Data to AI™ / Copilot/YouTube
Give the video team a Copilot agent in Teams that answers questions on views, watch time and subscriber changes straight from your YouTube channel data.
Less tokens, better answers.
Microsoft 365 Copilot
Which traffic sources brought the most watch time to our September uploads?
Suggested videos drove 63% of watch time across these three sources, about twice as much as YouTube search, and held viewers longest at 46% average view duration.
| Traffic Source Type | Views | Watch Time (Minutes) | Average View Duration (%) |
|---|---|---|---|
| Suggested videos Owned Channel Videos Traffic Sources | 48,200 | 212,100 | 46% |
| YouTube search Owned Channel Videos Traffic Sources | 31,500 | 101,000 | 38% |
| External Owned Channel Videos Traffic Sources | 9,800 | 21,600 | 27% |
Views and Watch Time (Minutes) are summed per traffic source; Average View Duration (%) is weighted by Views, not a plain average of videos.
YouTube Organic extracts your channel's non-paid performance: views, watch time, subscribers, traffic sources, audience, comments and playlists, per video and per day.
@Video desk How many Views and Engaged Views has the launch video reached since Tuesday, and what is its Average View Duration (%)?
The product marketing channel asks the agent after each scheduled run lands, so nobody has to open YouTube analytics separately or post screenshots during launch week.
@Video desk Which End Screen Element Type and Card Type earn the highest click rate on our tutorials this quarter?
In Microsoft 365 Copilot, the channel manager compares calls to action across uploads and decides which end screen elements and cards to keep on the next tutorials.
Use the dataddo tools to rank our playlists by Playlist Starts and Playlist Saves Added for the last 90 days.
A web developer asks GitHub Copilot in Agent mode before deciding which playlists the site's video hub component features first, without leaving VS Code or exporting a report.
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 | |
|---|---|---|---|
| Launch numbers in Teams | Someone opens YouTube Studio after each launch and posts screenshots of views into the product marketing channel. | The Copilot Studio agent in that channel reads Owned Channel Videos Basic User Activity from Dataddo whenever it is mentioned. | Launch numbers on request |
| Several channels | Brand, product and regional channels are reported separately and merged by hand for every review. | Multi-account extraction pulls the same dataset from every channel you can access, and Managed Channels Videos Basic User Activity covers managed channels. | All channels in one agent |
| Cross-dimension questions | Device, playback location and traffic source live in separate reports, so a combined question needs several exports. | Owned Channel Videos Combined Playback Insights joins playback location, traffic source, device type and operating system in one dataset the agent can query. | Combined answers in one ask |
| Token consumption | Copilot spends tokens exploring raw YouTube 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 YouTube datasets marketing teams use most, with their real field names. Copilot 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 the schedule you set, for example daily. YouTube Organic datasets do not use a date range, so every run pulls all currently available data.
YouTube 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 YouTube Organic source in Dataddo with datasets such as Owned Channel Videos Basic User Activity and Playlist Basic User Activity, then attach it to a Copilot destination or AI Model. In Copilot Studio, add the MCP tool https://headless.dataddo.com/mcp-data with OAuth 2.0 and Dynamic discovery, and publish the agent to Teams.
Go to Tools > Add a tool > New tool > Model Context Protocol, enter the Dataddo URL, choose OAuth 2.0 with Dynamic discovery and sign in. The agent can then query the YouTube flows attached in Dataddo.
Yes. Multi-account extraction collects the same dataset from every channel you can access, and Managed Channels Videos Basic User Activity aggregates activity across all managed channels.
Yes, once you publish it under Channels > Teams and Microsoft Copilot. Team members then mention the agent and get answers from the same YouTube data.
Yes. The Owned Channel Videos datasets include Country Code, so the agent can split Views and Watch Time (Minutes) by viewer country for any upload.
Yes, in VS Code. Add the server to .vscode/mcp.json with type http, sign in and ask in Agent mode. Business and Enterprise organizations first need the MCP servers in Copilot policy enabled.
The authorized account needs at least admin-level permissions. Missing permissions are one of the common reasons the data preview fails while you set up the source.