What it is for:A Wizard of Oz test lets you learn whether a service works before you build the technology. You walk away with a list of real user questions, evidence of which ones can be answered simply and which need human judgment, and a clear verdict on your hypothesis.
Who it helps:Teams considering a chatbot, assistant or automated advice who need evidence of what users ask before they fund the technology.
When to use it
You are considering a chatbot, a smart assistant or automated advice and want to know what users will ask.
The technology is expensive or uncertain, and you need evidence before committing budget.
You want to test the content and tone of automated replies before writing rules or training a model.
How to use it
Write the learning question and a hypothesis with a clear threshold.
Build the thinnest visible service, such as a chat window.
Give the hidden wizard a short guide on tone, sources and reply time.
Brief participants carefully, run realistic tasks, and log every question and delay.
Disclose that a person replied, debrief, and decide what to automate.
Tip:Use two wizards if replies are complex: one finds the answer, the other types it.
Credits and sources:Original Tiremesù worksheet and wording. Method credit: J. F. Kelley. Further reading: Nielsen Norman Group https://www.nngroup.com/articles/wizard-of-oz/
Full guide and film:https://www.tiremesu.com/guides/wizard-of-oz-test
