Data to AI™ / Copilot/Amazon Ads

Amazon Ads in Microsoft Copilot and Teams

Give the retail media team an agent in Teams that answers questions on Amazon campaign returns, brand searches and DSP delivery from scheduled report data.

Better answers, fewer tokens.

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

Which Sponsored Products campaigns had the highest ACOS on 14-day sales last month?

Copilot Answer · Amazon Ads

Generic - Kitchen ran the highest ACOS at 42.0%, more than four times Brand - Exact at 10.0%. Competitor ASINs came second at 33.0%.

Campaign NameSpendSales 14dAcos Clicks 14d
Generic - Kitchen Sponsored Products: Campaign 4,1209,81042.0%
Competitor ASINs Sponsored Products: Campaign 2,4607,45033.0%
Brand - Exact Sponsored Products: Campaign 1,35013,50010.0%

Spend and Sales 14d use the same 14-day attribution window; Sales 7d is never mixed in.

source
Amazon Ads · as of Mon 06:40 UTC
covers
1-30 Sep 2026
Example answer · fictional account and figures
Amazon Ads in Copilot

Questions Copilot can answer from your Amazon Ads data

Amazon Ads reports cover Sponsored Products, Sponsored Brands, Sponsored Display and Amazon DSP. Each source reads one report type for the profile you pick, daily or as a summary for the date range.

ROAS check at stand-up

Ask Copilot

@Retail Media Desk Which Sponsored Products campaigns had Roas Clicks 14d below 2 last week, and how much Spend did they use?

Account managers mention the agent in the retail media channel during stand-up instead of waiting for the weekly deck, and agree on budget moves in the same thread.

Brand searches after DSP spend

Ask Copilot

@Retail Media Desk Line up weekly DSP Total Cost with Sponsored Brands Branded Searches for the last eight weeks.

In Microsoft 365 Copilot the brand team checks whether awareness spend on DSP orders is followed by more shoppers searching for the brand on Amazon.

Report fields typed in VS Code

Ask Copilot

Use the dataddo tools to describe the Sponsored Products Advertised Product entity and generate a TypeScript type for our dashboard loader.

A developer uses GitHub Copilot in Agent mode to read the field list through Dataddo, so the internal retail media dashboard matches the real Advertised Asin and Spend columns.

Amazon Ads 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 Amazon Ads 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 Amazon Ads to Dataddo Sign in with your Amazon Ads account in Dataddo and choose the datasets to sync, such as Sponsored Products: Campaign and Sponsored Products: Search Term.
  3. 3
    Choose what Copilot can see Select the Amazon Ads data Copilot may query. Access is read-only, and data you don't select stays out of reach.
Copilot setup guide →
With vs. without

Amazon Ads in Copilot, with and without Dataddo

Without Dataddo With Dataddo Outcome for you
Numbers at stand-up Each account manager brings a different Amazon export to the meeting, so discussions in Teams start by reconciling numbers. The same Copilot Studio agent answers everyone in Teams and Microsoft 365 Copilot from the same Amazon Ads flows. One set of figures
When the agent looks things up A generic assistant has no idea that Amazon campaign data exists anywhere it can reach, so it answers from general knowledge. The server description you write in Copilot Studio tells the agent to call Dataddo for Amazon Ads campaign, search term and DSP questions. Right tool for the question
Developer access Engineers request Amazon reports through the API and work out column names by trial before building a dashboard. GitHub Copilot in VS Code reads the same entities through .vscode/mcp.json, so field names come from Dataddo instead of guesswork. Dashboards match the source
Token consumption Copilot spends tokens exploring raw Amazon 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 built on agreed definitions. In the Dataddo benchmark, Opus 5.5 reached 95.2% good outcomes, against 81% over raw SQL. Better answers
Datasets

Amazon Ads datasets and the questions they answer in Copilot

The Amazon 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
Sponsored Products: Campaign
  • Roas Clicks 14d
  • Top Of Search Impression Share
  • Campaign Name
  • Campaign Budget Amount
  • Spend
  • + others
Which campaigns have a low Top Of Search Impression Share but strong Roas Clicks 14d?
Sponsored Products: Search Term
  • Search Term
  • Keyword
  • Match Type
  • Cost
  • Sales 7d
  • + others
Which converting search terms are not yet added as a Keyword in our campaigns?
Sponsored Products: Advertised Product
  • Advertised Sku
  • Spend
  • Advertised Asin
  • Units Sold Clicks 14d
  • Sales 14d
  • + others
How is Spend distributed across each Advertised Sku, and which products take most of it?
Sponsored Products: Campaign Placement
  • Placement Classification
  • Campaign Name
  • Top Of Search Impression Share
  • + others
Which campaigns show up in the top of search Placement Classification versus product pages?
Sponsored Brands: Campaign
  • Detail Page Views
  • Campaign Name
  • Cost
  • Sales
  • New To Brand Sales
  • + others
Did Detail Page Views from Sponsored Brands rise or fall over the last eight weeks?
Sponsored Display: Campaign
  • Viewability Rate
  • Campaign Name
  • Cost
  • Purchases
  • Add To Cart
  • + others
Which Sponsored Display campaigns have a Viewability Rate below our account average?
DSP: Campaign
  • Order Name
  • Purchases
  • New to Brand Purchases
  • Total Cost
  • Impressions
  • + others
What share of DSP Purchases were New to Brand Purchases for each Order Name?
See all Amazon Ads 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

Amazon Ads and Copilot: FAQ

How do I connect Amazon Ads to Copilot?

Send Amazon Ads reports such as Sponsored Products Campaign and Sponsored Brands Campaign to a Copilot destination or AI Model in Dataddo. In Copilot Studio, add a Model Context Protocol tool with https://headless.dataddo.com/mcp-data, use OAuth 2.0 with Dynamic discovery, then publish the agent to Teams and Microsoft 365 Copilot.

Does the Amazon Ads agent work in Teams and Microsoft 365 Copilot?

Yes. Publish the Copilot Studio agent through Channels > Teams and Microsoft Copilot. People mention it with @ and it queries the Amazon Ads flows attached to your Copilot destination.

How does the agent know when to look up Amazon Ads data?

From the server description you enter in Copilot Studio. Describe it as the source for Amazon Ads campaign, search term and DSP results, so those questions trigger a Dataddo call.

Can GitHub Copilot read the same Amazon Ads data?

Yes. Add the server to .vscode/mcp.json, start it, sign in and use Copilot Chat in Agent mode. On Business and Enterprise an org admin must enable the MCP servers in Copilot policy.

Why are the newest Amazon Ads numbers missing from the agent's answer?

Amazon builds reports asynchronously and busy API traffic slows them down. The agent can call data_status to report when each Amazon Ads flow last received data.

Can the Copilot agent edit Amazon Ads campaigns?

No. It reads extracted report data by entity and field. Budget, bid and targeting changes stay in the Amazon Ads console.

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.