Data to AI™ / Copilot/LinkedIn Organic
Let communications and social teams ask a Teams agent how yesterday's company page post landed, how engagement is trending and which videos people watch, from current LinkedIn data.
Better answers, fewer tokens.
Microsoft 365 Copilot
Which of our company pages gained the most followers in September, and how much of it was paid?
The three pages gained 2,090 followers in September. Northwind Group added the most, 1,240, and 31% of its gain came from Paid Follower Gain; the careers page grew almost entirely organically.
| Organization Name | Organic Follower Gain | Paid Follower Gain |
|---|---|---|
| Northwind Group Company Daily Follower Metrics | 860 | 380 |
| Northwind Careers Company Daily Follower Metrics | 540 | 12 |
| Northwind Labs Company Daily Follower Metrics | 290 | 8 |
Organic Follower Gain and Paid Follower Gain are kept apart as LinkedIn reports them, read at Month granularity for each company page.
LinkedIn Organic covers the LinkedIn company pages you administer: followers by day and by audience segment, page views, page and post engagement, and video analytics. Dataddo extracts them per company page, so marketing can ask about audience growth and content performance in plain language. Paid campaigns are a separate connector, LinkedIn Ads.
@Page Pulse How did our product launch post perform since Created At? Show Impression Count, Like Count, Comment Count and Share Count.
The communications manager asks in the comms channel the morning after a launch, so the leadership update quotes real numbers rather than a feeling about the post.
@Page Pulse For video posts this month, list Post ID with VIDEO_VIEW and TIME_WATCHED Value, sorted by watch time.
The in-house video team checks in Microsoft 365 Copilot which formats people actually watch before they book the next shoot.
Use the dataddo tools to describe Company Daily Engagement Metrics and generate a TypeScript type for its fields, including Unique Impressions Counts and Engagement.
A web developer uses GitHub Copilot in Agent mode to keep the internal social dashboard typed against the real LinkedIn Organic schema.
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 | |
|---|---|---|---|
| Post results for leadership | A social manager opens LinkedIn page analytics, copies the numbers of one post into an email and sends it around the next day. | Anyone in the comms channel asks the agent in Teams, and it reads Post Lifetime Engagement Metrics from the latest scheduled extraction. | Post results on request |
| Engagement trend | Weekly engagement is rebuilt by hand from daily exports, and the trend line differs between decks. | Company Daily Engagement Metrics offers Day or Month granularity, so the agent answers weekly and monthly trends from the same data. | One engagement trend |
| Video performance | Video views and watch time are checked post by post, so the studio never sees which format holds attention. | Video Analytics returns one row per post per Metric Type, such as VIDEO_VIEW, VIEWER and TIME_WATCHED, for the agent to compare. | Video formats compared |
| Token consumption | Copilot spends tokens exploring raw LinkedIn Organic 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 LinkedIn Organic datasets marketing teams use most, with their real field names. Copilot queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Copilot
|
|---|---|---|
| Company Daily Follower Metrics |
|
What share of new followers came from Paid Follower Gain each month this year on our main company page? |
| Company Daily Engagement Metrics |
|
What was the monthly Engagement of each Organization Name over the last six months? |
| Company Daily Views Metrics |
|
Which weeks had the most Overview Page Views, and did Life At Page Views follow the same pattern? |
| Company Lifetime Follower Metrics by Seniority |
|
How does the Seniority mix of followers differ between each Organization Name we manage? |
| Company Lifetime Follower Metrics by Function |
|
Do our followers by Function Name match the buyer functions our campaigns are meant to reach? |
| Post Lifetime Engagement Metrics |
|
Which ten posts got the most Comment Count and Share Count since January? |
| Posts Metadata |
|
Which Author published the most posts on our company page this quarter? |
| Video Analytics |
|
Which videos reached the most people, based on the VIEWER Metric Type? |
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 LinkedIn Organic source in Dataddo with Post Lifetime Engagement Metrics, Company Daily Engagement Metrics and Video Analytics, and attach it to a Copilot destination or AI Model. In Copilot Studio, add a Model Context Protocol tool for https://headless.dataddo.com/mcp-data with OAuth 2.0 Dynamic discovery, then publish the agent to Teams.
Build a Copilot Studio agent, add Dataddo Data Access as a Model Context Protocol tool with OAuth 2.0 Dynamic discovery, then publish it through Channels to Teams and Microsoft 365 Copilot.
From the server description you write in Copilot Studio. Say it holds LinkedIn company page followers, views, posts and video analytics, so those questions trigger a Dataddo call.
People you publish the agent to. In Teams or Microsoft 365 Copilot they type @ and select it, and the agent answers from the LinkedIn Organic flows attached in Dataddo.
Video Analytics supports four Metric Type values: VIDEO_VIEW, VIEWER, TIME_WATCHED and TIME_WATCHED_FOR_VIDEO_VIEWS. You choose which ones to extract when you create the source.
Yes. Add the Dataddo server to .vscode/mcp.json, start it, sign in and use Copilot Chat in Agent mode. On Business and Enterprise, an organization admin must enable MCP servers in Copilot policy first.
