Ami Payroll
Reviews timekeeping anomalies and explains why this period's pay differs from the last.
Payroll errors are rarely caught before the money reaches the employee's account. The agent reviews timekeeping and the payroll run before the pay date, and explains every difference against the previous period.
Job in hand — here is what the agent does
You handed it over once, above. From there the agent watches the data, runs when a business event happens, does the part you delegated and brings the rest back with its evidence. This is what it has done — and what is still waiting for you.
Done by the agent — nobody had to ask
- Screened time records and shifts for the period
- Flagged time records outside the norm
- Applied pay, allowance and insurance rules
- Compared each element to last period
- Explained the variance person by person
Waiting on you
- Three time records still unconfirmedfor you to review
- Allowance raised outside the rule setfor you to approve
Why is payroll different from last period?
The variance comes from overtime shifts in one department and one newly raised allowance.
Lock the confirmed time records and leave the gaps for me.
Locked the confirmed time records and calculated pay on the current rule set.
The allowance raised outside the rule set is outside what you delegated — noted, waiting for your approval.
Where is the largest variance?
In the department with the most overtime this period. I listed each person with their shift count and the matching amount so you can check it.
Audit log · Ami Payroll · delegated by Payroll Officer
The figures in this example are illustrative. In production the agent creates no numbers — it reads and reorders what your system already holds.
- Reads inside your permissions
- Acts only where you delegated
- Every action leaves a trace
Where you meet the agent
- Right inside the module screenSuggestions appear beside the document you already have open, not in a separate app.
- Ask Ami in plain wordsType or speak, in the same language you already use across the system.
- Runs by itself when there is workFires on a business event and brings the work to you, instead of waiting for you to remember.
Where the agent gets its data
The agent has no data store of its own, syncs nothing outward and keeps no copy. It reads directly on the permissioned data layer the module already runs on — within the exact rights of whoever called it.
- Data leaves the company
- Permissions get rebuilt a second time — and can drift
- Figures lag behind the sync cycle
- Timekeeping and shift data
- Pay, allowance and insurance configuration
- Previous payroll runs
And where does the AI model run?
The diagram above is about where the DATA sits; this is about where the MODEL runs — two different things. Routing follows data sensitivity automatically; you do not pick per task.
See the hybrid AI modelAgents in the same group
Other agents on the same data layer — usually switched on together.
- Ami HiringReads CVs, matches them against the job description, ranks a shortlist and drafts the interview invitation.
- Ami ProjectFlags schedule slip and cost overrun early, and summarises portfolio status for the executive team.
- Ami PerformanceTracks OKRs and KPIs against real operating data and points out where results are drifting from strategy.
- Ami TenderExtracts quantities from tender documents and flags unit-price contradictions across the schedules.
- Ami UtilizationTracks people utilisation and margin per project, and flags a losing project while it can still be fixed.
- Ami HandoverChecks each unit's handover conditions — paperwork, payment stage, inspection — and shows exactly where it is stuck.
What this agent does not do
- It grants itself nothing.The agent pre-fills forms and can write to the system — but only within what you delegated; beyond that it stops at a suggestion.
- There is no data shortcut.The agent sees exactly what the calling account may see — no private connection of its own.
- It never acts anonymously.The log records which agent acted, under whose delegation and who approved — accountability stays with people.
How to switch this agent on
- Your company needs to be running the Human Resources – HRM module — the agent reads that module's own data.
- No separate permission setup: the agent's rights are the rights of whoever calls it.
- Switched on and tuned during rollout, following your existing approval flow.
The exact scope and the order modules are switched on get settled in the demo, against your current setup.
Questions people usually ask
Can the agent change data on its own initiative?+
Not on its own initiative — but it does more than read. The agent pre-fills forms and writes to the system within exactly the scope you delegated to it; anything beyond that stops at a suggestion and waits for someone with authority. Either route, every action lands in the audit log.
What if the agent suggests the wrong thing?+
Every suggestion carries its evidence: which document, which line, and why. The reviewer edits or rejects it before anything is written — and both of those actions leave an audit trail too.
How is this different from a chatbot?+
A chatbot only answers when asked. An agent also takes a job you hand over once, then watches the data on its own, runs when a business event fires, and reports back — that is the half a chatbot never does.
How is this different from an automation flow?+
An automation flow runs the steps it was configured with. An agent reads business data, ranks it by situation and picks what needs doing — within exactly the scope you delegated, and anything needing approval still goes through your existing approver.
Does data leave the company?+
Tasks that touch sensitive data run on Internal AI placed inside your own infrastructure; only non-sensitive tasks use an external model. Routing follows the sensitivity of the data automatically.
See the agents run on your own data.
Book a demo scoped to the modules and industry you actually need.