Data to AI™ / Claude/Personio
Get headcount, probation and contract-end answers from Personio in Claude, so the People team prepares the monthly report in minutes instead of rebuilding pivots.
Better answers, fewer tokens.
Claude
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.
Count active Employees by Department Name and Office Name, and list hires by Hire Date and exits by Termination Date for last month.
Before the leadership meeting, the Head of People gets headcount, joiners and leavers per department from Claude and spends the time on what changed instead of on the spreadsheet.
Which employees have a Probation Period End or a Contract End Date Value in the next 60 days? Group them by Department Name and Team.
HR business partners send each manager a short list of reviews and renewals to prepare, weeks before a probation period quietly runs out.
Use the dataddo server to pull Employees with Department Name, Cost Centers Name and Cost Centers Percentage and write people/headcount-by-cost-center.csv.
A people analyst runs Claude Code next to the workforce planning notebook and commits the file, with the query noted in the commit message.
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 | |
|---|---|---|---|
| Monthly headcount | Someone exports the employee list from Personio, filters out leavers and rebuilds the department and office pivot every month. | Employees pulls all current records on each run with Status, Department Name and Office Name, so Claude counts headcount from the latest extraction. | Report without rebuilds |
| Probation and contract ends | Upcoming probation ends and fixed-term contract ends are checked profile by profile, and some slip past. | Claude reads Probation Period End and Contract End Date Value across all employees and lists what falls in the coming weeks. | Deadlines seen in time |
| Personal data | An employee export pasted into a chat carries names, emails, gender and salaries along with the headcount figures. | Leave columns such as Fix Salary, Hourly Salary, Gender and Email out of the source when you choose its attributes, so they never reach Claude. | Only the columns you choose |
| Access for the People team | Each HR partner keeps a private export, so headcount differs depending on who pulled it and when. | A Claude Team or Enterprise Owner adds the connector once, and each member signs in with their own Dataddo account. | One headcount for the team |
| Token consumption | Claude 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. Claude queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Claude
|
|---|---|---|
| Employees |
|
Whose Probation Period End or Contract End Date Value falls in the next 60 days, by Department Name? |
| Absences |
|
How many Days Count of each Time Off Name were taken last month? |
| Attendances |
|
How many attendance periods per week are still in pending Status? |
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 Personio client ID and client secret, and extract datasets such as Employees and Absences. Attach it to a Claude destination or AI Model, then add Dataddo Data Access from the Claude connectors directory and sign in with your Dataddo account.
An API credential. In Personio, open Settings > API credentials, generate a credential with Read access to personal data and the readable employee attributes, and enter the client ID and secret in Dataddo.
Only if you extract them. When you create the source, untick columns such as Fix Salary, Hourly Salary, Gender, Email or Profile Picture, and Claude can only query what remains.
Absences and Attendances read a sliding date window that each run replaces. Run a full data re-sync with a wider range once, and Claude can then answer about earlier months.
Yes. Signed in with your Claude account, Claude Code loads the Dataddo connector, so you can query Personio entities from the terminal while you work in a repository.
No. Claude 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.
Yes. Claude shows the connector's tool permissions, and for each tool you choose whether Claude may use it freely or must ask you first.
