01 Access and authorization
Confirm the merchant account, domain and target markets, and get merchant authorization. For the Merchant API, create an API data source first.
PLATFORM PLAYBOOK / 02
Merchant Center / AI Discovery
From your catalogto GoogleMerchant Center.
Gemini's product data starts in Merchant Center. Map feed fields, submit through the Merchant API, read product status back and keep changes in sync.
This page describes a service. Merchant Center eligibility, review and which AI experiences are supported are Google's call.
CATALOG → CONSISTENCYIllustration
Start from data consistency
“Do the feed and the product page show the same price right now?”
01
Source checkCatalog ↔ product page
02
Spec validationIdentifiers · variants · required fields
03
Issue handlingDiagnose → fix → resubmit
Consistent data is what keeps products published.
Reuse your product masterSourced AI enrichmentMapped to each platform's specTraceable updates and releases
PRODUCT FEED INTEGRATION
How does your catalog connect to Google Merchant Center?
Read the source → map fields → validate against the spec → submit → read results back. This is the integration design, not a live connector.
02 Export and submit
Plan a file source or the Merchant API. The API writes through productInputs; the table below uses feed field names, which map to API fields and types during implementation.
03 Updates and removals
Price, stock and discontinuation events trigger updates or deletions. After submitting, read products back for processing results, per-destination status and data issues, not just a successful API call.
Field mapping: get the spec right first.
The left column is a source-data concept, not a verified field name in your system; required, conditional and market rules follow the official spec.
| Source data concept | Google Feed field | Mapping and validation |
|---|---|---|
| SKU | id | Keep a stable product identifier. |
| Name / description | title / description | Content must match the landing page. |
| Product page / main image | link / image_link | Each variant points to the right page and image. |
| Price / stock | price / availability | Check currency, promotions and availability. |
| Brand / barcode | brand / gtin / mpn | Follow category and identifier rules; never invent barcodes. |
| Parent product / options | item_group_id / color / size | Keep variant data as category and market rules require. |
An integration you can accept and audit.
Traceable batches
Keep product IDs, source versions, submission times and results. Catch missing required values first; retry transport failures, but don't resend rejected data forever.
Fix, then verify again
Format errors fix the mapping; data conflicts go back to the source; permission and policy issues go to their owners. Inclusion and recommendation are never guaranteed.
Integration docs: Merchant API product lifecycle ↗
KNOW THE BOUNDARIES
Shopping, AI experiences and checkout are different things.
Being clear about what each platform supports, and what onboarding needs, comes first.
Product data entry
Merchant Center and the Merchant API are where product data is managed; eligibility follows account, product, country and destination rules.
AI shopping discovery
Google says existing Merchant Center Shopping feeds support product discovery; an approved product isn't guaranteed to appear in Gemini.
UCP commerce
UCP supports commerce actions in AI experiences. It doesn't replace your everyday feed, and a feed alone doesn't complete checkout integration.
DATA, NOT GUESSWORK
Every field has a job to do.
These are onboarding checkpoints, not the full platform spec; required fields depend on category, market and the approved format.
| Area | Data | How we plan it |
|---|---|---|
| Product identity | ID, brand, GTIN / MPN | Apply identifier rules by product type; never invent a GTIN when one is missing. |
| Variants | item_group_id, color, size | Keep parent–child relationships and check each variant's link and image. |
| Price and availability | price, availability, product page | Compare feed, page and checkout; fix the source, not just the displayed text. |
| Markets and policy | Language, currency, shipping, returns | Check data specs and merchant policies together; confirm extra requirements by region and category. |
WORKED EXAMPLE
From one question
to one fix you can make.
An illustration, not customer data or a platform report.
- Spot
Feed price doesn't match the product page
- Check
Compare source timestamps, promotion dates and currency
- Fix
Fix the source, resubmit, then confirm the diagnostic status
FROM CATALOG TO MARKET
Don't rebuild your catalog. Build a publishing flow.
Your product system keeps the original facts; AI Catalog manages enrichment, review history and platform outputs.
- 01
Audit the account
Confirm domain, sales markets and existing data sources.
- 02
Validate the spec
Check required fields, identifiers, variants and policies.
- 03
Publish and fix
Plan file or Merchant API sync and work through diagnostics.
- 04
Keep it in sync
Sync product changes, discontinued items and stock so nothing goes stale.
A successful submission isn't the finish line.
Publishing health
Track available processing status, data freshness and open issues.
Observable results
Watch exposure and referral traffic separately; an accepted product is not proof of an AI recommendation.
BEFORE YOU START
Worth asking first.
No shortcut guarantees ranking.
A data flow you can check and fix does help.
I already use Google Merchant Center. What else is there to do?
Start from your existing sources and issues instead of rebuilding the account: field gaps, variant mapping, site consistency and the update flow, then fix what matters most.
Is Google Merchant Center the same as a Gemini feed?
Not exactly. Merchant Center is the product data foundation; which AI experiences show products, and in which markets, is up to Google. An approved product is not proof of Gemini exposure.
Do I need to integrate UCP?
Everyday product data management and UCP commerce integration are separate projects. Build an accurate, current feed first; consider UCP when you need AI checkout and qualify.
Can this page log in to my account or fix disapprovals?
No. It describes a service and never accesses Merchant Center. Real onboarding needs merchant authorization, an account diagnosis and an agreed scope.
START WITH YOUR CATALOG
Start with your product data.
Bring your target markets, catalog scope and platform account status, and we'll scope a pilot.
Book a catalog consultation Opens Crescendo Lab's official contact page; this page collects no data and connects to no platform.