By
Austin Coker
Reading time: 22 min
Instead of buyers scrolling through search results and clicking links, AI agents in Google’s AI Mode and Gemini now evaluate product data directly, compare options, and recommend products to buyers in real time.
If your products aren’t set up for UCP, they’re invisible to these AI agents. It doesn’t matter how good your Google Ads are or how well your site ranks organically. AI-powered shopping is a separate channel, and it requires its own setup.
This guide walks you through the complete Google UCP setup, step by step. It’s platform-agnostic. Whether you’re on Shopify, WooCommerce, BigCommerce, Magento, or a custom platform, the Google side of UCP works the same way.
Before diving into UCP setup, make sure you have:
Google Merchant Center is the foundation of everything UCP-related. It’s where Google stores, validates, and serves your product data to AI agents. Without it, UCP doesn’t work.
If you already have a Merchant Center account, skip to the optimization section below. If not:
Google needs to confirm you own the website you’re listing products from:
HTML tag verification is the fastest for most merchants. Just add the meta tag to your site’s head section.
This is often overlooked. Google offers free product listings across Search, Shopping, Images, Maps, and YouTube. These listings also feed into AI Mode recommendations.
This gives your products maximum visibility across Google’s ecosystem, including the AI agents that power UCP.
If you run Google Ads, linking your Merchant Center account gives AI agents additional performance signals about your products:
You don’t need Google Ads for UCP to work, but the additional data helps Google’s AI agents understand which of your products perform well and deserve recommendations.
Your product feed is the data AI agents use to evaluate your products. If the data is incomplete, vague, or inconsistent, AI agents will skip your products and recommend a competitor’s instead.
This is the most important step in the entire process.
Every product in your feed must have:
Missing any of these will either get your product disapproved or severely limit its visibility to AI agents.
These aren’t technically required by Merchant Center, but they’re essential for UCP. AI agents use these to compare and recommend products:
This is where most merchants get it wrong. Titles optimized for Google Shopping ads are not the same as titles optimized for AI agents.
Shopping ad titles front-load keywords for click-through rate. AI agent titles need complete product information because the agent is evaluating whether to recommend your product, not whether a human will click on it.
“Blue Jacket XL – Free Shipping – Best Price”
“Men’s Waterproof Hiking Jacket, Navy Blue, XL, Gore-Tex Shell, Rated to -10C, 340g”
“Industrial Air Compressor – SALE”
“DeWalt 60-Gallon Two-Stage Industrial Air Compressor, 175 PSI Max, 6.5 HP, 230V Single Phase”
“Premium Dog Food”
“Orijen Original Grain-Free Dry Dog Food, 25 lb Bag, Fresh Free-Run Chicken and Turkey”
AI agents parse every word. Include: brand, product type, key specs, size/weight, distinguishing features. Leave out: promotional language, “best price,” “free shipping,” urgency words.
Your descriptions need to be functional, not persuasive. AI agents don’t respond to emotional language. They need facts.
“Experience the ultimate in comfort with our premium jacket. You’ll love the way it feels. Perfect for any adventure!”
“Waterproof hiking jacket with Gore-Tex shell membrane. Rated to -10C. Sealed seams prevent moisture penetration. Adjustable hood fits over helmets. Two zippered chest pockets and one internal mesh pocket. Weighs 340g. Suitable for alpine hiking, cold-weather camping, and winter day hikes. Machine washable on gentle cycle.”
The good description gives an AI agent everything it needs to compare this jacket against competitors: waterproof rating, temperature rating, weight, features, use cases, and care instructions.
AI agents will not recommend products with mismatched data. This is non-negotiable:
If a buyer follows an AI agent’s recommendation and finds a different price on your site, Google penalizes your feed quality score. This reduces future AI recommendations.
We’ll audit your catalog and show you exactly what needs to change.
This is the UCP-specific layer that most merchants don’t know about yet. Google is rolling out new feed attributes designed specifically for AI-powered shopping conversations.
These attributes feed directly into AI Mode and Gemini conversations. Products with these attributes get richer, more detailed recommendations.
What questions do customers frequently ask about this product? Add them to your feed:
Example for an air compressor: “What size air hose do I need?” “Can this run two tools at once?” “Does it require 220V or 110V?”
AI agents use these to proactively answer buyer questions during the recommendation conversation, which makes your product more likely to be selected.
What accessories or complementary items work with this product?
Example: “Compatible with DeWalt 3/8-inch and 1/2-inch pneumatic impact wrenches, 50-foot rubber air hose (3/8-inch), and inline moisture filter.”
This helps AI agents make bundled recommendations and answer “what else do I need?” questions.
If this product is out of stock, what alternatives would you recommend from your own catalog?
This keeps buyers in your store even when their first choice isn’t available. AI agents can redirect to your alternative instead of recommending a competitor.
In what situations or scenarios is this product used?
Example for a commercial dehumidifier: “Water damage restoration, basement moisture control, construction site drying, warehouse humidity management, indoor pool room climate control.”
Use cases help AI agents match your product to specific buyer needs. The more specific you are, the better the match quality.
Structured data gives AI agents a second data source beyond your Merchant Center feed. When both sources agree and provide rich information, AI agents have higher confidence in recommending your products.
Every product page on your site should include comprehensive JSON-LD markup. Here’s what to include:
Google cross-references your structured data with your Merchant Center feed. When both sources provide consistent, complete information, your product gets a higher quality score. Discrepancies (different prices, different descriptions) lower your score and reduce AI recommendations.
Think of it as two votes of confidence. Merchant Center says your product costs $299 and is in stock. Your structured data confirms: $299, in stock. The AI agent trusts the data and feels confident recommending it.
Use Google’s Rich Results Test (search.google.com/test/rich-results):
Common issues: missing GTIN, price format errors, availability status not matching your site, aggregate rating without review count.
Your ecommerce platform is what generates and syncs your product feed to Merchant Center. The connection method depends on your platform.
Shopify has native Google Merchant Center integration through the Google and YouTube app. It also supports Agentic Storefronts, which is Shopify’s UCP implementation.
For detailed Shopify setup, see our complete Shopify UCP guide.
WooCommerce connects to Merchant Center through the Google Listings and Ads plugin or through third-party feed management tools like Google Product Feed Pro.
BigCommerce offers a native Google Shopping integration in the Channel Manager. Connect your store, map your product attributes, and sync your catalog.
Use the Google Shopping Feed extension or a third-party feed management tool. Magento requires more manual configuration than Shopify or WooCommerce.
If you’re on a custom platform, you’ll need to generate a product feed in Google’s required format (XML, TSV, or Google Sheets) and upload it to Merchant Center directly or via the Content API for Shopping.
Regardless of platform, the key requirement is the same: your feed must be complete, accurate, and synced regularly. Daily syncs are the minimum. Real-time syncs are ideal.
With your product data optimized and your platform connected, it’s time to enable UCP-specific settings.
Note: Google is rolling out UCP settings in phases. If you don’t see these options yet, your account may not have access. Ensure your Merchant Center account is in good standing and your product feed has no critical errors.
When available, you can enable different UCP capabilities:
Enable all capabilities. The more access AI agents have to your product data, the more likely they are to recommend your products over competitors who share less data.
Review what data is shared:
You maintain control over what’s shared. But restricting data access reduces AI agent confidence in your products, which reduces recommendations.
Don’t assume everything is working. Test it.
In Google Merchant Center:
Aim for zero disapprovals and minimal warnings. Every disapproved product is invisible to AI agents.
Test 5 to 10 product pages across different categories:
This is the real test. Try searching for your products the way an AI agent would:
The most common reasons are:
UCP requires a fundamentally different approach to product data. It’s not about keywords or click-through rates. It’s about giving AI agents enough information to confidently recommend your product.
“Feel the difference” means nothing to an AI agent. “340g waterproof jacket rated to -10C” means everything.
Common questions, compatible products, substitutes, and use cases are the differentiator. Most competitors aren’t using these yet. If you do, your products get richer AI recommendations.
Google is updating UCP capabilities regularly. New attributes, new settings, new AI agent behaviors. Your product data needs ongoing attention.
This is the fastest way to get your products deprioritized. If your site says $299 and Merchant Center says $279, AI agents lose trust in your data.
The only way to know if UCP is working is to ask AI agents about your products and see what happens.
Once your UCP setup is complete and validated:
Google reindexes your updated Merchant Center data and structured data.
Your products may start appearing in AI Mode recommendations and Gemini responses.
AI recommendation frequency should increase as agents build confidence in your product data.
Continue optimizing, adding conversational commerce attributes, and monitoring AI recommendations.
The timeline varies by category competitiveness and catalog size. Well-optimized stores with complete data typically see AI-driven visibility within the first month.
Currently, Google doesn’t provide a dedicated UCP analytics dashboard. Monitor through:
As UCP matures, expect Google to add more granular reporting. For now, the best signal is whether your products appear when you ask AI agents about your category.
Start with Step 1 and work through each step sequentially. Don't skip the product data optimization (Step 2). It's the foundation everything else depends on.
Read our UCP overview guide for broader context on what UCP means for ecommerce.
If you're on Shopify or WooCommerce, follow up with the platform-specific guide after completing these Google-side steps.
If you want expert help, schedule a call for an AI commerce audit. We'll assess your product data, Merchant Center setup, and structured data, then tell you exactly what needs to change.
UCP is the most significant new commerce channel since Google Shopping launched. The brands that set up now build an advantage that compounds over time as AI-powered shopping grows. Waiting means your competitors get indexed first.
Want us to handle this for you? We set up and optimize Google UCP for ecommerce and B2B brands. Schedule a call for an AI commerce audit at 95projects.com.
Have questions about working with us? Book a 30-minute strategy call to discuss your goals and see if we’re a good fit.
No-pressure conversation
Clear next steps (if we’re a fit)
Talk directly to an expert
No. Google Merchant Center is free. UCP participation is free. You don’t need Google Ads for UCP to work, though linking your Ads account provides additional data signals. The only cost is the time to optimize your product data.
All of them. Any platform that can generate a product feed for Google Merchant Center works with UCP. Shopify and WooCommerce have native integrations. BigCommerce, Magento, Wix, Squarespace, and custom platforms all work through feed uploads or API connections.
Google Shopping is a product listing service where buyers browse and click through to your site. UCP is a commerce protocol where AI agents evaluate your product data, compare it against competitors, and recommend products directly to buyers in conversation. Shopping is passive (you list, buyers find). UCP is active (AI agents evaluate and recommend).
No. UCP works through free product listings and AI-powered surfaces. However, running Google Ads (especially Performance Max) gives Google additional performance signals about your products, which may improve AI agent recommendations.
AI Mode and Gemini are the interfaces where buyers interact with AI agents. UCP is the protocol that feeds your product data to those agents. When someone asks Gemini “What’s the best dehumidifier for a basement?”, the AI agent queries UCP-connected product data to generate its recommendation. Your Merchant Center feed, structured data, and conversational commerce attributes are what the agent evaluates.
Yes. B2B products with clear specifications, pricing, and use cases work well with UCP. In fact, B2B buyers who research online before purchasing are exactly the type of buyer AI agents assist. If your B2B product can be listed in Google Merchant Center (which many can), it can participate in UCP.
Product data completeness. Every step in this guide ultimately comes back to one thing: giving AI agents enough accurate, detailed information to confidently recommend your product. Stores with complete attributes, functional descriptions, and conversational commerce data consistently outperform stores with minimal feeds.
