Data to AI™ / Copilot/X Ads
Give the social media team an agent in Teams that answers X Ads spend, follower growth and campaign end date questions, so nobody logs in to Ads Manager for a quick number.
Better answers, fewer tokens.
Microsoft 365 Copilot
Which X Ads campaigns got the cheapest link clicks last week?
Spring Webinar Promo had the cheapest link clicks at $0.41 each, on less than a quarter of the spend. Brand Awareness Q2 took the most budget but cost $1.12 per URL click.
| Campaign Name | Spend | URL Clicks | Impressions |
|---|---|---|---|
| Spring Webinar Promo Campaign Analytics | $1,230 | 3,000 | 184,500 |
| Product Launch Retarget Campaign Analytics | $2,050 | 3,420 | 142,800 |
| Brand Awareness Q2 Campaign Analytics | $4,480 | 4,000 | 611,200 |
Spend is Billed Charge Local Micro divided by 1,000,000, in the ad account's currency, for placements on X itself.
X Ads (formerly Twitter Ads) extracts paid and organic performance from an X ads account: campaign spend and engagement, promoted post results with web conversions and video completion, post text, and campaign budgets and status.
@Social Ads What did each Campaign Name spend yesterday in Campaign Analytics, and how many URL Clicks and Follows did it bring?
The social team asks the agent in its Teams channel each morning and discusses outliers in the thread, instead of one person checking X Ads Manager and posting a screenshot.
@Social Ads Give me a table of Impressions, Engagements, Follows and Replies from Account Analytics for each day we have this month.
In Microsoft 365 Copilot, the agent returns a table while you write the monthly social report in PowerPoint, using the same numbers the team saw in Teams.
Use the dataddo tools to describe Campaigns and generate a JSON calendar of Name, Start Time, End Time and Entity Status for our internal planning tool.
A marketing engineer uses GitHub Copilot in Agent mode in VS Code, so the planning tool shows real X Ads campaign dates without a manual 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 | |
|---|---|---|---|
| Quick numbers in Teams | One person has access to X Ads Manager, so every spend question in the channel waits until they log in and paste a number. | The Copilot Studio agent answers spend and engagement questions in Teams from the scheduled X Ads flow. | No waiting for one login |
| When the agent calls Dataddo | A general assistant cannot tell which questions need X ad data, so people type figures into prompts by hand. | The server description you enter in Copilot Studio tells the agent to call Dataddo for X Ads spend, follower and campaign questions. | Ad questions routed to ad data |
| Campaigns ending soon | Campaign end dates are checked one by one in the X Ads interface, and a campaign that ends before a launch is noticed late. | Campaigns carries Start Time, End Time and Entity Status, so the agent lists campaigns ending in the next weeks on request. | Renewals decided on time |
| Several ad accounts | Each ads account is exported separately and merged in a spreadsheet before anyone can answer a cross-account question. | Each X Ads source reads one Ads Account; attach the flows for every account to the AI destination and the agent can query all of them. | One agent across accounts |
| Token consumption | Copilot spends tokens exploring raw X 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 X 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 Analytics |
|
Which campaigns brought the most Follows for the Spend yesterday? |
| Promoted Tweets |
|
Which promoted video posts keep viewers to the end, based on Video Views 100? |
| Promoted Tweets Metadata |
|
Which promoted posts were Created at more than 60 days ago and are still in use? |
| Campaigns |
|
Which campaigns have an End Time in the next 14 days? |
| Organic Tweets |
|
Which organic posts with video had the highest Video Total Views? |
| Account Analytics |
|
How many Replies and Retweets did the account collect in total yesterday? |
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 →Set up an X Ads source in Dataddo with Campaign Analytics and Account Analytics and attach it to a Copilot destination or AI Model. In Copilot Studio, add https://headless.dataddo.com/mcp-data under Tools as a Model Context Protocol tool with OAuth 2.0 Dynamic discovery, then publish the agent to Teams and Microsoft 365 Copilot.
Yes. Dataddo connects as a Model Context Protocol tool on a Copilot Studio agent. Once the agent is published to Microsoft 365 Copilot and Teams, people reach the data by typing @ and selecting it.
Write a clear server description in Copilot Studio. Say it holds X Ads (formerly Twitter Ads) campaign, spend and engagement data, so only those questions trigger a lookup.
Yes. Each source selects one Ads Account. Create a source per account and attach their flows to the Copilot destination; the Ads Accounts dataset lists the accounts with names and status.
Yes. Add the Dataddo server to .vscode/mcp.json, start it, sign in and use Copilot Chat in Agent mode. On Business and Enterprise an admin first enables MCP servers in the Copilot policy.
The X API allows extraction only up to 7 days back, so older periods cannot be loaded into a new source. The agent can answer for the periods your flow has extracted since you set it up.
No. The agent reads X Ads data that Dataddo extracted and answers questions about it. Status and budget changes still happen in X Ads Manager.
