next, let's look at how we determine pricing over time from our real-world execution visibility across the market.

What's really important to know is not only what price you've agreed to with the retailer, but what price are we being executed at day by day across the real world in the market footprint you have. And so we've trained an AI to go and find price tags and facings in the market. So I'm just going to click on one of these examples. You can see here we have an item in the cracker space. Down there at the bottom left you'll see there's a green rectangle where our AI has identified. There's a facing and there's a price tag beneath it. Why is this important? Well, we can aggregate this data and now search for it over time to see how has pricing changed. Since we're indexing all of the numbers and all the text that we see, I can now search for this product and see how is that product looking when it comes to pricing over time. And I can filter by retailer to compare different retailers on how are different retailers pricing this item over time. We can download that to Excel or have a scatter plot visualization to compare across the real world how has this product been priced over time by retailer. This enables you to get the real ground truth on how your execution is going in the real world and prevent things like revenue leakage across the market.

Well, we hope this demo has been helpful for you to show you quickly what are some of the features that we can utilize to navigate how our execution is going in the market, to up-level our buyer meetings, and to have a much better understanding of how our product is looking to our customers as they shop the shelves in the real world. Thanks for your time.