Data to AI™ / Copilot/Google Merchant Center
Let ecommerce and marketing teams ask a Copilot agent in Teams which products are blocked, mispriced or missing data in Merchant Center.
Less tokens, better answers.
Microsoft 365 Copilot
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.
@Feed Health How many products per Brand have at least one item-level issue right now? Show the five worst brands.
Category managers mention the agent in their Teams channel, see which brands carry the most issues and assign fixes to the right supplier contact in the same conversation.
@Feed Health List offers where Sale Price is equal to or higher than Price, with Offer ID, Title and Price Currency.
In Microsoft 365 Copilot, the pricing team gets a list of sale prices that do not discount anything and corrects them before the next feed upload.
Use the dataddo tools to describe the Products entity and update our feed validation rules for Price, Availability and GTIN.
A developer uses GitHub Copilot in Agent mode to align in-house validation with the attributes that Merchant Center names in Item Level Issue Attribute Name.
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 | |
|---|---|---|---|
| Feed status for the whole team | One person owns the Merchant Center login and forwards screenshots of diagnostics to whoever asks. | A Copilot Studio agent in Teams answers any category manager from the same Product statuses data. | Everyone sees the same issues |
| Routing questions to the data | Copilot answers feed questions from general knowledge, because it cannot see your catalog. | The server description in Copilot Studio tells the agent to call Dataddo for products, prices, availability and item-level issues. | Answers from your feed |
| Validation code in VS Code | Developers copy attribute names from documentation pages and hope they match what the feed actually contains. | GitHub Copilot reads field names from Dataddo through .vscode/mcp.json, once an org admin on Business or Enterprise enables the MCP servers in Copilot policy. | Rules match the feed |
| Token consumption | Copilot 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. Copilot 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 →Create Dataddo sources for Products and Product statuses from Google Merchant Center and attach them to a Copilot destination or AI Model. In Copilot Studio, add a Model Context Protocol tool with https://headless.dataddo.com/mcp-data, select OAuth 2.0 with Dynamic discovery, sign in and publish to Teams and Microsoft Copilot.
In Microsoft 365 Copilot and in Teams, after you publish the Copilot Studio agent through Channels > Teams and Microsoft Copilot. Users type @ and select the agent.
Write the server description in Copilot Studio around Merchant Center products, prices, availability and item-level issues. The agent uses that description to decide when to call Dataddo.
Yes, with GitHub Copilot. Add the server to .vscode/mcp.json, start it and sign in, then use Agent mode. Business and Enterprise orgs need the MCP servers in Copilot policy enabled.
Each run pulls the full current catalog without a date range, so the agent answers about the catalog as of the last run, not a history of changes.
No. It only reads the extracted Products and Product statuses data. Feed updates happen in Merchant Center or in your feed tooling.