Data to AI™ / Gemini/Instagram Public Data
Pull competitor and creator posts into the terminal or the IDE, and let Gemini write the CSVs, notebooks and scripts your marketing analytics already run on.
Better answers, fewer tokens.
Gemini CLI
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.
Query Posts for every tracked account with Media Id, Timestamp, Media Type, Like Count, Comments Count and View Count, and save it as data/competitor-posts.csv.
A marketing analyst feeds the file into an existing Jupyter notebook that charts weekly cadence and response, instead of maintaining a scraper of their own.
Compare Followers Count per Username between the two latest dataddo_extraction_timestamp values and print accounts that moved more than five percent.
A growth engineer runs the check from the terminal each Monday and pastes the list into the team update when a competitor suddenly gains followers.
Read Caption and Like Count for all tracked posts from the last 90 days, extract recurring keywords and hashtags, and write the top terms with average likes to reports/caption-terms.md.
A technical marketer commits the report to the content repository, so copywriters see which words rivals lean on before the next brief.
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 | |
|---|---|---|---|
| Getting the data into code | Analysts copy numbers from rival profiles into a sheet, export it and load it by hand before any analysis can run. | Gemini CLI queries Posts and Profile through Dataddo and writes the file straight into the working directory. | Data lands where the code is |
| Field names in scripts | Scripts break when someone renames a column in a hand-made export of competitor data. | Posts and Profile keep the same field names on every run, such as Like Count, Comments Count and Followers Count. | Stable inputs for scripts |
| Control in the terminal | A pasted CSV gives the model everything at once, and you cannot see what it actually read. | Gemini CLI asks you to confirm each Dataddo tool call, and you can choose Always allow per tool once you trust it. | Every call visible |
| Token consumption | Gemini 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. Gemini queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Gemini
|
|---|---|---|
| Posts |
|
Which video posts, filtered by Media Type, have the highest View Count, and what is their Permalink? |
| Profile |
|
How did Followers Count of each Username change between the last two scheduled extractions? |
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 Public Data source with Posts and Profile for each public Username and attach it to a Google Gemini destination or AI Model in Dataddo. Add dataddo under mcpServers with httpUrl https://headless.dataddo.com/mcp-data in ~/.gemini/settings.json, restart Gemini CLI and run /mcp auth dataddo to sign in.
With the url key, Gemini CLI falls back to SSE, which Dataddo does not support. Use httpUrl with https://headless.dataddo.com/mcp-data and leave out any headers or oauth block, then run /mcp auth dataddo.
Yes. Agent mode in VS Code reads the same settings.json as Gemini CLI. In IntelliJ, add the Dataddo server to the mcp.json of Gemini Code Assist instead, then sign in the same way.
No. Once signed in, Gemini reaches every flow or Context attached to an AI destination or AI Model in that Dataddo account, not only the Google Gemini ones. Keep that in mind when you share an account.
Like Count, Comments Count and View Count are public totals at the moment of extraction. Neither dataset uses a date range, so every scheduled run updates them, and dataddo_extraction_timestamp tells you when each row was read.
The Id column in Posts refers to the Id in Profile, so Gemini can join each post to its Username and Followers Count, while Media Id identifies the post itself.
Credentials are stored in ~/.gemini/mcp-oauth-tokens.json and renewed automatically. If a session expires or is revoked, run /mcp auth dataddo again and sign in with your Dataddo email and password.
No. Gemini queries extracted data through the semantic layer by entity and field name. Dataddo never accepts SQL from the model and nothing is written back to Instagram.
