Data to AI™ / Claude/DV360
Ask Claude about DV360 spend, line item pacing and frequency per insertion order, with reach handled correctly, instead of stitching offline reports together.
Less tokens, better answers.
Claude
Which insertion orders showed ads to the same people too often this month?
Retargeting Display reached 96,500 people at 11.2 impressions each, more than three times the 3.4 of Brand Awareness CTV. Prospecting Video sat in between at 7.8.
| Insertion Order | Unique Reach: Total Reach | Unique Reach: Average Impression Frequency |
|---|---|---|
| Retargeting Display DV360 Reach/Frequency by Insertion Order | 96,500 | 11.2 |
| Prospecting Video DV360 Reach/Frequency by Insertion Order | 412,000 | 7.8 |
| Brand Awareness CTV DV360 Reach/Frequency by Insertion Order | 1,180,000 | 3.4 |
Reach is shown per insertion order and not added up, because DV360 reach is estimated.
Dataddo extracts Google Display & Video 360 (DV360) reporting through a flexible report dataset with report types such as Standard and YouTube, plus a reach and frequency dataset and an advertiser list.
Which line items have a Line Item Pacing Percentage below 80 this week? Show Budget Segment Budget and Total Media Cost (Advertiser Currency) for each.
A programmatic trader sees under- and over-pacing line items before the day starts and moves budget in DV360 before an insertion order ends short.
From DV360 Reach/Frequency by Insertion Order, which insertion orders have Unique Reach: Average Impression Frequency above 6 this month?
A media planner finds the insertion orders that hit the same people too often and caps frequency there, reading reach per insertion order rather than one summed figure.
Pull Total Media Cost (Advertiser Currency) and Active View: % Viewable Impressions by Exchange and Campaign via the dataddo server and write reports/dv360-weekly.md.
An agency analyst runs Claude Code in the reporting repository and commits a weekly markdown recap that the account team reviews with clients.
Data to AI™ is free while in private pre-release. We onboard teams in waves and shape the product with their feedback. At launch, it will be priced like the AI assistants your team already uses. Need tailored contracts or volume pricing? Talk to us about Enterprise.
Serve governed business data to Claude, ChatGPT and other AI tools over MCP.
Free during pre-release
Flexibly deploy Dataddo in any cloud or hybrid environment.
We have a payment model that works for you
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| Report types in one place | Standard, YouTube and reach metrics come from separate offline reports, each downloaded and lined up by hand before Claude can see them. | Dataddo runs each DV360 report type on your schedule, and Claude queries Insertion Order, Line Item or Exchange fields by name across them. | One conversation, all report types |
| Reach that cannot be summed | Unique reach from several insertion orders or months gets added up in a spreadsheet, so the audience looks larger than it was. | The reach dataset is described as estimated and non-additive across insertion orders, so Claude reports reach per insertion order instead of totalling it. | Audience size not overstated |
| Ranges longer than 93 days | DV360 returns cumulative reach in blocks of at most 93 days, and long manual pulls mix blocks without saying where one ends. | Dataddo splits longer ranges into blocks and stamps each row with Block Start Date and an Exceeds 93 Days flag that Claude can read. | Every figure tied to its block |
| Traders on one setup | Each trader keeps a personal export folder, and the desk argues over which file holds the right pacing numbers. | On Claude Team and Enterprise an Owner adds Dataddo Data Access once, and each trader signs in with their own Dataddo account. | Shared setup, own access |
| Token consumption | Claude spends tokens exploring raw DV360 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. | Less 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 DV360 datasets marketing teams use most, with their real field names. Claude queries them by name through the Dataddo semantic layer.
List of curated datasets
Need a dataset, metric, or attribute you don't see?
Tell us what's missing and we'll add it to the connector.
Runs on your schedule with a relative date range such as yesterday or last 30 days. Reach comes in blocks of up to 93 days that cannot be summed, and DV360 Advertisers reloads the full list every run.
DV360 connector →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 →Create a Google Display & Video 360 source in Dataddo, add DV360 Reach/Frequency by Insertion Order and a Standard report with Total Media Cost (Advertiser Currency) and Line Item Pacing Percentage, then attach it to a Claude destination or AI Model. In Claude, add https://headless.dataddo.com/mcp-data as a custom connector, or run claude mcp add.
No. Dataddo runs your DV360 reports on a schedule and serves them through the Data Access MCP server. Claude signs in there with your Dataddo account.
Reach in DV360 is estimated and cannot be summed across insertion orders or across date blocks. The reach dataset stamps each row with its block, so Claude can report reach per block.
DV360 returns cumulative reach in blocks of at most 93 days. Dataddo splits longer ranges into blocks and marks each row with Block Start Date and an Exceeds 93 Days flag.
Yes, if you extract a YouTube report type. It adds fields such as TrueView: Views, TrueView: View Rate and Earned Views, which Claude can query alongside your Standard report.
Yes. Run claude mcp add with the Dataddo URL and sign in with /mcp. Claude Code keeps the credentials in your system keychain and queries the same DV360 entities from your terminal.
All plans support custom connectors, and Free allows one. On Team and Enterprise an Owner adds Dataddo Data Access once, and each trader signs in with their own Dataddo account.