Data to AI™ / Copilot/Microsoft Ads
Give the search and demand generation team an agent in Teams that answers questions from Microsoft Advertising reports, so audience and campaign figures are one @ mention away.
Better answers, fewer tokens.
Microsoft 365 Copilot
Which campaigns lost the most impressions to budget last month, and were they profitable?
Brand Search lost 38% of eligible impressions to budget while returning 6.2 per unit of spend, so it is the clearest case for more budget. Generic Search lost less and returned far less.
| Campaign Name | Spend | Impression Lost To Budget Percent | Return On Ad Spend |
|---|---|---|---|
| Brand Search Campaign Performance Report | $4,100 | 38% | 6.2 |
| Generic Search Campaign Performance Report | $9,800 | 21% | 1.9 |
| Performance Max Campaign Performance Report | $6,300 | 12% | 3.4 |
All three columns come from one Campaign Performance Report with Monthly time aggregation, so the shares are not averaged from daily rows.
Microsoft Advertising (formerly Bing Ads) runs paid search campaigns across Bing and Microsoft's partner network. Dataddo extracts its reports, from account and campaign down to keyword, search term and ad, with the attributes and metrics you pick for each report type.
@Search Team Which Industry Name and Job Function Name segments drove the most Conversions last month in the Professional Demographics Audience Report, and what did each spend?
Demand generation managers mention the agent in the channel instead of opening reports, and agree on audience bid adjustments in the same thread where the question was asked.
@Search Team Give me Spend, Conversions and Return On Ad Spend by Campaign Name for last month from the Campaign Performance Report, as a table I can paste into PowerPoint.
In Microsoft 365 Copilot, the agent returns the campaign table while you prepare the leadership review, so the slide shows the same numbers the team discussed in Teams.
Use the dataddo tools to describe the Keyword Performance Report and map Keyword, Clicks, Average Cpc and Quality Score into our metrics config.
In VS Code, GitHub Copilot in Agent mode reads real field names and sample rows, so marketing engineers wire Microsoft Ads data into internal tools without asking for a fresh export.
Data to AI™ is priced per seat, like the AI assistants your team already uses, with ~25% off on annual billing. Need tailored contracts or volume pricing? Talk to us about Enterprise.
Serve governed business data to Claude, ChatGPT and other AI tools over MCP.
$10.49/month
per seat
3 seats minimum
Flexibly deploy Dataddo in any cloud or hybrid environment.
Custom
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Answers where the team talks | A specialist exports Microsoft Advertising reports and posts them in Teams, and every follow-up waits for the next export. | The Copilot Studio agent answers campaign and audience questions in Teams from the scheduled Microsoft Ads flow. | No waiting for the weekly report |
| When the agent calls Dataddo | A general assistant cannot tell which questions need search ad data, so people paste figures into prompts by hand. | The server description in Copilot Studio tells the agent to call Dataddo for Microsoft Ads spend, conversions and audience questions. | Ad questions routed to ad data |
| Several advertiser accounts | Each advertiser account is exported on its own and merged before anyone can compare them. | One Microsoft Ads source can include several advertiser accounts, optionally narrowed to one campaign or ad group, before the agent queries it. | One agent across accounts |
| Token consumption | Copilot spends tokens exploring raw Microsoft Ads 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. | Fewer 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 Microsoft Ads datasets marketing teams use most, with their real field names. Copilot queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Copilot
|
|---|---|---|
| Campaign Performance Report |
|
How do Conversions and Spend compare by Campaign Type, including Performance Max? |
| Keyword Performance Report |
|
Which Keyword had the steepest rise in Average Cpc over the last four weeks? |
| Search Query Performance Report |
|
Which Keyword triggers the widest range of Search Query terms, and how much Spend do they take? |
| Ad Performance Report |
|
Which Ad Description texts mention a price or discount, and how do they perform? |
| Budget Summary Report |
|
How did Month To Date Spend compare with Monthly Budget for each campaign last month? |
| Professional Demographics Audience Report |
|
Which companies by Company Name clicked our ads most often last quarter? |
| Geographic Performance Report |
|
How is Spend split by State across our US campaigns? |
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 Microsoft Ads source in Dataddo with report types such as Campaign Performance Report and attach it to a Copilot destination or AI Model. In Copilot Studio, add https://headless.dataddo.com/mcp-data as a Model Context Protocol tool with OAuth 2.0 and Dynamic discovery, then publish the agent to Teams and Microsoft 365 Copilot.
Yes. Dataddo connects as an MCP tool on a Copilot Studio agent. After you publish the agent to Microsoft 365 Copilot and Teams, people reach the Microsoft Ads data by typing @ and selecting that agent.
Not through this setup. Here Dataddo extracts the Microsoft Advertising reports you choose and serves them to the Copilot Studio agent over MCP. Both products being from Microsoft does not change that step.
Write a clear server description in Copilot Studio. It tells the agent when to call Dataddo, for example only for Microsoft Ads spend, conversion and audience questions.
The agent reaches every flow or Context attached to an AI destination or AI Model in the signed-in Dataddo account. Build sources with only the advertiser accounts a team should query and attach just those.
Yes. Add the Dataddo server to .vscode/mcp.json, start it, sign in and use Copilot Chat in Agent mode. On GitHub Copilot Business and Enterprise an admin enables MCP servers in Copilot policy first.
No. The agent reads Microsoft Ads data that Dataddo extracted, through the semantic layer, and nothing is written back. Campaign, bid and budget changes stay in Microsoft Advertising.
