Data to AI™ / Copilot/Gusto
Give HR business partners and managers a Teams agent for headcount, onboarding progress and leave balances from Gusto, with personal fields hashed at the source.
Better answers, fewer tokens.
Microsoft 365 Copilot
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.
@People Desk Which Employees are not Onboarded yet, by Department, and what Hire Date do their Employee Jobs show?
HR business partners ask the agent in their Teams channel each Monday and chase the new starters whose paperwork is still open.
@People Desk Show the remaining Balance per Policy Name from Employee Time Off Activities, with the largest balances first.
Before summer planning, a department head asks Microsoft 365 Copilot who still has a lot of leave to take and plans cover around it.
Use the dataddo tools to describe Employees and generate a JSON of Manager UUID to direct report counts for people who are not Terminated.
An internal tools developer uses GitHub Copilot in Agent mode to keep the team directory's reporting lines in sync with Gusto.
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 Copilot 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 | |
|---|---|---|---|
| Agent shared with managers | Managers ask HR for team lists by email, and HR replies with exports that include home addresses and dates of birth. | The Teams agent reads Employees with Hash Sensitive Fields applied, so Home Address Street 1, Date of Birth and SSN arrive as hashes. | Managers get counts, not identities |
| Onboarding follow-up | HR checks each new hire's profile in Gusto to see whether onboarding is complete. | Employees carries Onboarded and Department, so the agent lists everyone still in onboarding across all teams at once. | Open onboarding surfaced |
| Leave planning | Department heads request balance reports from HR and wait for a spreadsheet before planning cover. | Employee Time Off Activities carries Balance, Balance Change and Policy Name, and managers ask the agent directly in Teams. | Self-serve leave balances |
| Token consumption | Copilot 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. Copilot queries them by name through the Dataddo semantic layer.
| Dataset | Metrics and attributes |
Ask Copilot
|
|---|---|---|
| Employees |
|
How many active employees are paid by each Payment Method? |
| Employee Jobs |
|
How does the Rate range for each Title, grouped by Payment Unit? |
| Employee Terminations |
|
For how many terminations did we choose Run Termination Payroll this year? |
| Payrolls |
|
Which payrolls in the window are not yet Processed, and when is their Check Date? |
| Payroll Employee Compensations |
|
How many employee payments per Check Date went out by each Payment Method? |
| Time Off Requests |
|
Which Employee UUID has more than one request whose Status is still pending? |
| Employee Time Off Activities |
|
How much leave was used per Time Off Type in the last quarter, based on Effective Time? |
| Contractor Payments |
|
How much was paid as Payments Reimbursement to contractors per month this year? |
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 Employees, Employee Time Off Activities and Employee Jobs, then attach it to a Copilot destination or AI Model. In Copilot Studio, add a Model Context Protocol tool for https://headless.dataddo.com/mcp-data with OAuth 2.0 Dynamic discovery and publish the agent to Teams and Microsoft 365 Copilot.
Through a Copilot Studio agent. Add Dataddo Data Access as a Model Context Protocol tool with OAuth 2.0 Dynamic discovery, then publish the agent via Channels to Teams and Microsoft Copilot.
From the server description you write in Copilot Studio. State that it holds Gusto employees, jobs and time off, so headcount and leave questions trigger a Dataddo call.
Turn on Hash Sensitive Fields for Employees and Employee Terminations. Names, SSN, Date of Birth, Phone and home address fields are hashed during extraction, so the agent can count and group people without exposing them.
Employee Time Off Activities is extracted per Time Off Type, sick or vacation, chosen when you create the source. Add a second source if you need both.
Yes. Add the Dataddo server to .vscode/mcp.json, start it, sign in and use Copilot Chat in Agent mode. Business and Enterprise orgs must enable MCP servers in Copilot policy.
