Data to AI™ / Gemini/X Ads
Pull X Ads data into scripts, notebooks and pull requests from the terminal, so naming mistakes and broken conversion tracking show up before a release, not in next month's report.
Better answers, fewer tokens.
Gemini CLI
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.
Using the dataddo server, list each Tweet Id in Promoted Tweets for the last 7 days with Clicks above 0 but Conversion Site Visits Order Quantity at 0.
A developer who changed the landing page template runs this the next day. An empty list means site visits are still attributed; any rows go straight into the bug ticket.
Read Name from Campaigns and check each one against the pattern in config/naming.yml. Write the names that do not match to reports/x-ads-naming.md.
A marketing ops engineer runs the check in Gemini Code Assist before merging a reporting change, so campaigns with broken names do not fall out of the dashboards.
Query Promoted Tweets for the last 7 days and save Tweet Id, Spend, Conversion Sign Ups Order Quantity and Conversion Sign Ups Sale Amount to data/x-signups.parquet.
A growth analyst loads the file in a notebook next to the repo, joins it with Full text from Promoted Tweets Metadata and models cost per sign-up by message.
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 | |
|---|---|---|---|
| Ad data in code | Every script needs its own X Ads API client, signed requests and a batch limit of 20 entity IDs per stats call. | Gemini CLI queries the extracted datasets by entity and field name through one MCP server, with no X API code in the repo. | Checks without API plumbing |
| Snapshots before data expires | A forgotten pull means the week is gone, because the X API only allows extraction up to 7 days back. | The flow extracts on schedule, and a script in the repo can ask Gemini to write a dated CSV after each run. | Weekly files kept in Git |
| Control over each call | A script with stored X credentials can call any endpoint, and nobody reviews what it requested. | Gemini CLI asks you to confirm each Dataddo tool call, and you decide per tool whether to choose Always allow. | Every lookup visible |
| Token consumption | Gemini 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. Gemini queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Gemini
|
|---|---|---|
| Campaign Analytics |
|
Which campaigns had Spend but no URL Clicks on a given Date Start? |
| Promoted Tweets |
|
What did we pay per Billed Engagements on each promoted post by Tweet Id this week? |
| Promoted Tweets Metadata |
|
How is our promoted content split by Tweet type? |
| Campaigns |
|
Which campaigns show an Effective Status that differs from their Entity Status? |
| Organic Tweets |
|
Which organic posts earned more Likes than our best promoted post? |
| Account Analytics |
|
Which ad Account ID had the highest Engagements in the last 7 days? |
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 X Ads datasets such as Promoted Tweets and Campaigns in Dataddo and attach them to a Google Gemini destination or AI Model. Add Dataddo under mcpServers in ~/.gemini/settings.json with httpUrl https://headless.dataddo.com/mcp-data, restart Gemini CLI, run /mcp auth dataddo and sign in.
No. Dataddo extracts the X Ads datasets into a flow, and Gemini CLI reads that flow through the Dataddo MCP server. The setup is the same as for any other Dataddo source.
Use the httpUrl key, not url, because url falls back to SSE, which Dataddo does not support. Leave out headers and oauth blocks, restart Gemini CLI and check /mcp.
Yes, through Gemini Code Assist. In IntelliJ it uses its own mcp.json, so add the Dataddo server there. Agent mode in VS Code reads the same settings.json as Gemini CLI.
Every flow or Context attached to an AI destination or AI Model in your Dataddo account, not only the Google Gemini ones. Keep Twitter Ads accounts out of AI destinations if Gemini should not see them.
Credentials are stored in ~/.gemini/mcp-oauth-tokens.json and renewed automatically. If a session expires or is revoked, run /mcp auth dataddo again and sign in.
No. Gemini queries extracted data through the semantic layer by entity and field name. Dataddo never accepts SQL from the model, and nothing is written back to X.
