Data to AI™ / Copilot/Instagram
Ask about reels, reach and follower growth in Microsoft 365 Copilot and Teams, without exporting insights or rebuilding the weekly social report.
Less tokens, better answers.
Microsoft 365 Copilot
Which content format reached the most accounts per post last month?
Reels reached about 2.4x more accounts per post than single images and drew most of the shares. Carousels sat in between on both.
| Format | Posts | Avg Reach | Avg Shares |
|---|---|---|---|
| Reels Reel Lifetime Insights | 14 | 18,240 | 412 |
| Carousels Carousel Post Lifetime Insights | 9 | 9,860 | 133 |
| Images Post Lifetime Insights (Image) | 11 | 7,450 | 61 |
Reach is averaged per post from lifetime insights, not added up across posts or days.
Instagram Organic extracts non-paid insights from Instagram Business accounts: posts, stories, reels, audience demographics and engagement.
@Social data Which reels from last week had the most Shares Count, and how did their Avg Watch Time compare?
The social lead asks the agent in the team channel instead of compiling screenshots. Shares Count and Avg Watch Time come straight from Reel Lifetime Insights.
@Social data Compare the Reach of posts published inside and outside our top Online Followers hours last quarter.
Online Followers by Hour of Day sits next to per-post Reach, so the posting schedule follows your own audience, not a generic best-time chart.
@Social data Which format, carousels, reels or images, got the most Saved per post last month?
Carousel, reel and image insights come from separate datasets. The agent compares them per post, so the content plan can lean on what people keep.
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 exports Instagram insights per account and format, then pastes or uploads them into the chat every week. | The Copilot Studio agent reads Business Interactions, reels and stories from Dataddo whenever someone asks. | No weekly export work |
| What the metrics mean | Copilot sees column names like Reach and Views without definitions and has to guess how to combine them. | Every field comes with its business description from the Dataddo semantic layer, so the model knows what each metric means. | Numbers you can quote |
| Freshness | Answers reflect whatever file was uploaded last, with no date attached. | Answers come with the freshness of the last extraction, which runs on the schedule you set. | You know how current each answer is |
| One answer for the team | Each person keeps their own export, so discussions in Teams start from different numbers. | The same agent in Teams and Microsoft 365 Copilot answers everyone from the same Instagram data. | One version of the numbers |
| Token consumption | Copilot spends tokens exploring raw Instagram 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 Instagram 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, with a relative date range such as yesterday that moves forward on every run. The Instagram API allows up to 2 years of history, loaded with a full data re-sync.
Instagram 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 an Instagram Organic source in Dataddo and attach it to a Copilot destination or AI Model. In Copilot Studio, add the Dataddo Data Access MCP server (https://headless.dataddo.com/mcp-data) as a tool on an agent, sign in with OAuth, and publish the agent to Microsoft 365 Copilot and Teams.
Yes, through a Copilot Studio agent. Add Dataddo Data Access as a Model Context Protocol tool, publish the agent to Microsoft 365 Copilot, then mention it with @ and ask about the Instagram datasets you attached.
Yes. After publishing, go to Channels > Teams and Microsoft Copilot and add the channel. The same agent answers from the same Instagram data in Teams.
Yes. Add the Dataddo server to .vscode/mcp.json, sign in and use Copilot Chat in Agent mode. On Business and Enterprise, an admin must first enable the MCP servers in Copilot policy.
Reach counts daily unique accounts, so daily values cannot be summed. For weekly or monthly reach, extract a weekly or monthly breakdown in a separate source and flow and ask Copilot about that.
Yes. The Business Follower Demo Country, Age and Gender datasets give follower counts per value, so the agent can tell you which markets and age groups make up your audience.
Up to 2 years, the limit of the Instagram API. A new source starts from its current date range, so load older data once with a full data re-sync.