Data to AI™ / Copilot/Google Search Console
Give marketing a Copilot agent in Teams that answers questions on organic clicks, rankings and CTR, and let developers query the same data in VS Code.
Less tokens, better answers.
Microsoft 365 Copilot
Which blog pages lost the most clicks in September compared with August?
The CRM guide lost 1,240 clicks, down 37%, the largest drop, and now averages Position 7.8. The other two pages fell 21% and 12%.
| URL | Clicks (Sep) | Clicks (Aug) | Position (Sep) |
|---|---|---|---|
| /blog/crm-guide Daily Metrics by Page | 2,140 | 3,380 | 7.8 |
| /blog/pricing-models Daily Metrics by Page | 1,620 | 2,050 | 5.2 |
| /blog/api-basics Daily Metrics by Page | 980 | 1,110 | 6.4 |
Page rows are sampled by Google, so pages are compared with each other and not added up into a site total.
Google Search Console shows how a site performs in Google search: Clicks, Impressions, CTR and average Position by date, query, page, country and device, for the properties your account can access.
@Search desk How did our new pricing landing page rank last month, and how many Clicks did it get from Daily Metrics by Page?
Campaign and content managers ask the agent in Teams instead of requesting a report from the SEO specialist, who gets time back for actual optimization work.
Use the dataddo tools to query Daily Metrics by Page for URLs under /docs with Impressions but zero Clicks in the last 30 days.
A developer maintaining the documentation site uses GitHub Copilot in Agent mode, then fixes titles and meta descriptions for those pages in the same pull request.
@Search desk Show Impressions and Position by Country for our top product queries last quarter from Daily Metrics by Country and Query.
In Microsoft 365 Copilot, the regional marketing lead checks where the brand is already visible in search before planning budgets for local campaigns.
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 | |
|---|---|---|---|
| SEO numbers for non-specialists | Marketing colleagues ask the SEO specialist for a Search Console report and wait days for a spreadsheet. | The Copilot Studio agent in Teams answers questions on Clicks, Impressions and Position directly from the Dataddo flow. | Self-service SEO answers |
| Data in the developer workflow | Developers download a CSV of page performance and commit it next to the code to check titles. | GitHub Copilot in VS Code queries Daily Metrics by Page through the Dataddo server in Agent mode, so no file lands in the repository. | No CSV in the repo |
| When the agent calls Dataddo | A general Copilot answer about rankings draws on web knowledge, not on your own Search Console properties. | The server description in Copilot Studio names organic clicks, queries and rankings, so those questions trigger a Dataddo lookup. | Answers from your properties |
| Recent days | A report pulled too early shows partly processed days, and the channel reacts to a drop that is not real. | The source uses a date range of 4 days ago or older, so the agent only reports days Google has finished processing. | No false alarms |
| Token consumption | Copilot spends tokens exploring raw Google Search Console 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 Search Console 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.
Runs on the schedule you set over a relative date window. Google needs 24 to 72 hours to process data, so use a range of 4 days ago or older; the API returns up to 16 months of history.
Google Search Console 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 a Google Search Console source in Dataddo with Daily Metrics by Page and Daily Metrics by Query, and attach it to a Copilot destination or AI Model. In Copilot Studio, add https://headless.dataddo.com/mcp-data as an MCP tool with OAuth 2.0 and publish to Teams, or use .vscode/mcp.json for GitHub Copilot.
Yes. Publish your Copilot Studio agent with the Dataddo MCP tool and add it under Channels > Teams and Microsoft Copilot. Colleagues mention it and ask about clicks, queries and pages.
Query and page data is sampled, so sums over queries or pages differ from the UI while trends stay the same. For totals, point the agent to Daily Metrics or the country and device datasets.
Google needs 24 to 72 hours to process the data. Dataddo recommends a date range of 4 days ago or older for Search Console, so recent days appear a little later.
On Copilot Business and Enterprise, yes: an organization admin must enable the MCP servers in Copilot policy. Then add the server to .vscode/mcp.json and use Agent mode.
Say so in the server description in Copilot Studio, for example organic clicks, queries and rankings. The agent uses that description to decide when to call Dataddo.
The authorizing Google account must be a Site Owner or Site Full User. Sites Metadata then lists each Site URL with its Permission Level.