Data to AI™ / Copilot/Instagram Public Data
Let marketing and agency teams ask a Teams agent which rival Instagram accounts post most, grow fastest and earn the strongest response, from data refreshed on schedule.
Better answers, fewer tokens.
Microsoft 365 Copilot
How often did each competitor post in September, and whose posts drew the most likes?
@northpeak_coffee posted least but averaged the most likes per post. @harbor_roasters published almost daily, with about a third of the likes per post.
| Username | Posts | Avg Like Count | Avg Comments Count |
|---|---|---|---|
| @northpeak_coffee Posts | 9 | 4,820 | 212 |
| @harbor_roasters Posts | 27 | 1,610 | 48 |
| @bluestone_brew Posts | 14 | 2,370 | 95 |
Posts are counted by Timestamp; Like Count and Comments Count are the public totals at extraction time, averaged per post.
Instagram Public Data reads what anyone can see on a public Instagram profile you name by username, such as a competitor, a peer brand or a creator: the profile with its follower and post counts, and its posts with likes, comments and views. It is not for personal accounts.
@Social Radar Which tracked account published the most posts last week by Timestamp, and whose post had the highest Like Count?
The social team asks the agent in its Teams channel every Monday, so the weekly stand-up starts with what rivals did instead of a round of anecdotes.
@Social Radar Compare Followers Count and average Comments Count per post for our client and the three competitors we benchmark against.
An account manager asks Microsoft 365 Copilot while drafting the monthly client report and drops the comparison into the deck without rebuilding a spreadsheet.
Use the dataddo tools to describe Posts and Profile and write a loader that joins them on Id and outputs average Like Count per Username and Media Type.
A marketing engineer works in VS Code with GitHub Copilot in Agent mode and keeps the competitor dashboard code aligned with the real field names.
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 | |
|---|---|---|---|
| Competitor updates for the team | One person checks rival profiles on a phone and posts screenshots in the team chat, already out of date by lunch. | Anyone in Teams types @ and asks the agent, which reads Posts and Profile from the latest scheduled extraction. | Shared, current view |
| Agency reporting | Every client report needs a fresh manual tally of competitor followers and post likes before it can be written. | The agent answers from one source per tracked Username, so benchmark tables for each client come straight from Followers Count and Like Count. | Reports without tallies |
| When the agent looks up data | A general assistant answers competitor questions from memory and guesses at follower numbers. | The server description you write in Copilot Studio says the data holds Instagram competitor posts and profiles, so those questions trigger a Dataddo lookup. | Answers grounded in data |
| Token consumption | Copilot spends tokens exploring raw Instagram Public Data 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 Instagram Public Data 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
|
|---|---|---|
| Posts |
|
How many posts did each tracked account publish per week last month, counted by Timestamp? |
| Profile |
|
Which tracked brands link a Website in their profile, and what does each Biography say they offer? |
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 Instagram Public Data in Dataddo with Posts and Profile for each competitor Username you follow, 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 and Microsoft 365 Copilot.
Through a Copilot Studio agent. Add Dataddo Data Access as a Model Context Protocol tool with OAuth 2.0 Dynamic discovery, then publish the agent via Channels to Teams and Microsoft 365 Copilot, where people reach it by typing @.
As often as your Dataddo schedule runs, for example daily. Neither Posts nor Profile uses a date range, so each run pulls the profile and its posts as they are at that moment, with current Like Count and Followers Count.
Yes, if you add the dataddo_extraction_timestamp column when you create the Profile source. Every row then records when it was extracted, so with the runs kept in your destination the agent can compare Followers Count across extraction dates.
Sign in with Instagram, the recommended option, or use Meta Admin Center. The Instagram account you authorize with must be connected to a Facebook account.
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 first enable MCP servers in Copilot policy.
Only if you add it as a public Username like any competitor, which gives the same public counts. For private insights of accounts you manage, such as Reach or Saves, use the Instagram Organic connector.
