Config Copilot
Turn a plain-language request into a plan from a fixed action catalog, visibly fill the real form and wait for Confirm.
Intelligence · Assistance with accountable human control
It prepares the change. Your administrator approves it.
Use permission-scoped AI on the real product screen to plan supported changes, fill approved forms, explain anomalies and assist implementation—without allowing autonomous payroll, leave or configuration decisions.
Illustrative product interaction Grounded in supported product behaviour
Config CopilotIllustrative · human-approved
HR administrator
“Create a late-mark rule for Chennai factory employees.”
Prepared plan
LocationChennai Plant
Employee groupFactory workforce
Grace10 minutes
Third late markHalf day
Effective date01 Oct 2026
No configuration is applied until an authorised administrator confirms.
Reviewed · ready for authorised confirmationWhy this matters to the Head of HR
AI is useful when it reduces repetitive work and improves access to information without becoming an unreviewed decision-maker. The Head of HR needs clear boundaries, traceability and accountable ownership.
Use this page as a product-evaluation path: start with the operating problem, inspect the representative interaction, then verify the exact policy and output in the live product.
AI HR Companion capabilities
Designed around the full operating workflow.
Configure the module around your structures, policies, ownership and approval model—not a generic process diagram.
Setup Assist
Ask about industry, size, state, employment mix, work pattern and overtime, then suggest real configuration masters.
Specialist in-app agents
Use tenant data and current-screen context through role-scoped agents rather than a generic detached chatbot.
Attendance and payroll anomalies
Flag unusual patterns or variance for authorised human investigation.
Reimbursement bill analysis
Use deterministic checks first and AI when confidence is low, keeping the result reviewable.
Implementation coach
Guide the implementation team using the selected tenant’s live configuration context.
Governed model routing
Route tasks through rules, heuristics, local models or more capable models while preserving graceful degradation.
Connected operating workflow
Follow the action from policy to owner to downstream result.
The exact screens differ by module, but the operating principle remains the same: the applicable rule, current owner, status, effective date and history stay visible.
Faster supported configuration Visible human control Earlier anomaly review
AI HR Companion workflow
- Authorised user describes a supported changeOwner, status and history remain visible.
- Copilot prepares the plan and fills the actual formOwner, status and history remain visible.
- Administrator reviews and confirmsOwner, status and history remain visible.
- Action and AI audit context are retainedOwner, status and history remain visible.
Product proof and boundaries
Evaluate the operating behaviour—not only the feature name.
These examples are illustrative product patterns grounded in the supported product material. Use the live product to validate the exact screen, policy and output required for your organisation.
Supported pattern
Visible AI assistance
The real form and proposed action stay visible before human confirmation.
Verify in demo
Authorised user describes a supported change
Use a representative employee, workforce group and effective date. Follow the transaction through owner, status and downstream impact.
Current boundary
Scope honestly before committing.
AI does not autonomously approve leave, run payroll, change configuration or train itself on customer data.
A working view, not a static report
Give the team clear status and exception signals.
The example measures below are illustrative. Definitions and thresholds should be configured around the operating cadence and evidence your team uses.
VisibleReal form completion
MandatoryHuman confirmation
ScopedTenant and role context
GracefulCore HR works without AI
Connected modules
View all modules AI HR Companion works better when its inputs and outputs stay connected.
Policy Configuration
Configure attendance, leave, payroll, approvals, permissions and notifications around the way your organisation actually works, while keeping every policy scoped, dated and reviewable.
ExplorePayroll
Connect effective-dated salary structures, attendance and leave inputs, earnings, deductions, reimbursements, recoveries and statutory calculations in a payroll run that can be reviewed and rolled back before finalisation.
ExplorePeople Analytics
Bring headcount, movement, people cost, attendance, payroll, performance and HR service data into role-based dashboards with consistent definitions and explainable drill-down.
ExplorePerformance & Goals
Govern goals, appraisal calendars, eligibility, review windows, exceptions, calibration, development actions and salary-revision handoff from one effective-dated workforce foundation.
Explore
Questions about implementation
Bring this context into the demo Evaluate AI HR Companion in your policy context.
Use your actual workforce groups, approval paths and edge cases during product evaluation.
Can the AI approve leave, run payroll or change configuration automatically?
No. Those autonomous actions are not claimed. AI can prepare a supported action, but an authorised person must review and confirm it.
Does duoHR train models on customer data?
A self-learning training pipeline using customer data is not currently claimed. AI context is described as tenant- and role-scoped, with logged interactions and bounded actions.
Explore AI HR Companion
See AI HR Companion configured around your organisation.
Bring one representative workflow or current process challenge. The demo will show the operating path, controls and connected outcomes.