Optimal vs. Maze: Deep User Insights or Surface-Level Design Feedback

There’s not much a parent won’t do to ensure their child has the best chance of succeeding in life. Unsurprisingly, things are much the same in product development. Whether it’s a designer, manager, developer or copywriter, everyone wants to see the product reach its full potential.

‍

Key to a product’s success (even though it’s still not widely practiced) is UX research. Without research focused on learning user pain points and behaviors, development basically happens in the dark. Feeding direct insights from customers and users into the development of a product means teams can flick the light on and make more informed design decisions.

‍

While the benefits of user research are obvious to anyone working in the field, it can be a real challenge to convince others of just how important and useful it is. We thought we’d help.

‍

Define user research

‍

If you want to sell the importance of UX research within your organization, you’ve got to ensure stakeholders have a clear understanding of what user research is and what they stand to gain from backing it.

‍

In general, there are a few key things worth focusing on when you’re trying to explain the benefits of research:

‍

• More informed design decisions: Companies make major design decisions far too often without considering users. User research provides the data needed to make informed decisions.
• Less uncertainty and risk: Similarly, research reduces risk and uncertainty simply by giving companies more clarity around how a particular product or service is used.
• Retention and conversion benefits: Research means you’ll be more aligned with the needs of your customers and prospective customers.

‍

Use the language of the people you’re trying to convince. A capable UX research practice will almost always improve key business metrics, namely sales and retention.

‍

The early stages

‍

When embarking on a project, book in some time early in the process to answer questions, explain your research approach and what you hope to gain from it. Here are some of the key things to go over:

‍

• Your objectives: What are you trying to achieve? This is a good time to cover your research questions.
• Your research methods: Which methods will you be using to carry out your research? Cover the advantages of these methods and the information you’re likely to get from using them.
• Constraints: Do you see any major obstacles? Any issues with resources?
• Provide examples: Nothing shows the value of doing research quite like a case study. If you can’t find an example of research within your own organization, see what you can find online.

‍

Involve others in your research

‍

When trying to convince someone of the validity of what you’re doing, it’s often best to just show them. There are a couple of effective ways you can do this – at a team or individual level and at an organizational level.

‍

We’ll explain the best way to approach this below, but there’s another important reason to bring others into your research. UX research can’t exist in a vacuum – it thrives on integration and collaboration with other teams. Importantly, this also means working with other teams to define the problems they’re trying to solve and the scope of their projects. Once you’ve got an understanding of what they’re trying to achieve, you’ll be in a better position to help them through research.

‍

Educate others on what research is

‍

Education sessions (lunch-and-learns) are one of the best ways to get a particular team or group together and run through the what and why of user research. You can work with them to work out what they’d like to see from you, and how you can help each other.

‍

Tailor what you’re saying to different teams, especially if you’re talking to people with vastly different skill sets. For example, developers and designers are likely to see entirely different value in research.

‍

Collect user insights across the organization

‍

Putting together a comprehensive internal repository focused specifically on user research is another excellent way to grow awareness. It can also help to quantify things that may otherwise fall by the wayside. For example, you can measure the magnitude of certain pain points or observe patterns in feature requests. Using a platform like Notion or Confluence (or even Google Drive if you don’t want a dedicated platform), log all of your study notes, insights and research information that you find useful.

‍

Whenever someone wants to learn more about research within the organization, they’ll be able to find everything easily.

‍

Bring stakeholders along to research sessions

‍

Getting a stakeholder along to a research session (usability tests and user interviews are great starting points) will help to show them the value that face-to-face sessions with users can provide.

‍

To really involve an observer in your UX research, assign them a specific role. Note taker, for example. With a short briefing on best-practices for note taking, they can get a feel for what’s like to do some of the work you do.

‍

You may also want to consider bringing anyone who’s interested along to a research session, even if they’re just there to observe.

‍

Share your findings – consistently

‍

Research is about more than just testing a hypothesis, it’s important to actually take your research back to the people who can action the data.

‍

By sharing your research findings with teams and stakeholders regularly, your organization will start to build up an understanding of the value that ongoing research can provide, meaning getting approval to pursue research in future becomes easier. This is a bit of a chicken and egg situation, but it’s a practice that all researchers need to get into – especially those embedded in large teams or organizations.

‍

Anything else you think is worth mentioning? Let us know in the comments.

‍

Read more

‍

• Selling your design recommendations to clients and colleagues – Guest writer Jeff Tang outlines some of his techniques for presenting UX recommendations and answering objections.
• Quantifying the ROI of UX – Ashlea McKay delves into one of the toughest UX questions to answer: “What do we get for our money?”
• How to lead a UX team – With user-centered design growing in organizations around the world, we’ll need capable leaders to run UX teams.
• How do I explain what UX is? – Ashlea McKay covers how you can explain UX to people who may not necessarily have familiarity with the field.

Beyond Generative AI: A New Paradigm Emerges

‍

‍

The AI landscape is undergoing a profound transformation. While generative AI has captured public imagination with its ability to create content, a new paradigm is quietly revolutionizing how we think about human-computer interaction: Agentic AI.

‍

Unlike traditional software that waits for explicit commands or generative AI focused primarily on content creation, Agentic AI represents a fundamental shift toward truly autonomous systems. These advanced AI agents can independently make decisions, take actions, and solve complex problems with minimal human oversight. Rather than simply responding to prompts, they proactively work toward goals, demonstrating initiative and adaptability that more closely resembles human collaboration than traditional software interaction.

‍

This evolution is already transforming industries across the board:

‍

• In customer service, AI agents handle complex inquiries end-to-end
• In software development, they autonomously debug code and suggest improvements
• In healthcare, they monitor patient data and flag concerning patterns
• In finance, they analyze market trends and execute optimized strategies
• In manufacturing and logistics, they orchestrate complex operations with minimal human intervention

‍

‍

As these autonomous systems become more prevalent, designing exceptional user experiences for them becomes not just important, but essential. The challenge? Traditional UX approaches built around graphical user interfaces and direct manipulation fall short when designing for AI that thinks and acts independently.

‍

‍

‍

The New Interaction Model: From Commands to Collaboration

‍

‍

Interacting with Agentic AI represents a fundamental departure from conventional software experiences. The predictable, structured nature of traditional GUIs—with their buttons, menus, and visual feedback—gives way to something more fluid, conversational, and at times, unpredictable.

‍

The ideal Agentic AI experience feels less like operating a tool and more like collaborating with a capable teammate. This shift demands that UX designers look beyond the visual aspects of interfaces to consider entirely new interaction models that emphasize:

‍

• Natural language as the primary interface
• The AI's ability to take initiative appropriately
• Establishing the right balance of autonomy and human control
• Building and maintaining trust through transparency
• Adapting to individual user preferences over time

‍

‍

The core challenge lies in bridging the gap between users accustomed to direct manipulation of software and the more abstract interactions inherent in systems that can think and act independently. How do we design experiences that harness the power of autonomy while maintaining the user's sense of control and understanding?

‍

‍

‍

Understanding Users in the Age of Autonomous AI

‍

‍

The foundation of effective Agentic AI design begins with deep user understanding. Expectations for these autonomous agents are shaped by prior experiences with traditional AI assistants but require significant recalibration given their increased autonomy and capability.

‍

‍

‍

Essential UX Research Methods for Agentic AI

‍

‍

Several research methodologies prove particularly valuable when designing for autonomous agents:

‍

User Interviews provide rich qualitative insights into perceptions, trust factors, and control preferences. These conversations reveal the nuanced ways users think about AI autonomy—often accepting it readily for low-stakes tasks like calendar management while requiring more oversight for consequential decisions like financial planning.

‍

Usability Testing with Agentic AI prototypes reveals how users react to AI initiative in real-time. Observing these interactions highlights moments where users feel empowered versus instances where they experience discomfort or confusion when the AI acts independently.

‍

Longitudinal Studies track how user perceptions and interaction patterns evolve as the AI learns and adapts to individual preferences. Since Agentic AI improves through use, understanding this relationship over time provides critical design insights.

‍

Ethnographic Research offers contextual understanding of how autonomous agents integrate into users' daily workflows and environments. This immersive approach reveals unmet needs and potential areas of friction that might not emerge in controlled testing environments.

‍

‍

‍

Key Questions to Uncover

‍

Effective research for Agentic AI should focus on several fundamental dimensions:

‍

Perceived Autonomy: How much independence do users expect and desire from AI agents across different contexts? When does autonomy feel helpful versus intrusive?

‍

Trust Factors: What elements contribute to users trusting an AI's decisions and actions? How quickly is trust lost when mistakes occur, and what mechanisms help rebuild it?

‍

Control Mechanisms: What types of controls (pause, override, adjust parameters) do users expect to have over autonomous systems? How can these be implemented without undermining the benefits of autonomy?

‍

Transparency Needs: What level of insight into the AI's reasoning do users require? How can this information be presented effectively without overwhelming them with technical complexity?

‍

The answers to these questions vary significantly across user segments, task types, and domains—making comprehensive research essential for designing effective Agentic AI experiences.

‍

‍

‍

Core UX Principles for Agentic AI Design

‍

‍

Designing for autonomous agents requires a unique set of principles that address their distinct characteristics and challenges:

‍

Clear Communication

‍

Effective Agentic AI interfaces facilitate natural, transparent communication between user and agent. The AI should clearly convey:

‍

• Its capabilities and limitations upfront
• When it's taking action versus gathering information
• Why it's making specific recommendations or decisions
• What information it's using to inform its actions

‍

Just as with human collaboration, clear communication forms the foundation of successful human-AI partnerships.

‍

‍

Robust Feedback Mechanisms

‍

Agentic AI should provide meaningful feedback about its operations and make it easy for users to provide input on its performance. This bidirectional exchange enables:

‍

• Continuous learning and refinement of the agent's behavior
• Adaptation to individual user preferences
• Improved accuracy and usefulness over time

‍

The most effective agents make feedback feel conversational rather than mechanical, encouraging users to shape the AI's behavior through natural interaction.

‍

‍

Thoughtful Error Handling

‍

How an autonomous agent handles mistakes significantly impacts user trust and satisfaction. Effective error handling includes:

‍

• Proactively identifying potential errors before they occur
• Clearly communicating when and why errors happen
• Providing straightforward paths for recovery or human intervention
• Learning from mistakes to prevent recurrence

‍

The ability to gracefully manage errors and learn from them is often what separates exceptional Agentic AI experiences from frustrating ones.

‍

‍

Appropriate User Control

‍

Users need intuitive mechanisms to guide and control autonomous agents, including:

‍

• Setting goals and parameters for the AI to work within
• The ability to pause or stop actions in progress
• Options to override decisions when necessary
• Preferences that persist across sessions

‍

The level of control should adapt to both user expertise and task criticality, offering more granular options for advanced users or high-stakes decisions.

‍

‍

Balanced Transparency

‍

Effective Agentic AI provides appropriate visibility into its reasoning and decision-making processes without overwhelming users. This involves:

‍

• Making the AI's "thinking" visible and understandable
• Explaining data sources and how they influence decisions
• Offering progressive disclosure—basic explanations for casual users, deeper insights for those who want them

‍

Transparency builds trust by demystifying what might otherwise feel like a "black box" of AI decision-making.

‍

‍

Proactive Assistance

‍

Perhaps the most distinctive aspect of Agentic AI is its ability to anticipate needs and take initiative, offering:

‍

• Relevant suggestions based on user context
• Automation of routine tasks without explicit commands
• Timely information that helps users make better decisions

‍

When implemented thoughtfully, this proactive assistance transforms the AI from a passive tool into a true collaborative partner.

‍

‍

Building User Confidence Through Transparency and Explainability

‍

‍

For users to embrace autonomous agents, they need to understand and trust how these systems operate. This requires both transparency (being open about how the system works) and explainability (providing clear reasons for specific decisions).

‍

Several techniques can enhance these critical qualities:

‍

• Feature visualization that shows what the AI is "seeing" or focusing on
• Attribution methods that identify influential factors in decisions
• Counterfactual explanations that illustrate "what if" scenarios
• Natural language explanations that translate complex reasoning into simple terms

‍

From a UX perspective, this means designing interfaces that:

‍

• Clearly indicate when users are interacting with AI versus human systems
• Make complex decisions accessible through visualizations or natural language
• Offer progressive disclosure—basic explanations by default with deeper insights available on demand
• Implement audit trails documenting the AI's actions and reasoning

‍

‍

The goal is to provide the right information at the right time, helping users understand the AI's behavior without drowning them in technical details.

‍

‍

‍

Embracing Iteration and Continuous Testing

‍

The dynamic, learning nature of Agentic AI makes traditional "design once, deploy forever" approaches inadequate. Instead, successful development requires:

‍

Iterative Design Processes

‍

• Starting with minimal viable agents and expanding capabilities based on user feedback
• Incorporating user input at every development stage
• Continuously refining the AI's behavior based on real-world interaction data

‍

Comprehensive Testing Approaches

‍

• A/B testing different AI behaviors with actual users
• Implementing feedback loops for ongoing improvement
• Monitoring key performance indicators related to user satisfaction and task completion
• Testing for edge cases, adversarial inputs, and ethical alignment

‍

Cross-Functional Collaboration

‍

• Breaking down silos between UX designers, AI engineers, and domain experts
• Ensuring technical capabilities align with user needs
• Creating shared understanding of both technical constraints and user expectations

‍

This ongoing cycle of design, testing, and refinement ensures Agentic AI continuously evolves to better serve user needs.

‍

‍

‍

Learning from Real-World Success Stories

‍

Several existing applications offer valuable lessons for designing effective autonomous systems:

‍

Autonomous Vehicles demonstrate the importance of clearly communicating intentions, providing reassurance during operation, and offering intuitive override controls for passengers.

‍

Smart Assistants like Alexa and Google Assistant highlight the value of natural language processing, personalization based on user preferences, and proactive assistance.

‍

Robotic Systems in industrial settings showcase the need for glanceable information, simplified task selection, and workflows that ensure safety in shared human-robot environments.

‍

Healthcare AI emphasizes providing relevant insights to professionals, automating routine tasks to reduce cognitive load, and enhancing patient care through personalized recommendations.

‍

Customer Service AI prioritizes personalized interactions, 24/7 availability, and the ability to handle both simple requests and complex problem-solving.

‍

‍

These successful implementations share several common elements:

‍

• They prioritize transparency about capabilities and limitations
• They provide appropriate user control while maximizing the benefits of autonomy
• They establish clear expectations about what the AI can and cannot do

‍

‍

‍

Shaping the Future of Human-Agent Interaction

‍

Designing user experiences for Agentic AI represents a fundamental shift in how we think about human-computer interaction. The evolution from graphical user interfaces to autonomous agents requires UX professionals to:

‍

• Move beyond traditional design patterns focused on direct manipulation
• Develop new frameworks for building trust in autonomous systems
• Create interaction models that balance AI initiative with user control
• Embrace continuous refinement as both technology and user expectations evolve

‍

‍

The future of UX in this space will likely explore more natural interaction modalities (voice, gesture, mixed reality), increasingly sophisticated personalization, and thoughtful approaches to ethical considerations around AI autonomy.

‍

For UX professionals and AI developers alike, this new frontier offers the opportunity to fundamentally reimagine the relationship between humans and technology—moving from tools we use to partners we collaborate with. By focusing on deep user understanding, transparent design, and iterative improvement, we can create autonomous AI experiences that genuinely enhance human capability rather than simply automating tasks.

‍

The journey has just begun, and how we design these experiences today will shape our relationship with intelligent technology for decades to come.

‍

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. 

‍