Data to AI™ / Gemini/Personio
Pull Personio attendance hours, exit history and org data into notebooks, CSVs and pre-deploy checks from the terminal, without exporting files or storing API keys in the repo.
Better answers, fewer tokens.
Gemini CLI
Which departments took the most approved sick leave days in September?
Approved sick leave in September added up to 96 days. Customer Support took 41 of them, more than Engineering and Sales together.
| Department Name | Days Count |
|---|---|
| Customer Support Absences | 41 |
| Engineering Absences | 23 |
| Sales Absences | 17 |
Days Count is summed over absences with an approved Status; Department Name comes from Employees, matched on Employee ID.
Personio is an HR platform for small and medium-sized businesses that covers personnel administration, time tracking and absence management. Dataddo extracts Employees, Absences and Attendances, so People teams can ask about headcount, time off and working hours in plain language.
From Attendances for last month, compute hours per Employee from Start Time and End Time minus Break, confirmed Status only, and write payroll/hours-2026-09.csv.
A payroll analyst runs Gemini CLI in the payroll repo and diffs the file against the provider's import before the run is approved.
List active Employees with an empty Department Name, Office Name or Cost Centers Name, and exit non-zero in the script you write if any exist.
A data engineer adds the check to the deploy steps of the directory sync, so incomplete Personio records are fixed before they spread to other systems.
Load Employees with a Termination Date in the last 24 months into a dataframe with Termination Type, Termination Reason and Department Name, and plot exits per quarter.
A people analyst works in VS Code with Gemini Code Assist in agent mode and keeps the attrition analysis as a versioned notebook instead of a one-off export.
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 | |
|---|---|---|---|
| Attendance hours | Someone downloads attendance reports, cleans the time columns and recalculates breaks in a spreadsheet each month. | Gemini reads Attendances with Start Time, End Time and Break and writes the totals to a file in your repo. | Hours computed in code |
| Org data quality | Gaps in department or cost center assignments are discovered after a sync has already pushed them downstream. | A check written with Gemini CLI queries Employees before each deploy and fails when key org fields are empty. | Gaps caught before deploy |
| Credentials in the repo | Scripts call the Personio API with a client secret kept in an env file that ends up shared or committed. | Gemini CLI signs in to Dataddo with OAuth and stores the tokens in ~/.gemini/mcp-oauth-tokens.json, outside the project. | No secrets in the codebase |
| Exit history | Leavers are pulled from Personio when someone asks, and every analysis starts from a different export. | Employees carries Termination Date, Termination Type and Termination Reason, so the notebook queries the same fields every time. | Repeatable attrition analysis |
| Token consumption | Gemini spends tokens exploring raw Personio 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 Personio datasets HR and payroll teams use most, with their real field names. Gemini queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Gemini
|
|---|---|---|
| Employees |
|
What were the most common Termination Reason values over the last 12 months, by Termination Type? |
| Absences |
|
Which Time Off Category accounts for the most absence days this year, based on Start Date? |
| Attendances |
|
Which days had attendance periods with a Start Time before 7:00 or an End Time after 20:00? |
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 Personio source in Dataddo with your client ID and secret, extract Attendances or Employees, and attach it to a Google Gemini destination or AI Model. Add dataddo with httpUrl https://headless.dataddo.com/mcp-data to ~/.gemini/settings.json, restart Gemini CLI and run /mcp auth dataddo to sign in.
Add dataddo under mcpServers in ~/.gemini/settings.json, or .gemini/settings.json for one project, with the httpUrl key and no headers or oauth block. Restart Gemini CLI, run /mcp auth dataddo and check /mcp.
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.
Not by default. Gemini CLI asks you to confirm each Dataddo tool call, and you can choose Always allow for individual tools once you trust them.
Every flow or Context attached to an AI destination or AI Model in that Dataddo account, not only the Gemini ones. Leave salary and personal columns out of the Personio source if they should not be queried.
Attendances and Absences read a sliding date window that each run replaces. Run a full data re-sync with a wider range once to load the months your analysis needs.
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 Personio.
