Data to AI™ / Copilot/DV360
Give trading desks and account teams a Copilot agent in Teams that answers on DV360 invalid traffic, viewability and spend by exchange from scheduled report data.
Less tokens, better answers.
Microsoft 365 Copilot
Which insertion orders showed ads to the same people too often this month?
Retargeting Display reached 96,500 people at 11.2 impressions each, more than three times the 3.4 of Brand Awareness CTV. Prospecting Video sat in between at 7.8.
| Insertion Order | Unique Reach: Total Reach | Unique Reach: Average Impression Frequency |
|---|---|---|
| Retargeting Display DV360 Reach/Frequency by Insertion Order | 96,500 | 11.2 |
| Prospecting Video DV360 Reach/Frequency by Insertion Order | 412,000 | 7.8 |
| Brand Awareness CTV DV360 Reach/Frequency by Insertion Order | 1,180,000 | 3.4 |
Reach is shown per insertion order and not added up, because DV360 reach is estimated.
Dataddo extracts Google Display & Video 360 (DV360) reporting through a flexible report dataset with report types such as Standard and YouTube, plus a reach and frequency dataset and an advertiser list.
@Trading Desk Which Exchange had the most Invalid Impressions yesterday, and how does its % Invalid Impressions (Pre-bid) compare with last week?
The trading desk asks the agent each morning in its Teams channel, so suspicious supply is raised and discussed in the thread where buying decisions happen.
@Client Media Summarize Active View: % Viewable Impressions and Total Media Cost (Advertiser Currency) by Line Item for this client's campaign last month.
An account manager mentions the agent in Microsoft 365 Copilot while drafting a quarterly review and pastes the figures straight into the client deck.
Use the dataddo tools to list DV360 Advertisers with Advertiser ID, Partner ID and Time Zone, and update config/advertisers.json.
A data engineer in GitHub Copilot Agent mode refreshes the advertiser mapping file in the repository, so new advertisers appear in internal reports.
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 gets the answer | Traders and account managers ask the one person with DV360 reporting access and wait for an offline report to come back. | A Copilot Studio agent published to Teams and Microsoft 365 Copilot answers from the DV360 flow for anyone who mentions it. | Answers where the desk works |
| Telling the agent what DV360 covers | A general assistant cannot know that exchange, viewability and spend questions belong to your programmatic reporting. | The server description you enter in Copilot Studio tells the agent when to call Dataddo, for example for programmatic spend, exchanges and viewability. | Lookups triggered reliably |
| Several DV360 accounts | Each account is reported on separately and the team merges files by hand before every review. | Multi-account extraction, enabled by the Dataddo Solutions team, pulls the same fields from every account into the flow the agent reads. | All accounts in one agent |
| Token consumption | Copilot spends tokens exploring raw DV360 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 DV360 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 your schedule with a relative date range such as yesterday or last 30 days. Reach comes in blocks of up to 93 days that cannot be summed, and DV360 Advertisers reloads the full list every run.
DV360 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 Display & Video 360 source in Dataddo with Exchange, Line Item, Invalid Impressions and Active View: % Viewable Impressions, attach it to a Copilot destination or AI Model, then add https://headless.dataddo.com/mcp-data as a Model Context Protocol tool in a Copilot Studio agent with OAuth and publish it to Teams.
Build a Copilot Studio agent, add Dataddo Data Access as a Model Context Protocol tool with OAuth, publish it, then add Teams under Channels > Teams and Microsoft Copilot.
The server description you enter in Copilot Studio tells the agent when to call Dataddo. Mention programmatic spend, exchanges and viewability so those questions trigger a lookup.
Yes. Add the server to .vscode/mcp.json with type http and the Dataddo URL, start it, sign in and use Agent mode. On Business and Enterprise an org admin must enable the MCP servers in Copilot policy.
It should not. DV360 reach is estimated and cannot be summed across insertion orders, so ask the agent for reach per insertion order from the reach dataset instead.
Yes. Multi-account extraction, set up by the Dataddo Solutions team, pulls the same data from several accounts. Attach that flow to the agent's Copilot destination or AI Model.