Data to AI™ / Gemini/LinkedIn Organic
Pull company page posts, follower gains and page views into the terminal or VS Code, so marketing analysts build content datasets and report checks without a LinkedIn app of their own.
Better answers, fewer tokens.
Gemini CLI
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.
Join Posts Metadata and Post Lifetime Engagement Metrics on post ID for this year, keep Content Type, Published At, Impression Count, Click Count and Engagement, and save analysis/linkedin-posts.csv.
A marketing analyst builds one clean table of every company page post in Gemini CLI and opens it in the notebook that models which formats drive clicks.
Sum Impression Count and Click Count from Company Daily Engagement Metrics for September and compare them with reports/september.json. Flag any figure that differs.
Before the monthly social dashboard is redeployed, a technical marketer runs the check from the terminal and stops the release if a total drifted.
Write scripts/linkedin_growth.py that prints Organic Follower Gain and Paid Follower Gain per Organization Name for the last 7 days, using the dataddo tools for the numbers.
A RevOps engineer working in VS Code asks Gemini Code Assist in agent mode for the script, then runs it every Monday ahead of the pipeline review.
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 data for notebooks | An analyst downloads the updates export per page, fixes date formats and copies the post text into a separate sheet before any modelling starts. | Gemini CLI queries Posts Metadata and Post Lifetime Engagement Metrics by field name and writes the joined table straight into the repo. | Notebook-ready post table |
| LinkedIn API access | Calling the LinkedIn API from a script means registering your own app and keeping its tokens on every laptop that runs it. | LinkedIn is authorized once in Dataddo; Gemini CLI keeps only Dataddo sign-in tokens in ~/.gemini/mcp-oauth-tokens.json and renews them. | No LinkedIn app to maintain |
| Release checks | Dashboard numbers are compared with LinkedIn page analytics by eye, and mismatches are found by the readers. | A check in the repo asks Gemini for Company Daily Engagement Metrics totals and compares them with the dashboard fixtures before each deploy. | Totals verified before deploy |
| Control in the terminal | A script with full API access sends whatever requests it was written to send, without asking. | Gemini CLI asks you to confirm each Dataddo tool call, and Always allow can be granted only to the tools you trust. | Each lookup approved |
| Token consumption | Gemini 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. Gemini queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Gemini
|
|---|---|---|
| Company Daily Follower Metrics |
|
Write Organic Follower Gain and Paid Follower Gain by Start date for the last 90 days to a CSV for the growth chart. |
| Company Daily Engagement Metrics |
|
Pull Impression Count, Unique Impressions Counts and Click Count by Start for the last 30 days into a notebook. |
| Company Daily Views Metrics |
|
Write daily All Page Views and Careers Page Views by Start to a CSV for the employer brand report. |
| Company Lifetime Follower Metrics by Seniority |
|
Export Organic Follower Count and Paid Follower Count by Seniority as a table for the audience report. |
| Company Lifetime Follower Metrics by Function |
|
Compare Organic Follower Count by Function Name across every Organization Name in the account and save it as JSON. |
| Post Lifetime Engagement Metrics |
|
List Post ID, Created At and Engagement for every post this year in a CSV for the content review. |
| Posts Metadata |
|
Group posts by Visibility and Content Type for the last 90 days and save the counts to a file. |
| Video Analytics |
|
Write VIDEO_VIEW and TIME_WATCHED Value per Post ID by Start to a CSV. |
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 Posts Metadata and Post Lifetime Engagement Metrics, and attach it to a Google Gemini destination or AI Model. In ~/.gemini/settings.json, add a dataddo server under mcpServers with httpUrl https://headless.dataddo.com/mcp-data, restart Gemini CLI and run /mcp auth dataddo.
Attach the LinkedIn Organic flow to a Google Gemini destination or AI Model in Dataddo. Add the dataddo server with httpUrl to settings.json, restart Gemini CLI, run /mcp auth dataddo and confirm with /mcp.
In Gemini CLI, url falls back to SSE, which Dataddo does not support. Use httpUrl, leave out headers and any oauth block, and sign in through /mcp auth dataddo.
Yes. Agent mode in VS Code reads the same settings.json as Gemini CLI. In IntelliJ, Gemini Code Assist uses its own mcp.json, so add the Dataddo server there too.
Every flow or Context attached to an AI destination or AI Model in that Dataddo account, not only the Google Gemini ones.
No. Gemini queries extracted LinkedIn Organic data through the semantic layer by entity and field name. Dataddo never accepts SQL from the model, and nothing is written back to LinkedIn.
Yes. Company Daily Engagement, Follower and Views Metrics offer a time granularity of Day or Month, chosen when you create the source. For both, create two sources and tell Gemini which one a script should read.
