Data to AI™ / Copilot/Apple Search Ads
Publish a Copilot Studio agent to Teams that answers questions about Apple Search Ads spend, campaign serving and budgets, so marketing and finance stop waiting for the next export.
Better answers, fewer tokens.
Microsoft 365 Copilot
Which countries brought installs at the lowest cost last month?
Canada had the lowest cost per install at $1.84, on a third of the UK's spend. The United States took the most budget at $2.61 per install.
| Country Or Region | Local Spend Amount | Total Installs | Total Avg CPI Amount |
|---|---|---|---|
| CA Report Campaigns | $3,120 | 1,696 | $1.84 |
| GB Report Campaigns | $9,480 | 4,190 | $2.26 |
| US Report Campaigns | $21,700 | 8,314 | $2.61 |
Figures come from Report Campaigns with Group By set to Country Or Region and a monthly breakdown, requested from Apple in UTC.
Apple Search Ads promotes iOS apps in App Store search results. Dataddo extracts three datasets: Campaigns with budgets and serving status, Report Campaigns with spend, taps, installs and cost per install by day, country or device, and Targeting Keywords Find with the bids and match types of one campaign.
@App Ads Desk Which campaigns have Status enabled but a Serving Status other than running? Show Name and Serving State Reasons.
Every morning someone on the app marketing team asks the agent in Teams. A campaign that stopped serving overnight is caught before it costs a day of installs.
@App Ads Desk Total Local Spend Amount by Campaign Name for last month from Report Campaigns, with Local Spend Currency.
The finance controller asks Microsoft 365 Copilot during the close and matches the totals against the Apple invoice, without asking marketing for a spreadsheet.
Use the dataddo tools to read Campaigns and generate a JSON file mapping each Id to Name, Daily Budget Amount and Start Time for our internal dashboard.
A developer uses GitHub Copilot in Agent mode in VS Code to keep the dashboard's campaign lookup file in line with what is live in Apple Search Ads.
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 | |
|---|---|---|---|
| Morning campaign check | A marketer logs in to the Apple Search Ads dashboard and opens campaigns one by one to see whether they are still serving. | The Teams agent reads Serving Status and Serving State Reasons from Campaigns and lists the campaigns that need attention. | Stopped campaigns caught daily |
| Spend for the close | Finance emails marketing for last month's ad spend and waits for an export that arrives after the books should be closed. | The controller asks Microsoft 365 Copilot for Local Spend Amount per campaign and month straight from Report Campaigns. | Spend ready at month end |
| Who decides when to query | A general chat assistant has no idea where ad data lives and answers from guesses or old uploads. | The server description in Copilot Studio says Dataddo holds Apple Search Ads campaigns and reports, so spend and install questions trigger a lookup. | Questions routed to real data |
| Token consumption | Copilot spends tokens exploring raw Apple Search 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 Apple Search 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
|
|---|---|---|
| Report Campaigns |
|
Which Campaign Name spent the most Local Spend Amount last week, and how many Total Installs did it bring? |
| Campaigns |
|
Which campaigns have a Status of paused while their Budget Amount is still unspent? |
| Targeting Keywords Find |
|
Which keyword bids were changed recently, based on Modification Time? |
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 an Apple Search Ads source in Dataddo with Campaigns and Report Campaigns and attach it to a Copilot destination or AI Model. In Copilot Studio, add a Model Context Protocol tool for https://headless.dataddo.com/mcp-data with OAuth 2.0 Dynamic discovery, then publish the agent to Teams and Microsoft 365 Copilot.
Through a Copilot Studio agent. Add Dataddo Data Access as a Model Context Protocol tool with OAuth 2.0 Dynamic discovery, sign in, and publish the agent to Teams and Microsoft Copilot. People then type @ and pick the agent.
Name the data it holds, for example Apple Search Ads campaigns, budgets, serving status, spend, taps, installs and keyword bids. The agent uses that description to decide when a question needs a Dataddo lookup.
Report Campaigns carries Local Spend Amount together with Local Spend Currency, and Campaigns carries Budget Amount Currency. Ask the agent to show the currency column so totals from different accounts are not mixed.
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 organization admin must enable MCP servers in Copilot policy first.
Only for campaigns you extract. Targeting Keywords Find is set up for one Campaign Id per source, so create one source per campaign you want the agent to cover, or ask about each campaign separately.
Only if you extract them. Campaigns includes Client Name, Buyer Name, Buyer Email and Buyer Contact Email; untick them in the attribute list when you create the source and the agent never sees them.
