Data to AI™ / Gemini/Gusto
Pull payroll and workforce figures from Gusto into scripts, notebooks and checks from your terminal, with employee identifiers hashed before they reach Gemini.
Better answers, fewer tokens.
Gemini CLI
What did each September payroll cost us, including employer taxes?
The three September payrolls came to $412,300 in Gross Pay and $31,540 in Employer Taxes. The off-cycle run on Sep 19 covered bonuses only.
| Check Date | Gross Pay | Employer Taxes | Net Pay |
|---|---|---|---|
| Sep 15, 2026 Payrolls | $196,800 | $15,060 | $141,900 |
| Sep 19, 2026 Payrolls | $18,700 | $1,430 | $12,600 |
| Sep 30, 2026 Payrolls | $196,800 | $15,050 | $142,100 |
Payrolls reads processed and unprocessed payrolls in the date window, so the answer checks Processed. Gross Pay and Employer Taxes were left out of Hash Sensitive Fields here so they can be summed.
Gusto runs payroll, benefits and HR for small and mid-sized businesses. Dataddo extracts employees, jobs, terminations, payrolls, per-employee pay, time off and contractor payments for one Gusto company, so HR and payroll teams can ask about headcount, payroll cost and leave in plain language.
Use dataddo to get Payroll Employee Compensations per Check Date for last quarter, count distinct Employee UUID and write recon/gusto-paid-headcount.csv.
A finance systems analyst compares paid headcount per payroll with the general ledger in a script kept next to the reconciliation notebook.
Compare the count of Employees that are not Terminated with distinct Employee UUID in the latest Payroll Employee Compensations and print any gap.
Before deploying a change to the internal HR sync, a data engineer runs the check in the terminal to make sure no active employee dropped out of payroll.
From Employee Jobs, summarize Primary jobs by Title and Payment Unit and save it as planning/fixtures/gusto-roles.json.
A developer of the workforce planning tool refreshes test fixtures from real role counts without copying any personal data into the repository.
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
Gusto datasets with personal data offer the Hash Sensitive Fields option. Dataddo replaces the values of the columns you select with a hash before the data leaves Dataddo, so Gemini can still count and group records but never sees the raw values.
| Dataset | Sensitive fields preselected by Dataddo |
|---|---|
| Companies |
|
| Contractors |
|
| Employees |
|
| Employee Terminations |
|
| Employee Work Addresses |
|
| Payrolls |
|
| Without Dataddo |
With Dataddo
|
Outcome for you | |
|---|---|---|---|
| HR data in the repository | An engineer downloads a Gusto export with SSN, Email and Date of Birth to a laptop and trims columns by hand before saving a CSV. | Hash Sensitive Fields hashes those columns during extraction, so files Gemini writes contain stable hashes that still join across datasets. | Safe extracts by default |
| Paid headcount checks | Comparing active employees with people paid in each run means two exports and a lookup formula every pay period. | Gemini CLI queries Employees and Payroll Employee Compensations in one session and prints the gap by Employee UUID. | Reconciliation in one command |
| Tool approvals in the terminal | A script with a stored API key runs unattended, and nobody reviews which HR data it reads. | Gemini CLI asks you to confirm each Dataddo tool call, and you can choose Always allow only for the tools you trust. | Reviewed access to HR data |
| Token consumption | Gemini spends tokens exploring raw Gusto 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 Gusto 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 |
|
How many direct reports does each Manager UUID have among employees who are not Terminated? |
| Employee Jobs |
|
Which employees hold more than one job, and which of them is the Primary one? |
| Employee Terminations |
|
Which Department lost the most people last quarter, counting terminations by Effective Date? |
| Payrolls |
|
How does Net Pay compare with Gross Pay for each payroll this year? |
| Payroll Employee Compensations |
|
Which Employee UUID received pay in an earlier payroll but not in the latest Check Date? |
| Time Off Requests |
|
How many requests per Policy Type were submitted last quarter, and how many Days do they cover? |
| Employee Time Off Activities |
|
Which Policy Name had the largest negative Balance Change last month? |
| Contractor Payments |
|
How many contractor payments went out by each Payment Method, by Payments Date? |
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 Gusto source in Dataddo with Payroll Employee Compensations, Payrolls and Employees and attach it to a Google Gemini destination or AI Model. Add dataddo with httpUrl https://headless.dataddo.com/mcp-data under mcpServers in ~/.gemini/settings.json, restart Gemini CLI and run /mcp auth dataddo to sign in.
Use the httpUrl key under mcpServers, with no headers or oauth block. The url key falls back to SSE, which Dataddo does not support.
Yes. Agent mode in VS Code reads the same settings.json as Gemini CLI. In IntelliJ, add the server to the mcp.json of Gemini Code Assist.
Yes. The same value always produces the same hash, so Gemini can still count employees and join datasets. Only the columns selected under Select Columns for Sensitive Computation are hashed; Employee UUID stays as is.
Every flow or Context attached to an AI destination or AI Model in that Dataddo account, not only the Google Gemini ones. Keep HR flows in an account meant for them.
In ~/.gemini/mcp-oauth-tokens.json, renewed automatically. If the session expires or is revoked, run /mcp auth dataddo again.
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 Gusto.
