Data to AI™ / Copilot/TikTok
Let the social team ask a Copilot agent in Teams about TikTok video reach, watch time and follower growth, instead of downloading analytics every Monday.
Less tokens, better answers.
Microsoft 365 Copilot
How did our TikTok followers change week by week in September, and when did we lose most?
The account gained 6,210 net followers over four weeks. Losses peaked in the week of 8 Sep at 1,150, and 22-28 Sep was the strongest week with 2,500 net.
| Week | Daily New Followers | Daily Lost Followers | Daily Total Followers |
|---|---|---|---|
| 1-7 Sep Profile Daily Insights | 1,840 | 420 | 1,420 |
| 8-14 Sep Profile Daily Insights | 2,310 | 1,150 | 1,160 |
| 15-21 Sep Profile Daily Insights | 1,520 | 390 | 1,130 |
| 22-28 Sep Profile Daily Insights | 2,960 | 460 | 2,500 |
Daily Total Followers is the daily net change in followers, not the follower count, so it is summed per week.
TikTok Organic extracts non-paid insights from a TikTok business account: daily profile activity, follower audience breakdowns, and per-video reach, watch time, retention, traffic sources and comments.
@TikTok pulse Which videos brought the most New Followers and Profile Views last week, and what Caption did each one use?
The agent sits in the social team's channel, so anyone can check last week's winners before the standup, read straight from Video Lifetime Insights instead of collected screenshots.
@TikTok pulse For our five videos with the most Reach, what Percentage of views came from each Impression Source?
In Microsoft 365 Copilot, the content lead sees which Impression Source values bring views to the strongest videos, using Video Lifetime Traffic Sources, and adjusts the posting plan.
Use the dataddo tools to query Video Lifetime View Retention and check our drop-off calculation in src/metrics/retention.ts.
A marketing engineer uses GitHub Copilot in Agent mode in VS Code to compare real retention by Second with the dashboard code, without copying a CSV into the repository.
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 | |
|---|---|---|---|
| Getting the numbers into Copilot | Someone downloads TikTok analytics every Monday and posts screenshots of follower and video numbers into the team channel. | The Copilot Studio agent reads Profile Daily Insights and Video Lifetime Insights from Dataddo whenever a colleague mentions it. | No Monday export |
| Several brand profiles | Each TikTok business account is exported on its own, then merged in a spreadsheet before anyone can compare brands. | Multi-account extraction collects the same dataset from every profile you can access, so one agent answers for all of them. | All profiles in one agent |
| When the agent calls Dataddo | A general Copilot answer about TikTok draws on public knowledge, not on how your own account performed. | The server description in Copilot Studio tells the agent to call Dataddo for TikTok videos and followers, so answers come from your data. | Answers from your account |
| Token consumption | Copilot spends tokens exploring raw TikTok 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 TikTok 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. Only Profile Daily Insights reads a relative window such as yesterday; the video and audience datasets are lifetime snapshots, so append them with dataddo_extraction_timestamp to track change.
TikTok 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 TikTok Organic source in Dataddo with datasets such as Video Lifetime Insights and Profile Daily Insights, and attach it to a Copilot destination or AI Model. In Copilot Studio, add https://headless.dataddo.com/mcp-data as a Model Context Protocol tool with OAuth 2.0, then publish the agent to Teams.
Yes. Dataddo extracts TikTok data on a schedule, and a Copilot Studio agent reads it through the Dataddo Data Access MCP tool. You only add the tool, sign in and publish.
Yes. Video Lifetime Audience by Type, Country, City and Gender give a Percentage per value for each Video ID, so the agent can describe the viewers behind a specific video.
Profile Lifetime Audience datasets by age, gender, city and country are only available for TikTok accounts with at least 100 followers.
Video datasets are lifetime snapshots. Append them with the dataddo_extraction_timestamp column and the agent can compare one day's snapshot with another.
Yes. Put the Dataddo URL in .vscode/mcp.json, start the server, sign in and use Copilot Chat in Agent mode. On Business and Enterprise, an admin enables the MCP servers in Copilot policy first.
The server description you write in Copilot Studio tells the agent when to call Dataddo. Mention TikTok videos and followers there, so those questions trigger a lookup.