Data to AI™ / ChatGPT/DV360
Compare DV360 creatives, YouTube campaigns and advertiser accounts in a ChatGPT chat, approving every lookup, without exporting another offline report.
Less tokens, better answers.
ChatGPT
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 Creative had the best Click Rate (CTR) and Total Conversions over the last 14 days, and which ones had Impressions but no conversions?
A creative strategist confirms each query as it runs and brings a pause-or-scale list to the weekly creative review instead of a stack of report screenshots.
Check data_status, then show TrueView: View Rate and Earned Views by YouTube Ad Group for last month, sorted from best to worst.
A video buyer knows how current the YouTube report is before sharing which ad groups held attention with the brand team.
From DV360 Advertisers, list every advertiser with Entity Status active, then tell me which had no Impressions in the last 30 days.
An agency operations lead finds accounts that are switched on but delivered nothing, which never appear in a performance export at all.
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 | |
|---|---|---|---|
| Exporting offline reports | Create an offline report in DV360, wait for it to run, download the file and upload it to the chat for every new question. | The Dataddo app in developer mode queries the scheduled DV360 source on request, and ChatGPT asks you to confirm each tool call. | No report downloads |
| Advertisers missing from exports | Performance reports only list advertisers with data in the period, so paused or forgotten accounts drop out without anyone noticing. | DV360 Advertisers lists every advertiser you can access across Partners, with Entity Status and Currency Code, even without performance data. | Every account accounted for |
| Mixed advertiser currencies | Spend from advertisers billed in different currencies lands in one column, and totals quietly add euros to dollars. | Currency Code from DV360 Advertisers and Total Media Cost (Advertiser Currency) let ChatGPT see which currency each spend figure is in. | Currencies kept apart |
| Which tools are allowed | An uploaded file can be reused in any chat, with no record of what was looked up from it. | In the app settings you turn individual Dataddo tools on or off, for example leaving query and data_status on while turning report_problem off. | Tool access you control |
| Token consumption | ChatGPT 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. ChatGPT 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 →Set up a Google Display & Video 360 source in Dataddo with a Standard or YouTube report covering Creative, Click Rate (CTR) and TrueView: View Rate, add DV360 Advertisers, and attach it to a ChatGPT destination or AI Model. Then, on the web, enable developer mode and create an app for https://headless.dataddo.com/mcp-data with OAuth.
Developer mode is needed, available on Pro, Plus, Business, Enterprise and Education plans in ChatGPT on the web. On Business and Enterprise an admin may need to allow it.
ChatGPT asks you to confirm each tool call in developer mode, so you can see which DV360 entity and fields it is about to query before data comes back.
Performance reports only include advertisers with data in the period. Add DV360 Advertisers, which lists every advertiser you can access across Partners, even with no performance data.
Yes, if you extract both report types. YouTube reports add TrueView: Views and Earned Views, while Standard reports cover display creatives, so ChatGPT can compare them by campaign.
It should not. DV360 reach is estimated and cannot be summed across insertion orders, so ask ChatGPT for reach per insertion order from DV360 Reach/Frequency by Insertion Order.