Data to AI™ / Copilot/Google Ad Manager

Google Ad Manager in Microsoft Copilot and Teams

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.

Better answers, fewer tokens.

  • Lower AI costs for the same work
  • More accurate, reliable answers
  • Read-only
  • Uses the Google Ad Manager data you already sync
  • SOC 2 Type II certified
Microsoft 365 Copilot
Connected to Dataddo

Which ad units earned the most last week, and where did inventory go unfilled?

Copilot Answer · Google Ad Manager

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 NameTotal ImpressionsTotal Line Item Level All RevenueTotal Inventory Level Unfilled Impressions
video_preroll Google Ad Manager 380,0006,84021,000
article_sidebar Google Ad Manager 2,310,0005,544412,000
homepage_leaderboard Google Ad Manager 1,240,0004,96086,000

Last week is re-read on every scheduled run, so its rows are replaced, not added twice.

source
Google Ad Manager · as of Mon 06:40 UTC
covers
21-27 Sep 2026
Example answer · fictional account and figures
Google Ad Manager in Copilot

Questions Copilot can answer from your Google Ad Manager data

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.

Order status in the ad ops channel

Ask Copilot

@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.

Advertiser recap before a renewal

Ask Copilot

@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.

Tag check after a release

Ask Copilot

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.

Google Ad Manager datasets and the questions they answer in Copilot →
Pricing

Priced per seat.

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.

Data to AITM

Serve governed business data to Claude, ChatGPT and other AI tools over MCP.

$10.49/month

per seat

3 seats minimum

Enterprise

Flexibly deploy Dataddo in any cloud or hybrid environment.

Custom

We have a payment model that works for you

See all plans and features →
Setup

Connect Google Ad Manager to Copilot step by step

  1. 1
    Connect Copilot to Dataddo Add Dataddo as an MCP tool to a Copilot Studio agent and sign in, or add it to mcp.json for GitHub Copilot in VS Code.
  2. 2
    Connect Google Ad Manager to Dataddo Sign in with your Google Ad Manager account in Dataddo and choose the datasets to sync, such as Delivery and Revenue.
  3. 3
    Choose what Copilot can see Select the Google Ad Manager data Copilot may query. Access is read-only, and data you don't select stays out of reach.
Copilot setup guide →
With vs. without

Google Ad Manager in Copilot, with and without Dataddo

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. Fewer tokens per answer
Answer quality Prone to wrong joins, invented fields and numbers that are hard to check. Answers built on agreed definitions. In the Dataddo benchmark, Opus 5.5 reached 95.2% good outcomes, against 81% over raw SQL. Better answers
Datasets

Google Ad Manager datasets and the questions they answer in Copilot

The Google Ad Manager 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
Delivery
  • Total Impressions
  • Total Line Item Level Impressions
  • Total Clicks
  • Total CTR
  • + others
How big is the gap between Total Impressions and Total Line Item Level Impressions?
Revenue
  • Ad Server CPM and CPC Revenue
  • Total Line Item Level All Revenue
  • Ad Exchange Estimated Revenue
  • Ad Exchange Ad eCPM
  • + others
On which days did Ad Server CPM and CPC Revenue fall well below normal?
Inventory and fill
  • Total Code Served Count
  • Total Inventory Level Unfilled Impressions
  • Ad Exchange Coverage
  • + others
What share of Total Code Served Count ended up as unfilled impressions?
Viewability
  • Total Active View Average Viewable Time
  • Total Active View Viewable Impressions Rate
  • Video Viewership Completion Rate
  • + others
Is Total Active View Average Viewable Time getting longer or shorter week over week?
Orders and line items
  • Advertiser Name
  • Order Name
  • Line Item Name
  • Line Item Type
  • Order Delivery Status
  • + others
Which Advertiser Name has the most orders running in Google Ad Manager?
Inventory dimensions
  • Country Name
  • Ad Unit Name
  • Placement Name
  • Demand Channel Name
  • + others
In which Country Name markets does each placement serve ads?
Line item attributes
  • Line Item Start Date Time
  • Line Item End Date Time
  • Line Item Cost Type
  • + others
Which line items start next month based on Line Item Start Date Time?
See all Google Ad Manager datasets, metrics and attributes on the connector page →
Benchmark

Fewer confident mistakes. No leaked personal data.

We asked three Claude models the same 21 business questions about a NetSuite company built from real-world data: once over a raw SQL connection, once as CSV exports and once through Data to AI™. Only the connection changed, and the answer key was fixed before the first run.

95.2%

good outcomes with Opus 5.5 on Data to AI™, against 81% on a raw SQL connection

58%

fewer confidently wrong answers with Sonnet 5 - 8 of 63 runs, against 19 on raw SQL

24x

cheaper per question: Haiku 5.5 on Data to AI™ (87.3%) beat Opus 5.5 on raw SQL (81%)

0 of 9

attempts disclosed a sales rep's email address, against 9 of 9 on raw SQL

Good outcomes Correct answer or correct decline, 63 runs per setup - higher is better
Wrong, but stated as fact Confidently wrong answers out of 63 runs - lower is better

21 questions, 3 runs each. 17 carry a real-world caveat (transaction types, voided invoices, foreign currencies, group companies billed as customers, a partial year) and 3 can't be answered from the data. Ground truth computed directly in SQL; CSV exports were run with Sonnet 5 only. Run date: 26 October 2026.

Read the benchmark →
FAQ

Google Ad Manager and Copilot: FAQ

How do I connect Google Ad Manager to Copilot?

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.

Can Microsoft 365 Copilot answer Google Ad Manager questions?

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.

How do I add the Ad Manager agent to a Teams channel?

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.

How does the agent decide when to query Ad Manager?

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.

Can GitHub Copilot read Ad Manager data?

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.

Why is a new Ad Manager agent missing older data?

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.

New from Dataddo · Data to AI™

Ask Claude or ChatGPT about your ads, analytics and CRM

“What did a new lead cost us last week, by paid channel?”

Connect 400+ sources once and get the answer right in your AI chat, without building a report. Better answers: your metrics are defined once, so the AI doesn't have to guess.