# Sizo: full site text > The readable text of sizo-ai.com, page by page, for AI assistants and answer engines. Summary and official facts: https://sizo-ai.com/llms.txt. The homepage example store (SoHo Flagship, Austin Store, Portland Knit Co.) is illustrative, not a customer. # Home Source: https://sizo-ai.com/ A working model of your store ## You don’t need another report. You need a decision. Sizo learns how your store sells and tells you what to do next, with the reasoning behind it. Connect your shop Get a free audit The cost of guessing ### Guessing is expensive. Here’s what it costs fashion brands. Size allocation Up to 20% of monthly profit is missed by fashion brands through poor size allocation. - Source: Kyndof ↗ Stockouts 55% of shoppers won’t come back after repeated stockouts. 76% say stockouts hurt how they see the brand. - Source: Opensend ↗ Excess stock Up to $140B in excess stock across fashion in 2023: 2.5–5 billion items made beyond demand. - Source: BoF & McKinsey, The State of Fashion 2025 ↗ How it learns ### Sizo builds a brain for your shop. It learns every product, shop, size and season, and how they connect, so every recommendation starts from what it already knows about your store. Every connection It connects every product to how it sells. The order How much to order: 240 units. The split And where each one goes. All of it, connected One brain that keeps learning your shop. Ask about your store ### Ask a question. Get a clear next step. Sizo answers from what it knows about your shop, and shows you why. Free revenue audit ### What did wrong orders cost you last year? Orders that came too late, too small or in the wrong sizes all cost sales. The audit shows how much, and how much you can win back. Revenue audit · last 12 months example store $48,260 lost to wrong orders: too late, too small or in the wrong sizes. 29,140 you can win back Where it leaked #### Your 5 biggest misses Example store · by recoverable loss - Rib-knit sweaterSize M$5,130 missed sales + $1,290 sold at markdown while sizes were out3841d$6,420 - Wool coatSize L$4,120 missed sales + $1,190 sold at markdown while sizes were out963d$5,310 - Linen dressSize S$0 missed sales + $4,280 sold at markdown while sizes were out012d$4,280 - Wide-leg trousersSize 28$3,510 missed sales + $380 sold at markdown while sizes were out2788d$3,890 - Linen shirtSize M2134d$2,740 - Connect ShopifyRead-only, in about two minutes. Nothing in your store changes. - Sizo reads your yearTwelve months of orders and stock: every order that came too late or in the wrong sizes, and what it cost you. - Get your reportYour biggest misses by product and size, and how much of it you can win back. Audit my store, free →Free · no card · read-only Who we work with ### Fashion brands that stopped guessing. Case study · Dé Rococo · Shopify Plus, multi-location Read the case study → - 3.1%of revenue was lost to orders placed too late or wrong - 77%of that loss closed within six months - +65%units sold in a year “Sizo does in seconds what used to take me and my employee a long time and pull us away from other work, saving us money on every single order.” > Shon & Romy Spector · Co-founders, Dé Rococo Revenue lost to wrong ordersshare of revenue, month by month Units sold, year before100 First year with Sizo165 Questions ### Ask us anything. Pick a question. The answers are short. All questions **Q: What does Sizo do?** Sizo learns how your store sells, by product, size, shop and season, and tells you what to order next: how much, in which sizes, and where each unit should go. Every recommendation comes with the reasoning behind it. **Q: How does Sizo decide how much to order?** It looks at what each size really sold, how fast it sells in each shop and online, what is still in stock, returns, the season ahead and your supplier’s lead time and minimums. Then it suggests a quantity, with a lighter and a bolder option next to it. **Q: Does Sizo place orders for me?** No. Sizo drafts the order. You review it, change it and send it yourself. Nothing goes to a supplier without you. **Q: What data does Sizo read, and is it safe?** Order history, line items by SKU and size, stock levels and returns, read-only through Shopify’s official API. Nothing personal about your customers: Sizo only needs the size of what was bought. **Q: What does the free audit show?** What wrong orders cost you over the last 12 months: sales missed because an order came too late or too small, and stock sold at markdown because the wrong sizes were bought. It ranks your biggest misses and shows how much you can win back. **Q: How long until my first recommendation?** Connecting takes under a minute. Sizo reads your full sales history and, for most brands, the first recommendations arrive the same day. **Q: Which platforms does it work with?** Shopify today, in one click, read-only and with no dev work. ERPs, data warehouses and other integrations are available on request. **Q: What about new products with no sales history?** Sizo focuses on restocks, where it can measure real demand. Opening orders for new drops are in development. **Q: What does it cost?** See the pricing page. You can start with the free audit, no card needed. ### You don’t need another report. You need a decision. Connect your shopGet a free audit --- # Free revenue audit Source: https://sizo-ai.com/lost-revenue ## Your free revenue audit See what wrong orders cost your fashion brand over the last 12 months: sales missed because an order came too late or too small, and stock sold at markdown because the wrong sizes were bought. Sizo ranks your biggest misses by product and size and shows how much of the loss you can win back. ### How it works - Connect Shopify. One click, read-only, in about two minutes. Nothing in your store changes. - Sizo reads your year. Twelve months of orders and stock: every order that came too late or in the wrong sizes, and what it cost you. - Get your report. Your biggest misses by product and size, and how much of it you can win back. Free, no card needed. The audit is part of Sizo's Free plan. Connect your shop on the Shopify App Store · About Sizo · Pricing · Case studies --- # Case studies Source: https://sizo-ai.com/case-studies Sizo · Use-case reports ## Case studies What actually happened inside brands running on Sizo, measured against their own numbers from the season before, not against a benchmark. Every figure is computed from the merchant's own store data, with their permission. Who we work with Israel · Shopify Plus · Since Feb 2026 ### Most of the leak, closed Dé Rococo came in losing 3.1% of revenue to wrong orders and orders placed too late, already half the market average. Six months later, most of that was gone, while the shop sold more than triple the units of two years before. - 3.1%of revenue was lost to wrong orders and orders placed too late, before Sizo - 77%of the lost revenue recovered within six months - +65%units sold in a year - 49% → 69%stockouts on selling sizes fixed within 30 days - 65%of size-mix loss gone Read the case study Shon & Romy SpectorTel Aviv “Sizo does in seconds what used to take me and my employee a long time and pull us away from other work, saving us money on every single order.” > Shon & Romy Spector · Co-founders, Dé Rococo Figures are computed from each merchant's own store data with their permission; no merchant's data appears in another's report. More brands publishing soon. ### Want to see your own numbers? Connect your shop, or start with a free audit of what wrong orders cost you over the last 12 months. Connect your shopGet a free audit --- # Case study: Dé Rococo Source: https://sizo-ai.com/case-study-de-rococo Sizo · Use-case report ## De Rococo Use Case De Rococo was losing 3.1% of revenue to wrong orders and orders placed too late. Six months after Sizo went in, 77% of that leak was closed. This is how. Merchant De Rococo Israel · Shopify Plus, multi-location Growth units sold +65% in one year · +257% in two Result 77% of the leak closed Working together since February 2026 01 ### Recognizing the problem Fashion brands — especially mid-level ones, up to $100M in revenue — are fighting with data and decision-making. They don't know how to process all of it, and the reports they have don't lead them to a conclusion. De Rococo Israel is one of the fastest-growing fashion brands in the country. We started working with them six months ago, once we understood the pain they were carrying. At De Rococo, we found that producing a report for a single product took 30 minutes or more of fetching and calculating data — and even then, information was missing. Day to day, the work ran on Excel sheets and gut feeling. Even with an engineer as co-founder, they struggled to find a solution — including when they went looking in the market. 3.1% of revenue lost to wrong orders and orders placed too late. 18% of the catalogue affected by stockouts. 30 min+ per product report — fetched and calculated by hand, and still incomplete. To make it concrete with one running style: the Mid Rise Denim Shorts (Ivory Blue) were losing 14.3% of the demand on their size ladder to missing sizes — roughly one of every seven shoppers who wanted this style asked for a size that wasn't there. In our overall look at the industry, De Rococo is actually performing really well. Industry research puts inventory distortion — stockouts plus overstock — at 6.2% of retail sales worldwide (IHL Group, 2026), and fashion is among the hardest-hit categories: only about 60% of fashion inventory sells at full price, and unsold merchandise runs at 17–20% of stock. Measured against that, De Rococo's 3.1% is roughly half the market average — in the industry's hardest category. That is what a well-run brand looks like before Sizo: better than the market, and still leaving real money on the table. 02 ### Implementing a solution One of the things we recognized really fast: they are not analysts, and they are not going to be. Another: an AI agent will not solve it alone — it needs statistical models to reduce cost and be more accurate. So we decided to move from reports into decisions. The brain #### Every shop gets its own brain We wanted each shop to have its own training, so we built a brain for the shops. It has main categories, and each SKU is a node living inside a cluster, connected by reason graphs. The idea is to let the agent conclude — and update its own data for its shop. The models #### Statistical models by category The statistical model was split into different categories: supply chain, size distribution, and quantity. The loop #### Alerts, and orders to the manufacturer The implementation also includes an alert system, and direct orders to manage them with the manufacturer. The locations #### Split right between stores De Rococo sells from multiple locations, each with its own demand profile. Sizo decides the total quantity first, then splits it between locations by what each store actually sells, per SKU — so a size isn't sitting in one store while selling out in another. The voice #### Short, direct answers Another thing we understood: they want short and direct answers. Every answer follows one shape: Overview→ Result→ Reason How the pieces fit together One brain per shop. The statistical models do the maths; the agent concludes, updates the brain, and acts. Each SKU is a node living inside a cluster; reason graphs connect what sells together, exchanges together, and shares a size curve. The agent never guesses at maths — it reads the models, concludes, and writes what it learned back into the brain. 03 ### The results Every number below comes from Shopify's own daily inventory record — 7.3 million variant-days measured identically before and after — never from Sizo's own event tables, which would flatter the comparison. One thing to hold in mind while reading: these gains did not come from selling less. The shop is growing fast — units sold in the compared season were up +65% on the year before and +257% on two years before, the number of products with active demand grew +90% in a year, and on the best-sellers demand tripled (+208%). More sell-pressure makes staying in stock harder — the improvements below are against the current, not with it. Result 1 #### Stockouts fixed faster #### Stockouts on selling sizes get fixed far faster Holds against every check 49% → 68.9%FIXED WITHIN 30 DAYS 36.7% → 56.0%WITHIN 14 DAYS 1,531STOCKOUTS SINCE INSTALL Before Sizo, when a size that was selling ran out, it was back within a month about half the time. With Sizo it is 69% — and that figure holds whether "before" means the previous 6 months, 12, 18, or the weeks immediately before the install. Every "before" lands in the same place Share of stockouts on selling sizes fixed within 30 days **Q: View as data table** | Definition of “before” | Episodes | Fixed ≤30d | | All pre-install (from Jan 2024) | 5,705 | 54.9% | | 18 months before | 4,258 | 49.1% | | 12 months before | 3,021 | 49.2% | | 6 months before | 1,911 | 49.8% | | The weeks just before install | 560 | 51.4% | | With Sizo | 1,531 | 68.9% | The comparison a sceptic should ask for is the weeks immediately before the install — same catalogue, same buyers, same season. They sit at 51.4%. With Sizo: 17.5 points higher. A step, not a trend Same measure by half-year: stuck around 50% all through the year before the install — then a 17-point step. **Q: View as data table** | Period | Episodes | Fixed ≤30d | | 2025 H1 | 1,043 | 47.1% | | 2025 H2 | 1,699 | 50.4% | | 2026 pre-install | 560 | 51.4% | | With Sizo | 1,531 | 68.9% | Recovery speed sat between 47% and 51% through the entire year before the install, then stepped up 17 points. Restricting to stockouts after alerting went live on 6 May, the figure is 68.4%. Result 2 #### Best-sellers kept on the shelf #### Best-sellers stayed in stock through the season Holds against every check 54%FEWER OUT MOST OF THE SEASON 42.5% → 30.5%OUT-OF-STOCK DAYS, MAR–JUN 218 → 405BEST-SELLERS COMPARED A best-seller here is a size that proved itself before the season — at least 10 units sold in the 60 days before March. In the first season with Sizo those sizes were out of stock 30% of days, down from 43% the season before, on nearly double the number of best-sellers and with units sold tripling — more sell-pressure, better availability. The sizes that sat out for most of the season — the ones that actually cost orders — fell by 54%, from 38.1% of best-sellers to 17.5%. 2025 bled out. 2026 held. Out-of-stock day share on proven best-sellers, month by month, Mar–Jun **Q: View as data table** | Month | 2025 | 2026 with Sizo | Gap | | March | 37.8% | 32.9% | −4.9 | | April | 41.5% | 31.8% | −9.7 | | May | 43.5% | 27.1% | −16.4 | | June | 47.1% | 30.2% | −16.9 | The worst month with Sizo (32.9%) beats the best month of 2025 (37.8%). May 2026 is the single best month in 28 months of data. The widening gap is what rules out the January stock buy as the explanation — a pile of stock helps most at the start, not the end. Result 3 #### Size ladders that hold #### The styles where size-mix loss fell Case studies 65%OF SIZE-MIX LOSS, GONE 14.9% → 5.2%DEMAND LOST TO MISSING SIZES 1 in 7 → 1 in 19SHOPPERS MEETING A MISSING SIZE Size-mix loss is the share of a style's demand that asks for a size that isn't there. On the group of running styles where Sizo's restocks landed, it fell from 14.9% to 5.2% — 65% of that loss gone. Before, roughly one shopper in seven met a missing size; now it is one in nineteen. The flagship is the Limited Edition Collared Satin Dress: since a Sizo-guided restock landed in June 2026, all five sizes have held with zero estimated loss in June, July and August. Result 4 #### New products launched right #### 500 new products launched — sized by Sizo's analysis Scale of use 500PRODUCTS LAUNCHED IN 6 MONTHS 13% → 20%BECAME REAL SELLERS, VS LAST SEASON +30%FIRST-90-DAY UNITS, VS LAST SEASON Sizo is not only for restocking what already exists. In the six months together, De Rococo launched 500 new products, with first orders sized on Sizo's recommendations from the shop's own demand analysis. Compared with the same launch season a year earlier — each product judged on its first 90 days only, so the comparison is fair — a similar number of launches produced 30% more units, and the share of launches becoming real sellers (100+ units in 90 days) rose from 13% to 20%. The table compares the February–May cohorts — the launches that have a year-earlier twin; the remaining launches of the six months bring the total to 500. | New products, launch season vs launch season | Last year | With Sizo | Change | | Products launched (Feb–May) | 307 | 330 | +7% | | Units sold in the first 90 days | 18,051 | 23,524 | +30% | | Average units per new product | 59 | 71 | +21% | | Became real sellers (100+ units in 90 days) | 13.0% | 20.3% | +56% | 04 ### What the wins were worth Putting money on the improved products — conservatively. A unit only counts as "captured" if the product's availability math implies it and the sales growth actually happened; we never credit a unit that wasn't really sold. First #### Money #### Most of the leak, closed Lost-sales method 77%OF THE LOST REVENUE RECOVERED 2.4%OF THE SEASON'S REVENUE, IN ABSOLUTE TERMS De Rococo came in leaking 3.1% of revenue to wrong orders and orders placed too late. That leak is the thing being measured against — not the whole business. Here is how much of it closed, and the calculation, step by step. For every product sold in both seasons, we measure the share of days it stood out of stock — last season against this one. Where availability improved, the extra selling days earn the product's own measured selling rate: a product that sold its units while on the shelf 70% of days, against 20% a year ago, has sales it simply could not have made at last year's availability. Those captured units are priced at the product's own realised prices from this season's actual orders, summed, and divided by the season's total revenue. Computed two ways: counting only captured units matched by sales growth that actually happened gives 1.7%; the standard lost-sales method — the selling rate applied to all recovered in-stock days — gives more, and we cap it conservatively at 2.4%. The fixed size ladders, where lost demand fell from one shopper in seven to one in nineteen, are included the same way: the old loss rate applied to this period's real demand, minus what was actually lost. Against the 3.1% leak, the 2.4% we report is 77% of everything there was to recover. Second #### Time #### The 30 minutes are gone −95%WORKING TIME ON THIS PROBLEM 30 min+ → secondsPER PRODUCT DECISION The report that took the team 30 minutes or more per product — fetched and calculated by hand, and still incomplete — now takes seconds in the agent. Across the ordering workflow, that cut up to 95% of the working time this problem used to consume. From the field > “Sizo does in seconds what used to take me and my employee a long time and pull us away from other work — saving us money on every single order.” Shon & Romy Spector · Co-founders, Dé Rococo Forbes 30 Under 30 · de-rococo.co.il 05 ### Conclusion De Rococo came in with the pain every mid-size fashion brand knows: plenty of data, no decisions. Six months later — stockouts on selling sizes fixed within a month 69% of the time instead of half, best-sellers held through the season, lost demand on fixed ladders down from one shopper in seven to one in nineteen, and new products selling 30% more in their first 90 days — together closing 77% of that 3.1% leak, worth 2.4% of a season's revenue. And it happened while the shop scaled. Growth is supposed to create mess — recovery sat stuck around 50% through the whole year before the install. With Sizo, selling more than triple the units of two years ago, the shop runs at its best level in the data. No one had to become an analyst: the brain holds the shop's knowledge, the models do the maths, and every decision leaves the app as an alert or a purchase order — not another report. The pain was never a missing report. It was the moment of decision — and that is the moment Sizo now owns with the merchant. sizo · 2026 HOME FREE AUDIT CASE STUDIES PRICING PRIVACY INFO@SIZO-AI.COM --- # Pricing Source: https://sizo-ai.com/pricing Pricing ## Simple plans. Start free today. Install Sizo from the Shopify App Store and start on Free — no card, no call. We still onboard brands hands-on, validate every recommendation against real purchase orders, and tighten the model against your category. Pricing in USD, billed monthly or yearly on your regular Shopify invoice. Change or cancel your plan any time from inside the app. - Shopify App Store - Read-only access - No trials - Cancel anytime ### Free $0 / month See what sold-out sizes cost you. Connect your store and get the audit — no card. - One-click connect to Shopify — read-only, no dev work - 2 products analyzed a month - 500K of AI thinking a month - Lost-revenue audit on your last 12 months - Size-mix and sell-through breakdown, plus the weekly brief - Email support Urgent sellout alerts and the Combined Ratio planner start at Advanced. Get your free audit ### Advanced $99 / month or $999/year — save 16% The full restock engine. Size ratios, totals, and alerts for every product in your catalog. - Everything in Free - 50 products analyzed a month - 5M of AI thinking a month - Size-ratio & restock-quantity recommendations - Confidence scoring & stockout-aware demand - Urgent sellout & restock alerts — up to 100 emails a month - Combined Ratio planner, bulk CSV export, custom benchmarks - Priority support Connect your shop ### Pro $500 / month or $5,000/year — save 17% Everything in Advanced, with room to breathe — for larger catalogs and teams running Sizo across the whole range. - Everything in Advanced - 300 products analyzed a month - 20M of AI thinking a month - Sellout alerts that are never rationed - Custom benchmarks & priority support Connect your shop All plans are read-only — Sizo never writes to your store. Paid plans are billed on your regular Shopify invoice, and you can upgrade, downgrade or cancel at any time from the app’s Settings. How we work ### Trained on your shop, not the industry average. #### Hands-on onboarding We sit with each design partner, connect the store, and walk through the first recommendations together. #### Validated against real POs Every recommendation is checked against the brand’s actual next purchase order so the math earns trust. #### Tuned to your category The model is trained on your shop — not the industry average — and we tighten it against your size curve. #### Start free, move up when it pays Look into two products a month on Free. Upgrade when the numbers justify it — and change or cancel your plan any time from Settings. Get started ### Pick a plan when you’re ready. Start on Free. Install from the Shopify App Store and get your lost-revenue audit on the Free plan. Upgrade from inside the app whenever you want more. Connect your shopGet a free audit Or write to us directly: info@sizo-ai.com Shopify App Store · Read-only access · No trials --- # Privacy policy Source: https://sizo-ai.com/privacy Legal · Privacy ## Privacy Policy Sizo reads a Shopify store's sales and inventory data to forecast demand and recommend smarter restocks. This policy explains exactly what we read, what we store, who processes it, and how a merchant can have it exported or deleted. Effective date: July 14, 2026 ### 1. Who we are & scope Sizo AI ("Sizo", "we", "us") provides an inventory prediction and restock-recommendation application for fashion brands selling on Shopify. The app reads a merchant's store data through the official Shopify Admin API and turns it into demand forecasts and size-ratio recommendations. This policy applies to the Sizo app installed on a Shopify store and to this marketing website (sizo-ai.com). It is written for the Shopify merchants who are our customers. Questions about this policy or any request relating to your data can be sent to info@sizo-ai.com. ### 2. What we collect When a merchant installs Sizo, the app reads store data via the Shopify Admin API to power its forecasts. This includes: - Products and variants — titles, options, SKUs, sizes, colors, vendors, and prices. - Inventory levels — on-hand and available quantities, including per-location stock. - Orders and sales history — line items by SKU and size, quantities, discounts, and refunds/returns. - Locations and fulfillments — store and warehouse locations and how orders were fulfilled. We use this data to model real demand by size, exclude items that were unsellable because they were out of stock, and recommend the right size ratio and quantity for the next restock. We do not collect or store your customers' personal information. The only customer-related value we retain is the pseudonymous Shopify Customer ID (for example gid://shopify/Customer/123…), which we use solely to connect a refund to a later reorder by the same shopper so our return analysis is accurate. We do not collect, store, or process customer names, email addresses, phone numbers, or shipping/billing addresses. For the merchant's own account we store the store domain and the email address associated with the Shopify session, used for app access, alerts, and support. Team contact details. During onboarding a merchant may add teammates — names, email addresses, and phone numbers — so Sizo can route alerts and weekly digests to them. Providing these details is voluntary; they are used only for notifications and access roles, and anyone listed can ask to see, correct, or delete their details at any time (see section 6). ### 3. How we use data We use store data for two purposes only: - Inventory optimization analytics — forecasting demand by size, detecting stockouts, measuring lost revenue, and generating restock recommendations specific to your shop. - An optional AI assistant — a conversational feature that answers questions about your own store's data on request. Queries and the relevant data are processed by our AI subprocessor (see below) to produce an answer for you. We do not sell your data, and we do not use your data to train third-party AI models for other customers. Your store's data is used to serve your store. ### 4. Subprocessors We rely on a small set of trusted providers to operate the service. Each processes data only as needed to deliver their function: - Shopify — the source platform; we read store data through Shopify's official Admin API. - Fly.io — application hosting (Amsterdam, Netherlands). - Aiven — managed PostgreSQL database (AWS infrastructure, EU eu-west region). Each store's data lives in its own isolated schema. - Anthropic — AI processing that powers the optional AI assistant (United States); inputs are not retained to train models. - Resend — delivery of email alerts and notifications (United States). - Microsoft Clarity — usage analytics on this website and inside the Sizo app (heatmaps and session recordings; typed input and sensitive fields such as email addresses are masked before leaving the browser; United States). Store data is therefore stored in the European Union, with limited processing in the United States by the AI and email providers above. ### 5. Data retention, deletion & GDPR We honor Shopify's mandatory privacy webhooks and respond to them automatically: - customers/data_request — a merchant's request, on behalf of a shopper, for the data we hold. - customers/redact — a request to delete a specific shopper's data. - shop/redact — sent by Shopify after a store uninstalls Sizo, instructing us to delete the shop's data. While the app is installed we retain store data for as long as needed to provide forecasts and historical analysis. After an uninstall we keep the store's data for 48 hours in case of reinstall; when Shopify's shop/redact webhook arrives at the end of that window, the store's entire database schema is deleted. If a store uses Sizo through more than one Shopify app installation, deletion runs when the last installation is removed. Every deletion decision is recorded in an audit log. Merchants can request an export or deletion of their data at any time by emailing info@sizo-ai.com. If you are in a jurisdiction with data-protection laws such as the GDPR, you may have rights to access, correct, export, or delete your data; we will act on verified requests sent to that address. ### 6. Israeli Privacy Protection Law (Amendment 13) Sizo complies with the Israeli Privacy Protection Law, 5741-1981, as amended by Amendment 13 (in force since August 2025). Two roles apply: - For a store's data (orders, inventory, pseudonymous customer identifiers) the merchant is the database controller (בעל שליטה במאגר) and Sizo acts as a holder (מחזיק), processing the data only on the merchant's behalf and instructions. - For Sizo's own operational records (merchant accounts, app settings, usage events, configured team contact details) Sizo is the controller. Notice at collection (Section 11). Wherever the app asks a merchant to enter personal details about people — such as teammates' names, emails, and phone numbers — it states at the point of collection that providing them is voluntary, what they are used for, who receives them, that they are stored outside Israel (in the EU, per section 4), and how long they are kept. Access, correction, and deletion. Any person whose details we hold may request to review, correct, or delete them — in the app's Settings page or by emailing info@sizo-ai.com. Security incidents. If a security event affects a store's data we will notify the affected merchants — and, where Israel's Data Security Regulations require it, the Privacy Protection Authority — without undue delay. ### 7. Security Data is encrypted in transit over HTTPS and is access-controlled within our infrastructure. We request the minimum (least-privilege) Shopify API scopes the app needs to function, and we use read-only access to Shopify for analysis wherever possible. No method of transmission or storage is perfectly secure, but we work to protect your data and to limit who and what can access it. ### 8. Cookies The Sizo app itself uses only the cookies required for an authenticated session inside Shopify. This marketing website uses a small amount of privacy-respecting analytics to understand aggregate traffic; it does not use advertising or cross-site tracking cookies. ### 9. Changes to this policy We may update this policy from time to time. When we make material changes we will revise the effective date above and, where appropriate, notify merchants. Continued use of Sizo after an update means you accept the revised policy. ### 10. Contact For any privacy question or request, write to us at info@sizo-ai.com.