Moderated vs unmoderated research: which approach is best?

Introduction

‍

User Experience (UX) research has always been about people. How they think, how they behave, what they need, and—just as importantly—what they don’t yet realise they need. Traditional UX methodologies have long relied on direct human input: interviews, usability testing, surveys, and behavioral observation. The assumption was clear—if you want to understand people, you have to engage with real humans.

‍

But in 2025, that assumption is being challenged.

‍

The emergence of digital twins and synthetic users—AI-powered simulations of human behavior—is changing how researchers approach user insights. These technologies claim to solve persistent UX research problems: slow participant recruitment, small sample sizes, high costs, and research timelines that struggle to keep pace with product development. The promise is enticing: instantly accessible, infinitely scalable users who can test, interact, and generate feedback without the logistical headaches of working with real participants.

‍

Yet, as with any new technology, there are trade-offs. While digital twins may unlock efficiencies, they also raise important questions: Can they truly replicate human complexity? Where do they fit within existing research practices? What risks do they introduce?

‍

This article explores the evolving role of digital twins in UX research—where they excel, where they fall short, and what their rise means for the future of human-centered design.

‍

‍

The Traditional UX Research Model: Why Change?

‍

For decades, UX research has been grounded in methodologies that involve direct human participation. The core methods—usability testing, user interviews, ethnographic research, and behavioral analytics—have been refined to account for the unpredictability of human nature.

‍

This approach works well, but it has challenges:

‍

1. Participant recruitment is time-consuming. Finding the right users—especially niche audiences—can be a logistical hurdle, often requiring specialised panels, incentives, and scheduling gymnastics.
   ‍
2. Research is expensive. Incentives, moderation, analysis, and recruitment all add to the cost. A single usability study can run into tens of thousands of dollars.
   ‍
3. Small sample sizes create risk. Budget and timeline constraints often mean testing with small groups, leaving room for blind spots and bias.
   ‍
4. Long feedback loops slow decision-making. By the time research is completed, product teams may have already moved on, limiting its impact.

‍

In short: traditional UX research provides depth and authenticity, but it’s not always fast or scalable.

‍

Digital twins and synthetic users aim to change that.

‍

‍

What Are Digital Twins and Synthetic Users?

‍

While the terms digital twins and synthetic users are sometimes used interchangeably, they are distinct concepts.

‍

Digital Twins: Simulating Real-World Behavior

‍

A digital twin is a data-driven virtual representation of a real-world entity. Originally developed for industrial applications, digital twins replicate machines, environments, and human behavior in a digital space. They can be updated in real time using live data, allowing organisations to analyse scenarios, predict outcomes, and optimise performance.

‍

In UX research, human digital twins attempt to replicate real users' behavioral patterns, decision-making processes, and interactions. They draw on existing datasets to mirror real-world users dynamically, adapting based on real-time inputs.

‍

‍

Synthetic Users: AI-Generated Research Participants

‍

While a digital twin is a mirror of a real entity, a synthetic user is a fabricated research participant—a simulation that mimics human decision-making, behaviors, and responses. These AI-generated personas can be used in research scenarios to interact with products, answer questions, and simulate user journeys.

‍

Unlike traditional user personas (which are static profiles based on aggregated research), synthetic users are interactive and capable of generating dynamic feedback. They aren’t modeled after a specific real-world person, but rather a combination of user behaviors drawn from large datasets.

‍

Think of it this way:

‍

• A digital twin is a highly detailed, data-driven clone of a specific person, customer segment, or process.
• A synthetic user is a fictional but realistic simulation of a potential user, generated based on behavioral patterns and demographic characteristics.

‍

Both approaches are still evolving, but their potential applications in UX research are already taking shape.

‍

‍

Where Digital Twins and Synthetic Users Fit into UX Research

‍

‍

The appeal of AI-generated users is undeniable. They can:

‍

• Scale instantly – Test designs with thousands of simulated users, rather than just a handful of real participants.
• Eliminate recruitment bottlenecks – No need to chase down participants or schedule interviews.
• Reduce costs – No incentives, no travel, no last-minute no-shows.
• Enable rapid iteration – Get user insights in real time and adjust designs on the fly.
• Generate insights on sensitive topics – Synthetic users can explore scenarios that real participants might find too personal or intrusive.

‍

‍

These capabilities make digital twins particularly useful for:

‍

• Early-stage concept validation – Rapidly test ideas before committing to development.
• Edge case identification – Run simulations to explore rare but critical user scenarios.
• Pre-testing before live usability sessions – Identify glaring issues before investing in human research.

‍

However, digital twins and synthetic users are not a replacement for human research. Their effectiveness is limited in areas where emotional, cultural, and contextual factors play a major role.

‍

‍

The Risks and Limitations of AI-Driven UX Research

‍

For all their promise, digital twins and synthetic users introduce new challenges.

‍

1. They lack genuine emotional responses.
   AI can analyse sentiment, but it doesn’t feel frustration, delight, or confusion the way a human does. UX is often about unexpected moments—the frustrations, workarounds, and “aha” realisations that define real-world use.
   ‍
2. Bias is a real problem.
   AI models are trained on existing datasets, meaning they inherit and amplify biases in those datasets. If synthetic users are based on an incomplete or non-diverse dataset, the research insights they generate will be skewed.
   ‍
3. They struggle with novelty.
   Humans are unpredictable. They find unexpected uses for products, misunderstand instructions, and behave irrationally. AI models, no matter how advanced, can only predict behavior based on past patterns—not the unexpected ways real users might engage with a product.
   ‍
4. They require careful validation.
   How do we know that insights from digital twins align with real-world user behavior? Without rigorous validation against human data, there’s a risk of over-reliance on synthetic feedback that doesn’t reflect reality.

‍

‍

A Hybrid Future: AI + Human UX Research

‍

Rather than viewing digital twins as a replacement for human research, the best UX teams will integrate them as a complementary tool.

‍

Where AI Can Lead:

‍

• Large-scale pattern identification
• Early-stage usability evaluations
• Speeding up research cycles
• Automating repetitive testing

‍

Where Humans Remain Essential:

‍

• Understanding emotion, frustration, and delight
• Detecting unexpected behaviors
• Validating insights with real-world context
• Ethical considerations and cultural nuance

‍

The future of UX research is not about choosing between AI and human research—it’s about blending the strengths of both.

‍

‍

Final Thoughts: Proceeding With Caution and Curiosity

‍

Digital twins and synthetic users are exciting, but they are not a magic bullet. They cannot fully replace human users, and relying on them exclusively could lead to false confidence in flawed insights.

‍

Instead, UX researchers should view these technologies as powerful, but imperfect tools—best used in combination with traditional research methods.

‍

As with any new technology, thoughtful implementation is key. The real opportunity lies in designing research methodologies that harness the speed and scale of AI without losing the depth, nuance, and humanity that make UX research truly valuable.

‍

The challenge ahead isn’t about choosing between human or synthetic research. It’s about finding the right balance—one that keeps user experience truly human-centered, even in an AI-driven world.

‍

This article was researched with the help of Perplexity.ai. 

‍

Hi, I’m Martin. I work as a UX researcher at Trade Me having left Optimal Experience (Optimal Workshop's sister company) last year. For those of you who don’t know, Trade Me is New Zealand’s largest online auction site that also lists real estate to buy and rent, cars to buy, jobs listings, travel accommodation and quite a few other things besides. Over three quarters of the population are members and about three quarters of the Internet traffic for New Zealand sites goes to the sites we run.

‍

Leaving a medium-sized consultancy and joining Trade Me has been a big change in many ways, but in others not so much, as I hadn’t expected to find myself operating in a small team of in-house consultants. The approach the team is taking is proving to be pretty effective, so I thought I’d share some of the details of the way we work with the readers of Optimal Workshop’s blog. Let me explain what I mean…

‍

What agile at Trade Me looks like

‍

Over the last year or so, Trade Me has moved all of its development teams over to Agile following a model pioneered by Spotify. All of the software engineering parts of the business have been ‘squadified’. These people produce the websites & apps or provide and support the infrastructure that makes everything possible.Across Squads, there are common job roles in ‘Chapters’ (like designers or testers) and because people are not easy to force into boxes, and why should they be, there are interest groups called ‘Guilds’.The squads are self-organizing, running their own processes and procedures to get to where they need to. In practice, this means they use as many or as few of the Kanban, Scrum, and Rapid tools they find useful. Over time, we’ve seen that squads tend to follow similar practices as they learn from each other.

‍

How our UX team fits in

‍

Our UX team of three sits outside the squads, but we work with them and with the product owners across the business.How does this work? It might seem counter-intuitive to have UX outside of the tightly-integrated, highly-focused squads, sometimes working with product owners working on stuff that might have little to do with what’s being currently developed in the squads. This comes down to the way Trade Me divides down the UX responsibilities within the organization. Within each squad there is a designer. He or she is responsible for how that feature or app looks, and, more importantly, how it acts — interaction design as well as visual design.Then what do we do, if we are the UX team?

‍

We represent the voice of Trade Me’s users

‍

By conducting research with Trade Me’s users we can validate the squads’ day-to-day decisions, and help frame decisions on future plans. We do this by wearing two hats. Wearing the pointy hats of structured, detailed researchers, we look into long-term trends: the detailed behaviours and goals of our different audiences. We’ve conducted lots of one-on-one interviews with hundreds of people, including top sellers, motor parts buyers, and job seekers, as well as running surveys, focus groups and user testing sessions of future-looking prototypes. For example, we recently spent time with a number of buyers and sellers, seeking to understand their motivations and getting under their skin to find out how they perceive Trade Me.

‍

This kind of research enables Trade Me to anticipate and respond to changes in user perception and satisfaction.Swapping hats to an agile beanie (and stretching the metaphor to breaking point), we react to the medium-term, short-term and very short-term needs of the squads testing their ideas, near-finished work and finished work with users, as well as sometimes simply answering questions and providing opinion, based upon our research. Sometimes this means that we can be testing something in the afternoon having only heard we are needed in the morning. This might sound impossible to accommodate, but the pace of change at Trade Me is such that stuff is getting deployed pretty much every day, many of which affects our users directly. It’s our job to ensure that we support our colleagues to do the very best we can for our users.

‍

How our ‘drop everything’ approach works in practice

‍

‍

We recently conducted five or six rounds (no one can quite remember, we did it so quickly) of testing of our new iPhone application (pictured above) — sometimes testing more than one version at a time. The development team would receive our feedback face-to-face, make changes and we’d be testing the next version of the app the same or the next day. It’s only by doing this that we can ensure that Trade Me members will see positive changes happening daily rather than monthly.

‍

How we prioritize what needs to get done

‍

To help us try to decide what we should be doing at any one time we have some simple rules to prioritise:

• Core product over other business elements
• Finish something over start something new
• Committed work over non-committed work
• Strategic priorities over non-strategic priorities
• Responsive support over less time-critical work
• Where our input is crucial over where our input is a bonus

‍

Applying these rules to any situation makes the decision whether to jump in and help pretty easy.At any one time, each of us in the UX team will have one or more long-term projects, some medium-term projects, and either some short-term projects or the capacity for some short-term projects (usually achieved by putting aside a long-term project for a moment).

‍

We manage our time and projects on Trello, where we can see at a glance what’s happening this and next week, and what we’ve caught sniff of in the wind that might be coming up, or definitely is coming up.On the whole, both we and the squads favour fast response, bulleted list, email ‘reports’ for any short-term requests for user testing.  We get a report out within four hours of testing (usually well within that). After all, the squads are working in short sprints, and our involvement is often at the sharp end where delays are not welcome. Most people aren’t going to read past the management summary anyway, so why not just write that, unless you have to?

‍

How we share our knowledge with the organization

Even though we mainly keep our reporting brief, we want the knowledge we’ve gained from working with each squad or on each product to be available to everyone. So we maintain a wiki that contains summaries of what we did for each piece of work, why we did it and what we found. Detailed reports, if there are any, are attached. We also send all reports out to staff who’ve subscribed to the UX interest email group.

‍

Finally, we send out a monthly email, which looks across a bunch of research we’ve conducted, both short and long-term, and draws conclusions from which our colleagues can learn. All of these latter activities contribute to one of our key objectives: making Trade Me an even more user-centred organization than it is.I’ve been with Trade Me for about six months and we’re constantly refining our UX practices, but so far it seems to be working very well.Right, I’d better go – I’ve just been told I’m user testing something pretty big tomorrow and I need to write a test script!

Knowing and understanding why and how your users use your product can be invaluable for getting to the nitty gritty of usability. Where they get stuck and where they fly through. Delving deep with probing questions into motivation or skimming over looking for issues can equally be informative.

‍

Usability testing can be done in several ways, each way has its benefits. Put super simply, usability testing literally is testing how useable your product is for your users. If your product isn't useable users will not stick around or very often complete their task, let alone come back for more.

‍

‍

What is usability testing?

‍

Usability testing is a research method used to evaluate how easy something is to use by testing it with representative users.

‍

These tests typically involve observing a participant as they work through a series of tasks involving the product being tested. Having conducted several usability tests, you can analyze your observations to identify the most common issues.

‍

We go into the three main methods of usability testing:

1. Moderated and unmoderated
2. Remote or in person
3. Explorative, assessment or comparative

‍

‍

1. Moderated or unmoderated usability testing

‍

Moderated usability testing

Moderated usability testing is done in-person or remotely by a researcher who introduces the test to participants, answers their queries, and asks follow-up questions. Often these tests are done in real time with participants and can involve other research stakeholders. Moderated testing usually produces more in-depth results thanks to the direct interaction between researchers and test participants. However, this can be expensive to organize and run.

‍

Top tip: Use moderated testing to investigate the reasoning behind user behavior.

‍

Unmoderated usability testing

‍
Unmoderated usability testing is done without direct supervision; likely participants are in their own homes and/or using their own devices to browse the website that is being tested. And often at their own pace.  The cost of unmoderated testing is lower, though participant answers can remain superficial and making follow-up questions can be difficult.

‍

Top tip: Use unmoderated testing to test a very specific question or observe and measure behavior patterns.

‍

‍

2. Research or in-person usability testing

‍

Remote usability testing

‍
‍Remote usability testing is done over the internet or by phone. Allowing the participants to have the time and space to work in their own environment and at their own pace. This however doesn’t give the researcher much in the way of contextual data because you’re unable to ask questions around intention or probe deeper if the participant makes a particular decision. Remote testing doesn’t go as deep into a participant’s reasoning, but it allows you to test large numbers of people in different geographical areas using fewer resources.

‍

Top tip: Use remote testing when a large group of participants are needed and the questions asked can be direct and unambiguous.

‍

In-person usability testing

‍
‍In-person usability testing, as the name suggests, is done in the presence of a researcher. In-person testing does provide contextual data as researchers can observe and analyze body language and facial expressions. You’re also often able to converse with participants and find out more about why they do something. However, in-person testing can be expensive and time-consuming: you have to find a suitable space, block out a specific date, and recruit (and often pay) participants.

‍

Top tip: In-person testing gives researchers more time and insight into motivation for decisions.

‍

‍

3. Explorative, Assessment or comparative testing

‍

These three usability testing methods generate different types of information:

‍

Explorative testing

‍
‍Explorative testing is open-ended. Participants are asked to brainstorm, give opinions, and express emotional impressions about ideas and concepts. The information is typically collected in the early stages of product development and helps researchers pinpoint gaps in the market, identify potential new features, and workshop new ideas.

‍

Assessment research

‍
‍Assessment research is used to test a user's satisfaction with a product and how well they are able to use it. It's used to evaluate general functionality.

‍

Comparative research

‍
‍Comparative research methods involve asking users to choose which of two solutions they prefer, and they may be used to compare a product with its competitors.

‍

Top tip: Depending on what research is being done, and how much qualitative or quantitative data is wanted.

‍

‍

Which method is right for you?

‍

Whether the testing is done in-person, remote, moderated or unmoderated will depend on your purpose, what you want out of the testing, and to some extent your budget. 

‍

Depending on what you are testing, each of the usability testing methods we explored here can offer an answer. If you are at the development stage of a product it can be useful to conduct a usability test on the entire product. Checking the intuitive usability of your website, to ensure users can make the best decisions, quickly. Or adding, changing or upgrading a product can also be the moment to check on a specific question around usability. Planning and understanding your objectives are key to selecting the right usability testing option for your project.

‍

Let's take a look at a couple of examples of usability testing.

‍

‍

1. Lab based, in-person moderated testing - mid-life website

‍

Imagine you have a website that sells sports equipment. Over time your site has become cluttered and disorganized, much like a bricks and mortar store may. You’ve noticed a drop in sales in certain areas. How do you find out what is going wrong or where users are getting lost? Having an in-person, lab (or other controlled environment), moderated usability test with users you can set tasks, watch (and record) what they do.

‍

The researcher can literally be standing or sitting next to the participant throughout, recording contextual information such as how they interacted with the mouse, laptop or even the seat. Watching for cues as to the comfort of the participant and asking questions about why they make decisions can provide richer insights. Maybe they wanted purple yoga pants, but couldn’t find the ‘yoga’ section which was listed under gym rather than a clothing section.

‍

Meaning you can look at how your stock is organised, or even investigate undertaking a card sort. This provides robust and fully rounded feedback on users behaviours, expectations and experiences. Providing data that can directly be turned into actionable directives when redeveloping the website. 

‍

‍

2. Remote, moderated assessment testing - app product development

‍

You are looking at launching an app for parents to access for information and updates for the school. It’s still in development stage and at this point you want to know how easy the app is to use. Setting some very specific set tasks for participants to complete the app can be sent to them and they can be left to complete (or not). Providing feedback and comments around the usability.

‍

The next step may be to use first click testing to see how and where the interface is clicked and where participants may be spending time, or becoming lost. Whilst the feedback and data gathered from this testing can be light, it will be very direct to the questions asked. And will provide data to back up (or possibly not) what assumptions were made.

‍

‍

3. Moderated, In-person, explorative testing - new product development

‍

You’re right at the start of the development process. The idea is new and fresh and the basics are being considered. What better way to get an understanding of what your users’ truly want than an explorative study.

‍

Open-ended questions with participants in a one-on-one environment (or possibly in groups) can provide rich data and insights for the development team. Imagine you have an exciting new promotional app that you are developing for a client. There are similar apps on the market but none as exciting as what your team has dreamt up. By putting it (and possibly the competitors) to participants they can give direct feedback on what they like, love and loathe.

‍

They can also help brainstorm ideas or better ways to make the app work, or improve the interface. All of this done, before there is money sunk in development.

‍

‍

Usability testing summary: When to use each method (and why)

‍

Key objectives will dictate which usability testing method will deliver the answers to your questions.

‍

Whether it’s in-person, remote, moderated or comparative with a bit of planning you can gather data around your users very real experience of your product. Identify issues, successes and failures. Addressing your user experience with real data, and knowledge can but lead to a more intuitive product.