Prism is a cutting-edge generative AI tool designed to help you explore and understand survey data. By combining demographic information with survey comments, Prism enables deeper insights through its ability to compare multiple demographics and their combinations.
However, it's important to remember that Prism's AI is here to assist you in exploring your data, not to provide definitive answers. Asking thoughtful, well-phrased questions and iterating on them is key to unlocking the full potential of Prism.
Note:📍The results from one summary to another, as well as the recommended actions, may vary because Prism is not deterministic. This means that it generates responses based on patterns and probabilities, rather than following a fixed set of rules or outcomes.
As a result, even with the same input, Prism might produce different outputs each time, reflecting slight variations in how it interprets and processes the data.
This inherent flexibility allows the AI to provide diverse perspectives but also means that results can differ across sessions or prompts.
Understanding Prism’s Chat Feature
The chat interface is designed for exploration and questioning. Think of it as an assistant helping you navigate your data and uncover insights by refining your queries.
Key principles:
AI as exploration, not Determination:
Prism summaries and chat provide guidance based on patterns in your data but does not make final decisions. It’s a tool for generating insights, not conclusions.The importance of phrasing:
The way you phrase your question matters. Specific, clear, and focused queries lead to better results.Iterative Process:
Prism thrives on refinement. If the response doesn’t fully meet your needs, try rephrasing or breaking your question into smaller parts for clarity.
Asking effective questions
Here’s how to craft questions that help you uncover meaningful insights:
1. Focus on demographic comparisons
Prism can compare data across multiple demographics or combinations of them.
Examples:
"How do comments about leadership style differ between employees aged 30–40 and those aged over 50?"
"What themes are mentioned most by women in marketing compared to men in the same department?"
2. Use combinations of demographics
Dive deeper by layering multiple demographics to uncover intersectional insights.
Examples:
"Compare mentions of work-life balance across age group, length of service, and gender."
"What themes are mentioned most by employees under 30 with less than two years of service, compared to those over 40 with more than five years?"
3. Experiment with phrasing
If your first question doesn’t yield the desired result, reframe it.
Original Question: "What do employees think about leadership?"
Rephrased questions
"What themes about leadership emerge in comments from employees in IT?"
"How does sentiment about leadership vary between departments?"
4. Ask follow-up questions
Build on Prism’s responses by diving deeper into specific areas.
Example Workflow:
"What are the most mentioned themes in the comments from employees in sales?"
"How does sentiment on career growth in sales compare between men and women?"
Practical tips for using Prism
Start broad, then narrow: Begin with general questions to identify trends, then refine your focus to specific themes or demographics.
Be patient and persistent: AI responses improve with rephrasing and repeated attempts. Treat it as a collaborative process.
Check for clarity: Ensure your question specifies the demographic or theme of interest. Vague queries lead to less precise insights.
Conclusion
Prism’s true power lies in its ability to guide you through complex data by exploring questions and uncovering hidden insights. By asking thoughtful questions, refining your phrasing, and leveraging demographic comparisons, you can make the most of Prism’s capabilities to drive meaningful, data-informed decisions.