That kind of calendar AI will end up double-booking.

That does indeed happen in tests when the AI is allowed to book itself across multiple calendars. That’s why the AI only suggests, books into one system calendar, states the time zone explicitly and a person confirms.

Rostering is never one-size-fits-all: collective agreement, preferences, experience.

Exactly why the system makes the proposal and you make the decision. The rules (contract hours, rest periods, collective agreement) are built in; the human judgement isn’t. Swapping via the app saves the Sunday evening.

The works council has to consent to this.

True, for rostering arrangements and anything that measures performance. We put it to them beforehand, with what the system does and does not record.

Our planner becomes redundant.

The planner becomes the conductor: exceptions, swap requests that don’t fit, busy periods nobody saw coming. The Sunday-evening ring-round does disappear. Honestly: fewer hours on planning, more on people.

Surely I don’t need to build this for one event a year?

No. For one event a year, existing tools like Eventbrite and Mailchimp are enough; we help you tie them together. Building only pays off for recurring gatherings, customer days or training sessions.

Feature · Planning, scheduling & events

Knowledge workers are interrupted every two minutes. The roster gets fixed on WhatsApp on Sunday evening. There is a smarter way.

Planning is the department nobody has and everybody does: the office manager, the team leader, the owner on Sunday evening. Rosters, appointments, meetings, minutes, the annual event. All of it work that consists of back-and-forth: emails, messages, lists. AI and automation take the back-and-forth out. The choices remain yours.

// A feature at a fictional care and services provider with 35 employees on rotating shifts, an office manager who “does the diary”, two locations and a customer day in October. The company is fictional, the situations are real: we run into them again and again.

Book an intro call Take the free AI scan

Sound familiar?

The roster gets fixed on WhatsApp every Sunday evening; swap requests in private chats.
“Just a quick meeting with five people”: one in four employees loses three to four hours a week to it.
More than half of all meetings are ad hoc, without an invitation or a purpose.
Minutes: someone types along and emails them three days later; half the room does not know what the next step is.
Project planning in an Excel sheet nobody updates; “who has hours next week?” goes round by email.
The event that has three people doing emails and lists for two weeks; dietary requirements in a second Excel sheet.
The customer who does not show up because nobody sent a reminder.
Two calendars (Outlook and Google) and the time-zone mistake with the foreign supplier.

What usually runs here

The software we come across here most often. It does not have to go; we build around it and in between.

Microsoft 365 Outlook, Teams, BookingsGoogle Workspace calendar and mailCalendly / Doodle appointments, date pollsShiftbase / L1NDA / Planday rostersEitje / Werktijden.nl rosters for hospitality and retailAsana / Monday / Trello tasks and projectsJira / Notion projects and documentationSimplicate / Teamleader projects, hours, capacityEventbrite / Weeztix registration and ticketsMailchimp invitationsTeams Copilot / Fireflies / tl;dv minutes

// the same working day, twice

A day in planning, scheduling & events: now and next

On the left, the day as it usually runs now. On the right, the same day once the dull parts are automated and AI does the groundwork. Watch what changes: not the people, but where their time goes.

// how it goes nowWithout AI

07:45Team leaderOn Sunday evening the roster was “done”. Monday morning two sick-leave reports on WhatsApp. Calls three colleagues. Two don’t pick up.
09:00Office managerScheduling a meeting with five people: third round of emails. Thursday 15:00, unless someone turns out not to be able to make it after all.
10:30TeamAd-hoc meeting of an hour without an agenda. At the end: “okay, we’ll come back to that.”
12:00Office managerCustomer day in six weeks: 140 invitations by email, registrations in Excel, dietary requirements in a second tab, payments separately.
14:00Project leadEmails the whole team: “who still has hours next week?” Four replies, two don’t match the calendar.
15:30Office managerTypes up the minutes from this morning. Finished at 17:15, sent on Thursday.
16:30PlanningA customer did not show up. Nobody had sent a reminder. An hour lost.

// how it will goWith AI and automation

07:45Team leaderThe two sick-leave reports came in via the app. The system suggests three colleagues who are available and stay within their hours; two accept via the app. Done by 08:05.
09:00Office managerThe calendar assistant finds three times when all five can make it; she picks one and the invitation, with purpose and agenda, is in the calendar.
10:30TeamThe meeting has a purpose and three points. At the end the decisions and actions are in the task system, with an owner and a date.
12:00Office managerCustomer day: one flow. Invitation, registration, payment, dietary requirements, badges and reminders come from the same system. She only monitors the exceptions.
14:00Project leadCapacity per person is live: hours, leave, projects. Next week there are 26 hours free, and it shows who has them.
15:30Office managerThe AI summary of the meeting was there at 11:35. She read it, corrected two sentences and sent it. Done by 11:45.
16:30PlanningThe customer automatically got a reminder yesterday with a button to reschedule. Arrived on time.

Where AI makes the difference here

Per use case: what the automation does, what a person keeps doing, and whether it is proven or still promising. We say which one honestly.

01proven

Rosters that draft themselves

Draft roster from availability, contract hours, busy periods and collective agreement rules; swapping and reporting sick in the app; the system suggests replacements.

Still human: approves the roster and decides in case of conflicts.

Working more efficiently Handling more with fewer people

02proven

Appointments without email rounds

The calendar assistant suggests times from linked calendars; customers and candidates pick a slot themselves; reminders go out automatically.

Still human: confirms; one calendar is the single source of truth.

Saving time

03proven

Meetings with a decision

Every invitation gets a purpose and an agenda; AI minutes as a draft with decisions and actions that go to the task system.

Still human: checks the summary; recordings only with notice and an opt-out.

Working more efficiently

04proven

Capacity without asking around

Hours, leave and projects in one view: who has room when, what is getting stuck.

Still human: distributes the work.

Handling more with fewer people

05proven

Events as one flow

Invitation, registration, payment, badges, dietary requirements, reminders and follow-up from one system; AI writes the emails and answers standard questions.

Still human: decides on the programme and the guest list.

Saving time Handling more with fewer people

06promising

Fully autonomous calendar AI

Assistants that book on their own across multiple calendars still miss appointments and double-book in tests. We let AI suggest, not book.

Still human: clicks confirm.

Saving time

72%

of meetings are ineffective; 78% of knowledge workers have too many of them to get their work done. [1]

4× faster

catching up on a missed meeting with an AI summary: 11 instead of 43 minutes. [2]

7 in 10

employers cannot get their staffing sorted. [3]

Honestly: what AI does not do here

AI only makes a pointless meeting pointless faster. Without a purpose and an agenda no tool helps; that’s why it starts with the invitation.
AI minutes get about 80% of the content right. That’s a draft, not a register of decisions. A person reads them before they count.
Recording meetings is only allowed with notice beforehand and the option to say no; third-party note-taking bots that listen in uninvited aren’t something we deploy.
Rosters and systems that measure performance require the consent of the works council. We arrange that before we build.

The objections we hear — and whether we can close them off

We looked them up and heard them from clients. For each objection we say whether it is really solvable, partly solvable, or a risk that stays and that you accept knowingly.

Can it be closed off: yes. Rightly so if it happens secretly. With us: notice at the start, an opt-out for anyone who wants it, your own tool hosted in the EU with a short retention period, and the summary goes to the participants, not to a supplier.

// how we start, the first thirty days

01Week 1: core session with planners, the office manager and a team leader; we follow one roster week, one meeting and one event from start to finish.
02Weeks 1 and 2: one master calendar with booking links and automatic reminders; meeting invitations with a purpose.
03Weeks 2 and 3: roster app with swapping, reporting sick and replacement suggestions; works council consent arranged.
04Weeks 3 and 4: AI minutes as a draft with actions to the task system; capacity overview from hours and leave.
05Week 4: measure. Hours spent on rostering, no-shows, turnaround time of minutes. Only then the events flow.

// what it costs and how it works

First the free AI scan, then a core session on your floor (a half-day of 4 hours, €596 excl. VAT and travel costs) with a core report and an honest go/no-go. We build on a project basis with fixed hours: €110 per hour for straightforward work, €165 for complex development.

More hours only with your written approval. If we cannot deliver, you pay nothing for what was not delivered.

AI assistants & agents Process automation Custom software & integrations

Want to know what this means for your planning, scheduling & events?

Take the free AI scan or book an intro call with someone who builds it themselves. A reply within one working day, no slides, no obligations.