Data to AI™ / Copilot/Google Ad Manager
Give ad ops and sales a Copilot agent that answers questions on order status, advertiser delivery and ad tags from Google Ad Manager, right where they already chat.
Less tokens, better answers.
Microsoft 365 Copilot
Which ad units earned the most last week, and where did inventory go unfilled?
video_preroll earned the most, 6,840 from 380,000 impressions, an eCPM of 18.00. article_sidebar served the most impressions but left 412,000 unfilled.
| Ad Unit Name | Total Impressions | Total Line Item Level All Revenue | Total Inventory Level Unfilled Impressions |
|---|---|---|---|
| video_preroll Google Ad Manager | 380,000 | 6,840 | 21,000 |
| article_sidebar Google Ad Manager | 2,310,000 | 5,544 | 412,000 |
| homepage_leaderboard Google Ad Manager | 1,240,000 | 4,960 | 86,000 |
Last week is re-read on every scheduled run, so its rows are replaced, not added twice.
Google Ad Manager is Google's ad serving platform for publishers and advertisers. Dataddo extracts one flexible report dataset per network: choose from 101 standard metrics, 100 dimensions and line item attributes.
@Ad Ops List the Order Delivery Status of every order that started this week, grouped by Advertiser Name, with Total Impressions so far.
Trafficking and account staff ask the agent in Teams instead of opening Ad Manager or waiting for the morning report, and discuss stuck orders in the same thread.
@Ad Sales Summarize Total Impressions, Total Clicks and Total CTR for this Advertiser Name over the last quarter for my renewal call.
An account manager mentions the agent in Microsoft 365 Copilot and pastes the quarter's delivery into the meeting notes before talking to the client.
Use the dataddo tools to compare Total Code Served Count with Total Impressions per Ad Unit Name since yesterday's tag release.
A front-end developer in GitHub Copilot Agent mode spots ad units where code was served but impressions fell, a sign that ads stopped rendering.
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 | |
|---|---|---|---|
| Who can check an order | Only people with Ad Manager access can look up delivery, so sales and account teams wait for ad ops to send a status. | A Copilot Studio agent published to Teams answers from the Ad Manager flow for anyone in the channel who mentions it with @. | Status without a ticket |
| When the agent calls Dataddo | A general assistant has no idea that order and delivery questions should be answered from your network's reporting. | The server description you write in Copilot Studio tells the agent to call Dataddo for Ad Manager orders, line items and revenue. | Right questions, right data |
| Line item dates next to delivery | Checking whether a line item will finish in time means lining up start and end dates from one export with delivery from another. | Line item attributes such as Line Item Start Date Time and Line Item End Date Time sit in the same dataset as delivery metrics. | Pacing in one answer |
| Developers checking tags | After a tag release, developers wait for someone in ad ops to pull a report on served code and impressions. | GitHub Copilot in VS Code reads the same Ad Manager data through .vscode/mcp.json in Agent mode, with no separate export for the dev team. | Tag checks from the editor |
| Token consumption | Copilot spends tokens exploring raw Google Ad Manager 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 Ad Manager datasets marketing teams use most, with their real field names. Copilot queries them by name through the Dataddo semantic layer.
Runs on the schedule you set with a relative date range, for example yesterday, that moves forward on every run. Older reporting is loaded once with a full data re-sync.
Google Ad Manager 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 →Configure a Google Ad Manager source in Dataddo with fields such as Order Name, Order Delivery Status, Advertiser Name and Total Impressions, attach it to a Copilot destination or AI Model, then add https://headless.dataddo.com/mcp-data as an MCP tool in a Copilot Studio agent with OAuth and publish it to Teams.
Yes, through a Copilot Studio agent with Dataddo Data Access added as a Model Context Protocol tool. Publish the agent, then type @ and select it to ask about your Ad Manager data.
After publishing in Copilot Studio, go to Channels > Teams and Microsoft Copilot and add the channel. Ad ops can then mention the agent in Teams.
The server description you write in Copilot Studio tells the agent when to call Dataddo, so describe it as the source for Ad Manager delivery, orders and revenue.
Yes. Add the server to .vscode/mcp.json, start it and sign in, then use Copilot Chat in Agent mode. On Business and Enterprise an admin must enable the MCP servers in Copilot policy.
Data appears after the flow runs once, and a new source starts from its relative date range. Load older reporting with a full data re-sync.