New to Create using AI? Read how to create forms and surveys using AI first to see how to use it. This post explains what happens behind the scenes.
Writing a question is not the same as building it
When a creator uses Create using AI, the AI drafts the wording of each question. A survey needs more than wording. Each question also needs an answer type: a short text box, a long comment box, a single choice, checkboxes, a rating, an email field, a date and so on.
That choice matters to the people who answer. "What could we do better?" needs room to write. "How satisfied are you with our service?" works best as a rating. "Select all the features you use" needs checkboxes. The right type is decided by what the question asks for, not by which words it happens to contain.
So after the questions are drafted, the builder shows "Detecting question types..." and picks a type for each one from its wording alone. This post is about how that choice is made.
Step 1: Simple rules for obvious questions
Some questions are plain requests for one field, such as "What is your email?" or "Date of birth". A rule can settle those at once, with no model call. The rules only fire when the whole question is a standard request for that one field. A keyword alone is not enough, because "What is your email?" and "How often do you check your email?" both contain the word email, and they need different answer types.
Everything else goes to the second step.
Step 2: The decision model reads the rest
We use a decision model, JEV. We give it some text and a typed question, and it answers with a choice. It does not write text. For each remaining question we ask it one thing: which answer type is the best way to collect the respondent's answer to this question? It chooses from 41 types.
Why a decision model. This is classification with fixed labels, which is what a Choice question is built for. The model has to understand what a question asks for, then pick one type from a list. We give each type a short description, and the descriptions are where the hard judgment calls are written down:
- A number type is for one typed numeric value, such as an age in years. When a question names groups or ranges to pick from, like an age group, it is a choice.
- A date type is for one calendar date. "Which date works best?" offers dates to choose between, so it is a choice.
Types whose names already say everything, such as email, phone number, website or signature, go to the model as names only. That keeps each request small.
Rules settle the obvious. The decision model reads the rest. The creator never picks a type by hand.
The model's top answer is the type the question gets.
Six questions, two steps
We ran these six questions through the real type picker. One was settled by a rule, and five went to the decision model in one request.
| Question | Type picked | Settled by |
|---|---|---|
| What is your email address? | Rule | |
| How often do you check your email? | multiple choice | Decision model |
| Which age group do you belong to? | multiple choice | Decision model |
| How satisfied are you with our service? | number rating | Decision model |
| What could we do better? | long comment box | Decision model |
| Select all the features you use | checkboxes | Decision model |
Look at the pair. "What is your email address?" becomes an email field, while "How often do you check your email?" becomes a choice. The words overlap, but what each question asks for does not.
Many questions, few requests
A survey has many questions, and the creator is waiting on the screen. So the model does not get one request per question. The questions are grouped, and each group is one request with one typed question per survey question. Several groups run at the same time.
Rules run first, so questions they settle never reach the model at all. Only the wording of the survey's own questions is sent to pick a type. No respondent data is involved, because the survey has not been answered yet.
Get insights.
Unlock value.
- 14-day free trial
- Set up in minutes
- End-to-end encrypted
