Data to AI™ / ChatGPT/X Ads
Check budget delivery, blocked promoted posts and video completion on X in a ChatGPT conversation that reads scheduled ad data, with each lookup confirmed by you.
Better answers, fewer tokens.
ChatGPT
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.
Run data_status on the X Ads flow. Then compare yesterday's Spend per Campaign Name in Campaign Analytics with Daily Budget Amount Local Micro divided by 1,000,000 from Campaigns.
You approve each tool call, see that yesterday is loaded, and find campaigns that under-deliver against their budget, often a sign of narrow targeting or low bids to raise with the media buyer.
List Promoted Tweets whose Approval Status shows they are not approved, with Entity Status and Spend for the last 7 days.
ChatGPT surfaces posts held back by review, so the team fixes the creative the same day instead of wondering why a launch campaign spent nothing.
For promoted video posts, compare Video Views 25, Video Views 50, Video Views 75 and Video Views 100 and show where most viewers leave.
The answer shows whether people quit in the first seconds or near the end, and ChatGPT drafts edit notes for the video team in the same thread.
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 | |
|---|---|---|---|
| Budget delivery check | Someone downloads campaign budgets and spend from X Ads Manager, uploads both files, and converts micros before ChatGPT can compare them. | ChatGPT reads Campaigns and Campaign Analytics from the scheduled flow, and data_status tells you when the last run finished. | Pacing on current numbers |
| Review of each lookup | An uploaded export hands every column and post to the chat at once, including data the question never needed. | Developer mode asks you to confirm every tool call, and you can switch off Dataddo tools you do not want ChatGPT to use. | You approve each query |
| Gaps in short history | A chat answer about last month may quietly rely on a week of data, because X only allows extraction up to 7 days back. | known_gaps flags what the X Ads data does not cover, so ChatGPT tells you when a period is missing before you act on it. | Missing periods made visible |
| Token consumption | ChatGPT 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. ChatGPT queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask ChatGPT
|
|---|---|---|
| Campaign Analytics |
|
How did Impressions and Clicks change day by day for our X Ads campaigns this week? |
| Promoted Tweets |
|
Which promoted posts are not approved yet, according to Approval Status? |
| Promoted Tweets Metadata |
|
How many promoted posts do we run in each Tweet language? |
| Campaigns |
|
What is the Daily Budget Amount Local Micro of each active campaign, converted to whole currency units? |
| Organic Tweets |
|
What topics in the Full Text of our organic posts get the most Retweets? |
| Account Analytics |
|
On which Date Start did the account gain the most Follows? |
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 →Extract Campaigns, Campaign Analytics and Promoted Tweets from X Ads in Dataddo and attach them to a ChatGPT destination or AI Model. In ChatGPT, switch on developer mode, create a Dataddo Data Access app with https://headless.dataddo.com/mcp-data and OAuth, sign in, then pick it from the + menu.
Pro, Plus, Business, Enterprise and Education, since the app runs in developer mode on ChatGPT web. On Business and Enterprise a workspace admin may need to allow developer mode first.
Developer mode confirms each tool call before it runs. You see each query against your ad data, and in the app settings you can turn individual Dataddo tools on or off.
Daily Budget Amount Local Micro is stored in micros. Ask ChatGPT to divide it by 1,000,000. The Spend field in Campaign Analytics and Promoted Tweets is already converted to the account currency.
No. An upload is a one-off file. Dataddo refreshes the X Ads source on its schedule, and ChatGPT queries current data by field name through the semantic layer.
Try a smaller date range and check that the X account used for the authorizer has at least admin-level permissions on the ads account.
Yes, if you extract Promoted Tweets Metadata. It holds Full text, Tweet language and Tweet type, and links to Promoted Tweets through the Tweet ID.
