If you're creating your Wondering study using the AI-powered study generator, you'll need to describe what you would like to learn with your study with a prompt.
The Wondering AI-powered study generator is powered by large language models, which means there are specific prompt formats that are especially effective at generating useful studies. Here are a number of tips for how to write prompts that we find generate good studies.
We've found the prompt formats in this article work well for creating studies, but you should feel free to explore prompts that aren't recommended in this guide.
Be clear, concise and direct
When writing a prompt to generate a study on Wondering, try to write clear and concise instructions. Think of Wondering like a research assistant that you're asking to build a study for you, and who has no context on what you want except from what you explicitly tell them in your prompt. The less they have to guess about what you want, the more likely you'll get your study in a format you're happy with.
Be specific, descriptive and as detailed as possible about your desired content, length, style etc
If you have specific requirements in mind for your study, such as the desired length, questions or blocks you'd like to be included or the style and tone of voice of the study, include those details in your prompt.
For example, if you want your study to be no longer than 5 blocks long, include that in your prompt.
Avoid imprecise descriptions
The more precise you are in your descriptions, the better Wondering can create a study that matches your descriptions.
Ask yourself if a colleague would understand how to create a study based on your prompt
When writing your prompts, ask yourself if a colleague could follow the instructions in your prompt and (with enough time) create a good study that you are happy with. If your colleague is likely to be confused, so might the Wondering study builder.
Don't be afraid to test and iterate
The best way to test if a prompt gives you a study you're happy with is to generate a study using the AI-powered study builder in Wondering using your prompt, and then iterating if there's something you'd like to change.
Example use cases and prompts
Measure user satisfaction
Less effective ❌ | Better ✅ |
Make a study about product satisfaction. | Design a user satisfaction study consisting of 10 multiple-choice questions focused on evaluating customer satisfaction with the latest product version. Include questions on product usability, features, and overall satisfaction. The study should conclude with an open-ended question for additional feedback. Please ensure the survey is suitable for online distribution and completion within 5 minutes. |
Assess product usability
Less effective ❌ | Better ✅ |
Check if our product is accessible to everyone. | Organize a comprehensive usability and accessibility audit for our educational software, targeting users with varying abilities including visual and hearing impairments. Collect feedback on ease of use, accessibility barriers encountered, and user satisfaction. |
New product concept testing
Less effective ❌ | Better ✅ |
I want feedback on a concept. | Create a study for assessing whether frequent runners that use the running application Strava to track their fitness, but that do not have a running buddy, would be interested in using a feature that allows them to find a running buddy to run with. Understand their current situation, what motivates them to go running and if they already have tried finding a running buddy. Finally, gather feedback on initial impressions of the concept. |
Evaluate homepage copywriting
Less effective ❌ | Better ✅ |
Test our product copy. | Design a study to evaluate the effectiveness of different marketing copy variations for our new line of athletic wear. The study should compare the impact of three distinct copy styles (emotional, informative, and testimonial) on consumer engagement and purchase intent. Each participant should see each style of copy, followed by questions assessing their reaction, likelihood to purchase. Finally, ask participants to choose which option they prefer overall. |
Understand brand perception
Less effective ❌ | Better ✅ |
What do people think about our brand? | Construct a comprehensive brand perception study to assess how our brand is viewed in comparison to competitors in the fashion sector. Measure brand awareness, loyalty, and perception. Include a section for rating competitors on the same attributes. Ensure the study incorporates Show blocks to assess for brand recognition for competitor products and is designed to be completed in under 10 minutes. |