Help! How do I go beyond the average with Synthetic Users?
How to move past generic insights with Synthetic Users by changing your research mindset, framing better goals, and probing deeper — just like you would with organic participants.
Getting beyond generic insights when you already have substantial knowledge — is a common problem, even in traditional research with organic participants. The key to overcoming this lies first in a mindset change and second in how we frame the context and research goals for the Synthetic Users.
First. Algorithm aversion is the tendency for people to distrust data or decisions generated by algorithms or synthetic processes, especially when they lack human elements like personal interaction or diversity of perspectives.
When conducting interviews with organic users, each interaction is enriched by the unique personalities, appearances, and insights of different individuals. Discovering commonalities among them feels rewarding because it suggests genuine patterns in behavior that can be generalized. In contrast, with Synthetic Users—lacking the personal rapport and apparent diversity—finding too many commonalities can (and usually is) perceived negatively. Without the contrasting human interaction, data seem less credible —as it doesn’t feel like engaging with distinct individuals. This difference highlights how the perception of diversity and personal connection influences the value placed on common findings in user research.
Second, and because Synthetic Users are not perfect, here are some pointers on how to improve diversity of outputs (if they exist and are statistically relevant).
To make it easier here are some strategies to improve specificity. Remember granularity in your inputs tends to yield more specificity in terms of outputs:
Provide Existing Knowledge: In your research goal, explicitly state what you already know and understand about the industry or customer. This sets a baseline for the synthetic users to build upon.
Ask for Extension: Clearly indicate that you want to extend beyond this established knowledge. For example, "Given what we know about X, Y, and Z, what are some unexpected or less obvious insights about...?"
Focus on Gaps: Identify specific areas where your current knowledge is lacking and direct the research goals towards these gaps.
Use Advanced Research Goals: Utilize more sophisticated research goals, such as asking for contrarian views or exploring edge cases.
Iterative Approach: Use initial findings to inform follow-up questions, diving deeper into interesting or unexpected threads.
Cross-Industry Insights: Ask for comparisons or applications of concepts from other industries to your specific context.
What do leading experts in qualitative research do?
John Creswell and Cheryl Poth, in their book Qualitative Inquiry and Research Design, stress the importance of rich descriptions and constant refinement. They push us to keep questioning and to engage deeply with participants to uncover subtle insights. Applying Creswell’s and Poth’s advice means being ready to adjust your inputs with Synthetic Users, digging deeper into emerging themes.
Kathy Charmaz basically says that data collection and analysis happen together. She encourages researchers to stay open to unexpected findings and let new insights steer the study’s course. When dealing with Synthetic Users, adopting Charmaz’s approach means welcoming surprising responses and letting them guide further inquiry, revealing layers that might otherwise stay hidden.
Michael Quinn Patton, also a leader in qualitative evaluation, underscores the value of purposeful sampling and flexibility. He advises selecting cases rich in information and being adaptable as the research unfolds. With Synthetic Users, this translates to crafting diverse and challenging personas that push you into uncharted territory and make you question your assumptions.
By weaving these expert strategies into your work with Synthetic Users, you move beyond the generic and engage in a deeper exploration of your research questions. The key lies in treating Synthetic Users as dynamic partners — probing, adjusting, and staying open to the unexpected to enrich your understanding and drive insights.
As always, you can schedule a brief call to discuss your specific use cases and get one of our team to tailor these strategies to your needs.
Releated Articles
More articles for you
Synthetic users, an intro
A quick video walkthrough introducing the Synthetic Users platform — covering key navigation and core features for new users getting started.
Introducing Iris
Introducing Iris, Synthetic Users' research agent. A tutorial on how to work alongside Iris to define study parameters, run interviews, and get precisely structured insight reports.
Multi-study planner: plan and run multiple studies with different audiences
PRISMA is Synthetic Users' multi-study planner — a single interface to design, manage, and run multiple studies with different audiences simultaneously, without juggling separate projects.
Enrich your Synthetic Users with your data. RAG tutorial.
Learn how to enrich Synthetic Users with your own data using Retrieval-Augmented Generation (RAG) to make AI participants more context-aware and accurate.
Synthetic Users Leadership Webinar: Mapping the Synthetic Research Industry
Recap of the Synthetic Users Leadership Webinar featuring Wikipedia founder Jimmy Wales — covering the state of AI, synthetic research risks, differentiators, and the road ahead.
Help! How do I go beyond the average with Synthetic Users?
How to move past generic insights with Synthetic Users by changing your research mindset, framing better goals, and probing deeper — just like you would with organic participants.
Features: Knowledge Graph, Cloning Research, Exporting Annotations, Searching inside History...
A roundup of four new Synthetic Users features: Knowledge Graph for visualising interview themes, Research Cloning, Annotation Exporting, and searching inside your research history.
What's new? 4 new features
A look at four new Synthetic Users features: a Research Assistant UI, expanded language support, and more — designed to help teams run better research faster.
Generating, Running and Sharing Synthetic Research. Really?
A step-by-step walkthrough of how to generate your Synthetic User panel, run interviews, and share your research — from setup to insights report
What to do when you feel your Synthetic Users are being too generalist
Three practical steps to get more specific, nuanced insights from Synthetic Users — including how to probe deeper, ask better questions, and when to complement with organic research.
Which interview type should I pick?
A guide to Synthetic Users' three interview types — dynamic script, custom script, and concept testing — and how to choose the right one based on your research goal.
Do annotations matter to researchers?
Why annotations are essential to research — from medieval monks marking manuscripts to modern researchers highlighting insights. How Synthetic Users brings annotation into AI-powered research.
The transition to Continuous Insight and where we excel
A look at four new Synthetic Users features: a Research Assistant UI, expanded language support, and more — designed to help teams run better research faster.
Don’t fall into the: “It’s not real. It’s just programming.“ fallacy.
Why dismissing AI-generated feedback as "just programming" is a mistake. The value of synthetic research lies in the insights it generates — not in the origin of the participant.
Products creating products
A reflection on how AI is transforming product development — and how Synthetic Users fits into a future where products help create better products through real-time synthetic feedback loops.
Synthetic Users: Merging Qualitative and Quantitative Research, in seconds.
How Synthetic Users blurs the line between qualitative and quantitative research — enabling teams to get the depth of qual at the scale and speed of quant, in seconds.