March 31, 2025
8

Designing User Experiences for Agentic AI: The Next Frontier

Optimal Workshop

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.

Feature Traditional Software Agentic AI
Predictability High Variable
User Guidance Explicit (buttons, menus) Implicit (inference, proactivity)
Error Handling Error Prevention Error Correction
User Workflow Designed around software Software adapts to workflow
Interaction Model GUI-based Conversational/Multimodal

Method Description Best for Understanding Adaptations for Agentic AI
User Interviews One-on-one discussions to gather in-depth qualitative insights User perceptions, trust factors, control preferences, transparency Focus on autonomy, trust, control; explore nuanced preferences and emotional responses
Surveys Collect quantitative data from a large sample of users Broad trends, common expectations, preferences, concerns Gauge initial reactions, validate qualitative findings across diverse user groups
Usability Testing Observe users performing tasks with prototypes or existing applications Task performance, intuitiveness, efficiency Focus on perceived autonomy, trustworthiness, explainability; longitudinal studies
Ethnographic Studies Observe users in their natural environment to understand real-world context Integration into daily routines, subtle behaviors, unmet needs Understand social and cultural implications, ethical considerations, real-world adoption

Principle Description Importance for Agentic AI
Clear Communication AI agents communicate status, reasoning, intentions understandably Enables users to understand the AI and provide effective input
Feedback Mechanisms Users can provide input on AI performance for continuous learning Allows the AI to adapt to individual preferences and improve over time
Error Handling Graceful strategies help users understand and recover from errors Minimizes user frustration and builds confidence in the system
User Control Users have appropriate mechanisms to guide, adjust, or override AI actions Fosters a sense of agency and trust in the autonomous system
Transparency Visibility into AI reasoning, data, and decision-making processes Builds understanding and trust in the AI's behavior and outputs
Proactive Experiences AI anticipates user needs and offers relevant assistance Enhances efficiency and creates a feeling of a helpful partnership

Publishing date
March 31, 2025
Share this article
Topics

Related articles

min read
The future of UX research: AI's role in analysis and synthesis ✨📝

As artificial intelligence (AI) continues to advance and permeate various industries, the field of user experience (UX) research is no exception. 

At Optimal Workshop, our recent Value of UX report revealed that 68% of UX professionals believe AI will have the greatest impact on analysis and synthesis in the research project lifecycle. In this article, we'll explore the current and potential applications of AI in UXR, its limitations, and how the role of UX researchers may evolve alongside these technological advancements.

How researchers are already using AI 👉📝

AI is already making inroads in UX research, primarily in tasks that involve processing large amounts of data, such as

  • Automated transcription: AI-powered tools can quickly transcribe user interviews and focus group sessions, saving researchers significant time.

  • Sentiment analysis: Machine learning algorithms can analyze text data from surveys or social media to gauge overall user sentiment towards a product or feature.

  • Pattern recognition: AI can help identify recurring themes or issues in large datasets, potentially surfacing insights that might be missed by human researchers.

  • Data visualization: AI-driven tools can create interactive visualizations of complex data sets, making it easier for researchers to communicate findings to stakeholders.

As AI technology continues to evolve, its role in UX research is poised to expand, offering even more sophisticated tools and capabilities. While AI will undoubtedly enhance efficiency and uncover deeper insights, it's important to recognize that human expertise remains crucial in interpreting context, understanding nuanced user needs, and making strategic decisions. 

The future of UX research lies in the synergy between AI's analytical power and human creativity and empathy, promising a new era of user-centered design that is both data-driven and deeply insightful.

The potential for AI to accelerate UXR processes ✨ 🚀

As AI capabilities advance, the potential to accelerate UX research processes grows exponentially. We anticipate AI revolutionizing UXR by enabling rapid synthesis of qualitative data, offering predictive analysis to guide research focus, automating initial reporting, and providing real-time insights during user testing sessions. 

These advancements could dramatically enhance the efficiency and depth of UX research, allowing researchers to process larger datasets, uncover hidden patterns, and generate insights faster than ever before. As we continue to develop our platform, we're exploring ways to harness these AI capabilities, aiming to empower UX professionals with tools that amplify their expertise and drive more impactful, data-driven design decisions.

AI’s good, but it’s not perfect 🤖🤨

While AI shows great promise in accelerating certain aspects of UX research, it's important to recognize its limitations, particularly when it comes to understanding the nuances of human experience. AI may struggle to grasp the full context of user responses, missing subtle cues or cultural nuances that human researchers would pick up on. Moreover, the ability to truly empathize with users and understand their emotional responses is a uniquely human trait that AI cannot fully replicate. These limitations underscore the continued importance of human expertise in UX research, especially when dealing with complex, emotionally-charged user experiences.

Furthermore, the creative problem-solving aspect of UX research remains firmly in the human domain. While AI can identify patterns and trends with remarkable efficiency, the creative leap from insight to innovative solution still requires human ingenuity. UX research often deals with ambiguous or conflicting user feedback, and human researchers are better equipped to navigate these complexities and make nuanced judgment calls. As we move forward, the most effective UX research strategies will likely involve a symbiotic relationship between AI and human researchers, leveraging the strengths of both to create more comprehensive, nuanced, and actionable insights.

Ethical considerations and data privacy concerns 🕵🏼‍♂️✨

As AI becomes more integrated into UX research processes, several ethical considerations come to the forefront. Data security emerges as a paramount concern, with our report highlighting it as a significant factor when adopting new UX research tools. Ensuring the privacy and protection of user data becomes even more critical as AI systems process increasingly sensitive information. Additionally, we must remain vigilant about potential biases in AI algorithms that could skew research results or perpetuate existing inequalities, potentially leading to flawed design decisions that could negatively impact user experiences.

Transparency and informed consent also take on new dimensions in the age of AI-driven UX research. It's crucial to maintain clarity about which insights are derived from AI analysis versus human interpretation, ensuring that stakeholders understand the origins and potential limitations of research findings. As AI capabilities expand, we may need to revisit and refine informed consent processes, ensuring that users fully comprehend how their data might be analyzed by AI systems. These ethical considerations underscore the need for ongoing dialogue and evolving best practices in the UX research community as we navigate the integration of AI into our workflows.

The evolving role of researchers in the age of AI ✨🔮

As AI technologies advance, the role of UX researchers is not being replaced but rather evolving and expanding in crucial ways. Our Value of UX report reveals that while 35% of organizations consider their UXR practice to be "strategic" or "leading," there's significant room for growth. This evolution presents an opportunity for researchers to focus on higher-level strategic thinking and problem-solving, as AI takes on more of the data processing and initial analysis tasks.

The future of UX research lies in a symbiotic relationship between human expertise and AI capabilities. Researchers will need to develop skills in AI collaboration, guiding and interpreting AI-driven analyses to extract meaningful insights. Moreover, they will play a vital role in ensuring the ethical use of AI in research processes and critically evaluating AI-generated insights. As AI becomes more prevalent, UX researchers will be instrumental in bridging the gap between technological capabilities and genuine human needs and experiences.

Democratizing UXR through AI 🌎✨

The integration of AI into UX research processes holds immense potential for democratizing the field, making advanced research techniques more accessible to a broader range of organizations and professionals. Our report indicates that while 68% believe AI will impact analysis and synthesis, only 18% think it will affect co-presenting findings, highlighting the enduring value of human interpretation and communication of insights.

At Optimal Workshop, we're excited about the possibilities AI brings to UX research. We envision a future where AI-powered tools can lower the barriers to entry for conducting comprehensive UX research, allowing smaller teams and organizations to gain deeper insights into their users' needs and behaviors. This democratization could lead to more user-centered products and services across various industries, ultimately benefiting end-users.

However, as we embrace these technological advancements, it's crucial to remember that the core of UX research remains fundamentally human. The unique skills of empathy, contextual understanding, and creative problem-solving that human researchers bring to the table will continue to be invaluable. As we move forward, UX researchers must stay informed about AI advancements, critically evaluate their application in research processes, and continue to advocate for the human-centered approach that is at the heart of our field.

By leveraging AI to handle time-consuming tasks and uncover patterns in large datasets, researchers can focus more on strategic interpretation, ethical considerations, and translating insights into impactful design decisions. This shift not only enhances the value of UX research within organizations but also opens up new possibilities for innovation and user-centric design.

As we continue to develop our platform at Optimal Workshop, we're committed to exploring how AI can complement and amplify human expertise in UX research, always with the goal of creating better user experiences.

The future of UX research is bright, with AI serving as a powerful tool to enhance our capabilities, democratize our practices, and ultimately create more intuitive, efficient, and delightful user experiences for people around the world.

min read
Clara Kliman-Silver: AI & design: imagining the future of UX

In the last few years, the influence of AI has steadily been expanding into various aspects of design. In early 2023, that expansion exploded. AI tools and features are now everywhere, and there are two ways designers commonly react to it:

  • With enthusiasm for how they can use it to make their jobs easier
  • With skepticism over how reliable it is, or even fear that it could replace their jobs

Google UX researcher Clara Kliman-Silver is at the forefront of researching and understanding the potential impact of AI on design into the future. This is a hot topic that’s on the radar of many designers as they grapple with what the new normal is, and how it will change things in the coming years.

Clara’s background 

Clara Kliman-Silver spends her time studying design teams and systems, UX tools and designer-developer collaboration. She’s a specialist in participatory design and uses generative methods to investigate workflows, understand designer-developer experiences, and imagine ways to create UIs. In this work, Clara looks at how technology can be leveraged to help people make things, and do it more efficiently than they currently are.

In today’s context, that puts generative AI and machine learning right in her line of sight. The way this technology has boomed in recent times has many people scrambling to catch up - to identify the biggest opportunities and to understand the risks that come with it. Clara is a leader in assessing the implications of AI. She analyzes both the technology itself and the way people feel about it to forecast what it will mean into the future.

Contact Details:

You can find Clara in LinkedIn or on Twitter @cklimansilver

What role should artificial intelligence play in UX design process? 🤔

Clara’s expertise in understanding the role of AI in design comes from significant research and analysis of how the technology is being used currently and how industry experts feel about it. AI is everywhere in today’s world, from home devices to tech platforms and specific tools for various industries. In many cases, AI automation is used for productivity, where it can speed up processes with subtle, easy to use applications.

As mentioned above, the transformational capabilities of AI are met with equal parts of enthusiasm and skepticism. The way people use AI, and how they feel about it is important, because users need to be comfortable implementing the technology in order for it to make a difference. The question of what value AI brings to the design process is ongoing. On one hand, AI can help increase efficiency for systems and processes. On the other hand, it can exacerbate problems if the user's intentions are misunderstood.

Access for all 🦾

There’s no doubt that AI tools enable novices to perform tasks that, in years gone by, required a high level of expertise. For example, film editing was previously a manual task, where people would literally cut rolls of film and splice them together on a reel. It was something only a trained editor could do. Now, anyone with a smartphone has access to iMovie or a similar app, and they can edit film in seconds.

For film experts, digital technology allows them to speed up tedious tasks and focus on more sophisticated aspects of their work. Clara hypothesizes that AI is particularly valuable when it automates mundane tasks. AI enables more individuals to leverage digital technologies without requiring specialist training. Thus, AI has shifted the landscape of what it means to be an “expert” in a field. Expertise is about more than being able to simply do something - it includes having the knowledge and experience to do it for an informed reason. 

Research and testing 🔬

Clara performs a lot of concept testing, which involves recognizing the perceived value of an approach or method. Concept testing helps in scenarios where a solution may not address a problem or where the real problem is difficult to identify. In a recent survey, Clara describes two predominant benefits designers experienced from AI:

  1. Efficiency. Not only does AI expedite the problem solving process, it can also help efficiently identify problems. 
  2. Innovation. Generative AI can innovate on its own, developing ideas that designers themselves may not have thought of.

The design partnership 🤝🏽

Overall, Clara says UX designers tend to see AI as a creative partner. However, most users don’t yet trust AI enough to give it complete agency over the work it’s used for. The level of trust designers have exists on a continuum, where it depends on the nature of the work and the context of what they’re aiming to accomplish. Other factors such as where the tech comes from, who curated it and who’s training the model also influences trust. For now, AI is largely seen as a valued tool, and there is cautious optimism and tentative acceptance for its application. 

Why it matters 💡

AI presents as potentially one of the biggest game-changers to how people work in our generation. Although AI has widespread applications across sectors and systems, there are still many questions about it. In the design world, systems like DALL-E allow people to create AI-generated imagery, and auto layout in various tools allows designers to iterate more quickly and efficiently.

Like many other industries, designers are wondering where AI might go in the future and what it might look like. The answer to these questions has very real implications for the future of design jobs and whether they will exist. In practice, Clara describes the current mood towards AI as existing on a continuum between adherence and innovation:

  • Adherence is about how AI helps designers follow best practice
  • Innovation is at the other end of the spectrum, and involves using AI to figure out what’s possible

The current environment is extremely subjective, and there’s no agreed best practice. This makes it difficult to recommend a certain approach to adopting AI and creating permanent systems around it. Both the technology and the sentiment around it will evolve through time, and it’s something designers, like all people, will need to maintain good awareness of.

min read
Insights & AI Beta

As part of our beta release, you'll gain access to the newest enhancements to our Qualitative Insights tool (previously known as Reframer).

  1. Insights: A dedicated space to create, organize, and communicate your key takeaways. Create Insights on your own or with AI.
  2. AI capabilities: Optional AI-powered assistance to create Insights from your observations to accelerate your analysis process.

Our new Insights and AI functionality streamlines your qualitative analysis process, allowing you to quickly summarize, create, and organize key takeaways from your data.

Help documentation

  1. How AI Insights clustering works in Optimal
  2. Create an Insight with and without AI
  3. How AI generated Insights work in Optimal
  4. Our AI guiding principles
  5. How to set your preferences for AI
  6. Analyzing & sharing your Insights
  7. Learn more about Qualitative Insights

Notes on AI Privacy & Security


Optimal uses AWS Amazon Bedrock, which is the fully managed service that makes large language models (LLMs) from Amazon and leading AI startups available through an API, for AI generation for Qualitative Insights.


Amazon Bedrock meets industry-leading standards for compliance, including: ISO, SOC, CSA STAR Level 2, GDPR, and HIPAA eligible. Learn more about Amazon Bedrock.

We take your privacy seriously. When you use AI Insights: 

  1. Your data stays within your organization
  2. We don't use it to train other AI models
  3. You control when to use AI for insights
  4. AI features can be turned on or off anytime

Questions & feedback

If you have any questions, please reach out to our support team via live chat.

We appreciate any feedback you have on improving your experience and invite you to share your thoughts through this feedback form at anytime. Our product team will also be in touch mid-late October to to gather further insights about your experience.

Seeing is believing

Explore our tools and see how Optimal makes gathering insights simple, powerful, and impactful.