Data to AI™ / ChatGPT/Google Merchant Center
Ask ChatGPT about availability, expiring listings and product identifiers across your Merchant Center catalog, and approve every data lookup it makes.
Less tokens, better answers.
ChatGPT
Which feed issues keep the most of our products out of Shopping right now?
Invalid GTINs affect 412 of 5,020 products (8.2%), more than price mismatches and small images combined (283).
| Issue | Item Level Issue Attribute Name | Products | Share of catalog |
|---|---|---|---|
| Invalid GTIN Product statuses | gtin | 412 | 8.2% |
| Price mismatch Product statuses | price | 186 | 3.7% |
| Image too small Product statuses | image_link | 97 | 1.9% |
Counted from the latest Product statuses run, which pulls every current product; the dataset has no date range.
Google Merchant Center holds the product listings that appear on Google Shopping. Dataddo extracts two datasets: Products, with feed attributes such as price and availability, and Product statuses, with approval status and item-level issues.
How many products have Availability set to out of stock in each Target Country? List the brands with the most of them.
An ecommerce manager approves the query call and gets a per-country table for the buying team, without filtering a full feed export in a spreadsheet.
Call data_status on the Merchant Center flows, then list offers whose Google Expiration Date falls within the next 14 days.
The weekly check starts with freshness, so the team knows the list reflects this morning's run before anyone acts on it.
Which offers have neither GTIN nor MPN, broken down by Brand and Google Product Category, and what is their Identifier Exists value?
The catalog team sees where supplier data is incomplete and requests identifiers brand by brand, instead of scanning thousands of rows by hand.
Data to AI™ is free while in private pre-release. We onboard teams in waves and shape the product with their feedback. At launch, it will be priced like the AI assistants your team already uses. Need tailored contracts or volume pricing? Talk to us about Enterprise.
Serve governed business data to Claude, ChatGPT and other AI tools over MCP.
Free during pre-release
Flexibly deploy Dataddo in any cloud or hybrid environment.
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Getting the catalog into ChatGPT | Someone exports the full product list and uploads it to the chat, and the file is outdated after the next price or stock change. | A ChatGPT developer mode app reads Products and Product statuses from Dataddo whenever a question needs them. | No catalog uploads |
| Approving each lookup | Once a file is attached, there is no step where you see which part of the data an answer draws on. | ChatGPT asks you to confirm every tool call, showing whether it queries Products, Product statuses or data_status. | You see each query |
| Feed state, not history | Comparing two exports from different days is the only way to see what changed, and their dates are easy to mix up. | Each run reflects the catalog at that moment, and the optional Dataddo Extraction Timestamp column marks when every row was read. | A clear snapshot date |
| Limiting tool access | A file attached to a chat comes with no controls over what the assistant may do around it. | In the app settings you can switch off tools such as refresh while keeping query and describe_entity available. | Only the tools you allow |
| Token consumption | ChatGPT spends tokens exploring raw Google Merchant Center columns, sampling rows and retrying until it understands the data. | Field definitions and relations are supplied up front, so the model skips the exploration and goes straight to the answer. | Less tokens per answer |
| Answer quality | Prone to wrong joins, invented fields and numbers that are hard to check. | Answers grounded in defined fields. In the Dataddo benchmark, 78.5% of questions were answered correctly, against 65.5% with plain CSV files. | Better answers |
The Google Merchant Center datasets marketing teams use most, with their real field names. ChatGPT queries them by name through the Dataddo semantic layer.
List of curated datasets
Need a dataset, metric, or attribute you don't see?
Tell us what's missing and we'll add it to the connector.
Neither dataset uses a date range: every run on your schedule, for example daily, pulls all products and statuses currently in Merchant Center. The optional Dataddo Extraction Timestamp column shows when each row was read.
Google Merchant Center connector →We asked 43 pre-registered questions of three real datasets - Google Search Console, HubSpot deals and Google Ads - and delivered the same rows to the same model in four ways. Only the data layer changed.
of questions answered correctly - the best of the four delivery methods tested
fewer confidently wrong answers - 14.0% of runs against 24.0% and 26.3%
more correct answers on messy CRM data - better on 8 questions, worse on none
Same model, prompts and rows in every condition; 759 graded runs, ground truth frozen before any run. On Google Search Console alone, documented CSV files did as well as Data to AI™ - the advantage comes from messier data such as HubSpot deals.
Read the benchmark →Set up Dataddo sources for the Merchant Center Products and Product statuses datasets and attach them to a ChatGPT destination or AI Model. In ChatGPT on the web, enable developer mode under Settings > Security and login, create an app with https://headless.dataddo.com/mcp-data and OAuth, then sign in.
One with developer mode: Pro, Plus, Business, Enterprise or Education, used on the web. On Business and Enterprise an admin may have to allow developer mode first.
Developer mode asks you to confirm each tool call. Approve it, and ChatGPT runs the Dataddo query on Products or Product statuses and answers from the result.
It is as current as the last scheduled run. Each run pulls the full current catalog, and ChatGPT can call data_status to show when that happened.
The datasets carry no date range and each run reflects the catalog at that moment, so ask ChatGPT about the current state, not long-term trends.
Yes. In the app settings you can switch off individual tools, such as refresh, and keep read tools like query and describe_entity on.