Approach · Healthcare · 22 November 2026 · Martijn van Grieken

Smarter rostering in care

Can AI make a roster that works for staff, clients and the organisation? How we approach that question, presented at R’evolutie van zorg 2026.

Kantoor in een zorginstelling met een scherm met een weekrooster en een teal waterfles

In many care organisations a roster is only really fixed once the shift is over. There are too few permanent staff, the flexible pool is used every week, and working hours are one of the reasons people leave. The question that then comes up: can AI help make rosters that work for the support worker, the client and the organisation?

This page describes how we approach that question, worked out in a project with organisations in disability care. Martijn van Grieken presented the approach on 19 November 2026 at the R’evolutie van zorg congress in Apeldoorn.

Three interests in one roster

The support worker wants control over their own roster and to enjoy the work. The client wants support that fits their care needs, their own preferences and the location. The organisation wants a complete roster with less use of the flexible pool and of staff not on the payroll. Those interests can clash, and a good solution starts with having all three at the table.

The shortage often lies in how shifts are distributed

Staff want to schedule themselves. A worked example shows why that alone is not enough when staffing is tight. Ten support workers state their preferences for four shifts that each need four people.

Shift Needed Preferences With planner
Tuesday morning 4 7 4
Wednesday evening 4 5 4
Saturday evening 4 1 4
Sunday morning 4 2 3
Total 16 15 15

Illustrative calculation.

There are almost enough sign-ups, but if everyone chooses for themselves, five places remain open. A planner who distributes the preferences leaves one open and keeps most preferences intact. A Swedish pilot reports that an automated planner met around 81 per cent of nurses’ preferences, without substitute staff (Rönnberg & Larsson, 2010). The answer is therefore self-scheduling with a planner that looks at the whole, and AI can fill that role.

First the foundation, then AI

AI rostering is the application with the most impact, but rarely the first step. What has to be in place beforehand: clear communication about the roster, reliable data and linked systems for care, HR, finance and rostering, and management information on demand and staffing. Without that insight an AI planner has nothing to steer on. Improving communication is usually the quick win you start with. How we work on that foundation with care organisations is described under healthcare.

Six phases, with care practice at the table

We work in six phases, based on CRISP-DM, the process model used for data projects since the late 1990s:

  1. Clarifying the organisational question (Business Understanding). Who should it improve things for, and how do we measure success?
  2. Understanding the data (Data Understanding). What is actually recorded, and does it mean the same everywhere?
  3. Preparing the data (Data Preparation). Care practice checks the meaning; we make the data suitable and secure.
  4. Developing options (Modeling). Only here does AI come into the picture, always alongside the current way of working.
  5. Testing results (Evaluation). Deciding together: continue, adjust or stop.
  6. Use and maintenance (Deployment). Who uses the outcome, and who remains owner when the project team leaves?

The first phase takes four to six weeks and delivers a shared problem definition, success criteria and a plan. More about the process model is described under our approach.

What you can organise as an executive

  • Sharpen the shared question: what should improve, and for whom?
  • Bring practice and external expertise together early.
  • Check whether everyone means the same thing by the same words.
  • Make interests open to discussion and involve the works council early.
  • Organise a small trial, and agree beforehand who carries the follow-up.
  • Work together with other organisations, so that you are in a stronger position towards suppliers.

Discussing your planning question

Bring one planning question to a first conversation. That conversation is without obligation and we aim to respond within one working day.

Discuss your question

Sources

  • Chapman, P. et al. (2000). CRISP-DM 1.0: Step-by-step data mining guide. SPSS Inc.
  • Rönnberg, E. & Larsson, T. (2010). Automating the self-scheduling process of nurses in Swedish healthcare: a pilot study. Health Care Management Science, 13(1), 35–53. doi:10.1007/s10729-009-9107-x

Author: Martijn van Grieken, founder of Twentynext. How we make this. AI wrote the first version of the Dutch original, and a person at Twentynext read and approved it before it went live. This English version was translated with AI. Twentynext is responsible for the content but cannot guarantee that it is accurate or complete. See our disclaimer.

Related articles