Praktijk De Luwte, a fictional example.
Praktijk De Luwte is a fictional organisation (mental health · psychology & psychotherapy) that Zorgvorm built to show how such a website works, for visitors and for the team. The organisation, its people and its data do not exist; the website really works.
A complete website for a two-location mental health group practice: an intake guide that never asks about symptoms, a waiting-times map per location and diagnosis group, and a cover guide per insurer. Behind it, a waiting-list dashboard with intake decisions made by people, four-weekly check-ins and the mandatory NZa publication as a by-product of the list.
The problem behind this example.
A complete website for a two-location mental health group practice: an intake guide that never asks about symptoms, a waiting-times map per location and diagnosis group, and a cover guide per insurer. Behind it, a waiting-list dashboard with intake decisions made by people, four-weekly check-ins and the mandatory NZa publication as a by-product of the list.
Two sides of the same website.
What a visitor does arrives on the team side. Try both; all data is fictional and stays in your browser.
As a visitor
- Intake guide: route, wait and checklist, without symptom questions
- Waiting times per location and diagnosis group, with the Treeknorm
- Cover guide per insurer: contracted or not
On the team side: Registrations & waiting list
- Completeness check · intake decision by a clinician
- Check-in every four weeks · draft ready
- Anxiety · Noord: 9 → 8 weeks · updated today
Fixed rules, and where AI helps.
What runs on fixed, explainable rules, and where a language model takes part. Wherever AI is involved, the result says so.
Fixed rules
Waiting times are calculated from the waiting list itself, in whole weeks per location and diagnosis group; the intake and cover guides run on fixed rules and never ask about symptoms.
With a language model
A clearly labelled AI assistant answers practical questions only from the practice’s own texts; crisis-like questions never go to AI but show 113, the GP and 112 at once.
Choices for privacy.
- Everything you enter in this example website stays in your own browser. Nothing goes to a real organisation.
- Where a language model is involved, the result says so. It gives no medical advice and does not decide who receives care.
- For a real application we agree beforehand which data is needed, who processes it and under which data processing agreement.
What this means for your organisation.
What this means for your organisation depends on where things get stuck today. In an introduction we look at which part of this example would save you the most work, and what it would take to make it work with your own texts and systems.