Fewer routine questions
Leave balances, pay dates and policy questions are answered in private from your HR records and handbook, so HR stops answering the same things all day.
People AI Agent
People AI Agent answers employees’ HR questions from your own records and policies, and runs onboarding, offboarding and leave requests across HR, IT and managers. Your HR team handles half the routine requests it used to, and every decision about people stays with a person.
What it means for your business
-
−50%
routine requests to HR
- Before
- HR answered leave balances, pay dates and policy questions one by one.
- With People Agent
- Employees get the answer in private, from your HR records and handbook.
-
Day 1
accounts and equipment ready for new joiners
- Before
- New joiners waited for laptops, accounts and badges during their first week.
- With People Agent
- HR, IT, facilities and payroll steps are coordinated before the first day.
-
24/7
answers for every employee
- Before
- Shift and night staff waited for office hours to ask HR anything.
- With People Agent
- Questions are answered by message at any hour, and sensitive topics go to a person in HR.
What your HR team gets back
New joiners ready on day one
Contracts, accounts, equipment and first-week plans are coordinated with IT, facilities and managers, and leavers are handled with the same care.
Managers decide, without the paperwork
Leave and change requests arrive checked against balances and team calendars, so managers approve in one step and still make every decision.
Hiring that keeps moving
Interviews are scheduled, reminders sent and feedback collected, so recruiters spend their time with candidates and hiring managers.
What it looks like in practice
An employee asks one question. The agent checks the leave balance and company holidays, looks at the team calendar and sends the request to the manager. The manager makes the decision.
EmployeeHow many vacation days do I have left, and can I take 22–26 December?
People AgentYou have 9 days left this year. 22-26 December needs 3 days, because the 24th and 25th are company holidays. Your team calendar shows no conflicts, so I’ve sent the request to your manager.
Looked up
- HR records
- Company policies
- Google Calendar
- Slack
How six companies use the People AI Agent
Each one in short: the problem, the results, and how the agent handles the work.
Sick cover found in 6 minutes, not an hour
Store managers were the switchboard for everything: who can swap a shift, who covers a sick colleague, how many leave days someone has left.
- 1Understands the request
An employee messages "can I swap Saturday with Lea?" or "I'm sick today".
- 2Checks the rules and the rota
It checks hours limits, rest time between shifts, leave balances and how many people are already off.
- 3Prepares the change
For a swap it confirms with the colleague.
- 4Asks the store manager
The manager approves with one click in Teams.
- 71%answered by message
- 6 minto find sick cover
- −80%manager time on the rota
- 100%of changes approved by a person
99% of mandatory certificates in date, up from 86%
Ward managers tracked certificate expiry dates in spreadsheets and chased their teams by email.
- 1Watches the next 90 days
Every night the agent compares certificate expiry dates in the training records with each person's role and ward.
- 2Finds a course on a day off
It checks the rota and offers course dates that fall on the person's days off, so no shift is lost.
- 3Books and records it
When the employee agrees in Teams, the agent books the place, adds it to their Outlook calendar and updates the training record after they pass.
- 4Asks a person when needed
If no date fits, the ward manager gets one message with the options.
- 99%certificates in date
- 0shifts lost to expired certificates
- −70%time spent chasing training
- 1,900questions a month answered
From application to offer in 23 days, not 41
Booking an interview loop meant matching four interviewers' calendars by hand.
- 1Publishes approved job posts
When a role is approved, the agent posts it on LinkedIn and Indeed from the approved template and tells the hiring manager.
- 2Books interview loops
It finds a slot that works for every interviewer in Google Calendar and sends one invitation to the candidate, with the agenda.
- 3Chases feedback and approvals
Interviewers get a short Slack reminder until feedback is in Greenhouse.
- 4Hands over to onboarding
The contract goes out in DocuSign.
- 23 daysfrom application to offer
- 92%feedback within 24 hours
- 9 hsaved per hire
- −40%candidate drop-outs
100% of new joiners inducted before their first shift
Onboarding lived in a paper checklist that travelled between HR, the stores, IT and the shift lead.
- 1Builds each checklist
When a contract is signed, the agent creates the joiner's stations from the template for their role and shift.
- 2Moves people station to station
It tells each team when it's their turn, books the safety induction, and checks the result in training records before the next step.
- 3Keeps the shift lead informed
The shift lead gets one message in Teams with the joiner's start time, buddy and what's still open.
- 4Closes leavers properly
For leavers it collects handover notes, books the return of equipment, prepares final pay and switches off badge and accounts at the end of the last shift.
- 100%inducted before the first shift
- 0active badges after leaving
- −60%HR admin per joiner
- 1 dayto final pay
Employment letters signed in 2 hours, not three days
Letters were copied from old Word files, so wording drifted and details were sometimes wrong.
- 1Confirms who is asking
The employee asks in Teams.
- 2Fills the approved template
It picks the right template and fills in name, role, start date and contract type from the HR system.
- 3Leaves pay sealed
Salary lines stay empty for the agent.
- 4HR signs, the employee receives it
An HR partner reviews and signs in DocuSign.
- 2 hfrom request to signed letter
- 1,400letters a year prepared
- 0salary figures read by the agent
- −85%HR time on letters
180 seasonal joiners onboarded in 3 weeks, not seven
Each spring, two HR people sent out 180 contracts, collected documents and answered the same questions again and again.
- 1Hires in
Approved seasonal roles are posted on Indeed in four languages.
- 2Prepares day one
Each joiner gets a day-one pack on WhatsApp: start time, uniform pick-up, locker number, first rota and the house rules, in their language.
- 3Answers through the summer
Questions about shifts, tip pooling, days off and staff housing are answered from the handbook, any hour.
- 4Closes out the season
Leaving dates are agreed with each hotel manager, final pay and unused leave go to payroll, a reference is prepared, and everyone is asked about next year.
- 3 weeksto onboard 180 joiners
- 86%answered by message at peak
- 100%paid on their last day
- 64%want to come back
Illustrative scenarios with unnamed companies. The figures show the kind of improvement each setup is designed to deliver; actual results depend on volume, the systems connected and how the agent is configured.
From first conversation to live in three to eight weeks
We set up the People AI Agent around how your HR team and managers work today.
-
1
Week 1
Learn your process
We sit with the people who do the work, map the process step by step and find the systems that hold the information. You get a written plan before anything is built.
-
2
Weeks 2 to 3
Customize your agent
We build and configure the agent around your process: your rules, your approvals, your wording, and connections to your databases and the tools your teams use.
-
3
Weeks 3 to 4
Deploy and test with your team
We install it inside your infrastructure, or in our cloud if you prefer, and test it with your team on real requests until the results meet the standard you set.
-
4
From week 5
Onboard your team
We train your employees and administrators, hand over the controls and stay with you: monthly reviews, updates you approve, and the next process when you are ready.
What your team and managers see
People AI Agent: questions from business leaders
How quickly will we see results?
Employees ask real questions within the first weeks. Most companies see fewer routine requests to HR, and smoother onboarding, during the first month after going live.
What does it cost?
It depends on the number of employees, the systems it connects to and where it runs. After a first conversation you get a written proposal with the price, so you can compare it with what routine HR work costs you today.
Will it replace our HR team?
No. It takes over routine questions and coordination, so HR spends its time with the people who need a person. Decisions on leave, pay, hiring and every sensitive case stay with your people.
What if it gives a wrong answer?
It answers only from your HR records and policies, shows the policy it used and passes anything it is unsure about to HR. Every answer and action is recorded, so you can review and correct it.
Can we control what it does?
Yes. You decide which questions it answers alone, which requests it prepares and who approves them. Leave, letters and changes always wait for a manager or HR. You can pause it at any time.
Is personal data safe?
Each employee only sees their own records, and you decide what the agent may read, so salary, health and case notes can be closed to it entirely. It can run on your own servers, together with its AI models, so nothing leaves your company and we have no access.
Do we have to change our HR systems?
No. It works with Personio, Greenhouse and your own HR and payroll systems, and employees ask in Microsoft Teams, Slack or WhatsApp.
What happens with sensitive topics?
The agent recognises topics such as complaints, health or conflicts at work, does not answer them, and opens a private case for a person in HR. It cannot read those cases.
What do you need from our team?
One person from HR who knows your processes, access to test versions of the HR systems involved, and a few hours a week from HR and a few managers while we test.
Can we start small?
Yes. Most companies start with one process, such as leave requests or HR questions, see the results, and then add onboarding, letters or hiring.
See what the People AI Agent can do for your HR team.
Tell us how many employees you have, which requests reach HR most often and how onboarding works today. You get a written proposal with the expected results, the setup, a timeline and a price.