Vittori

Magma Design System

Iconsauce

Let's Connect

Interested in collaborating or learning more about my work in UX design and design systems?

LinkedIn

GitHub

Resume

The texts in this portfolio were written with the support of language models—Claude (Anthropic), Gemini (Google), and ChatGPT (OpenAI)—from project documentation, personal notes, and materials produced throughout my career. The content is based on globally recognized design principles—including those of the Nielsen Norman Group, Material Design, and established practices around design systems like those of Brad Frost and Nathan Curtis—refined in light of my direct experience. This approach reflects my interest in the conscious integration of AI tools into the design process, where technology augments thought without replacing it.

No tracking. No ads. Just static HTML.
This site respects your privacy by design.

Human-Centered AI Design

Designing transparent, predictable AI experiences following Microsoft HAX guidelines

Related references and bibliography

potentially outdated

Books

Jeremy Mendel — The Effect of Interface Consistency and Cognitive Load on User Performance in an Information Search Task

Although interface consistency is theorized to increase performance and user satisfaction, previous research has found mixed and often non-significant results. The source of this discrepancy may be due to varying levels of task difficulty employed in these past studies.

https://open.clemson.edu/cgi/viewcontent.cgi?article=2052&context=all_theses

Yvonne Earnshaw, Andrew A. Tawfik, & Matthew Schmidt — User Experience Design

The principles of HCI and UCD have implications for the design of learning environments. While the LIDT field has historically focused on learning theories to guide design.

https://open.byu.edu/lidtfoundations/user_experience_design

Articles & Posts

Adam Fard — Explainable AI: Ensuring Design Decisions are Transparent and Accountable

Explainable AI (XAI) is an evolving field that seeks to demystify the inner workings of artificial intelligence models. In essence, XAI aims to make AI decisions transparent and understandable to humans. This is particularly crucial in design, where decisions can significantly impact user experiences and business outcomes.

https://adamfard.com/blog/explainable-ai

Agentic Design — Human-in-the-Loop

Strategic integration of human judgment at critical decision points in AI workflows

https://agentic-design.ai/patterns/ui-ux-patterns/human-in-the-loop

Alexa Steinbrück — Daring more raw AI-ness, a critique of personified voice assistants

Personality and gender in voice assistants is not something that emerges due to the nature of “AI systems”. Rather, it is intentionally created based on the logic of market demand, gender biases, and prevalent unrealistic narratives about AI.

https://uxdesign.cc/daring-more-raw-ai-ness-a-critique-of-personified-voice-assistants-a700ec8cc7fe

Anshad Ameenza — Meaningful Control: Preserving Human Agency in an AI-Driven World

How we can maintain meaningful human control and decision-making power as AI systems become increasingly capable, and why agency preservation may be the defining challenge of the AI revolution.

https://anshadameenza.com/blog/technology/preserving-human-agency-ai-era

Bernardo Palos — Creating AI that adapts to user context and goals

Designing AI systems that adapt to user context and goals is crucial to ensuring that AI tools are truly useful and intuitive.

https://palospublishing.com/creating-ai-that-adapts-to-user-context-and-goals/

Bernardo Palos — Designing for recovery and forgiveness after AI mistakes

When designing AI systems, one of the essential yet often overlooked factors is how these systems can support recovery and forgiveness when they make mistakes.

https://palospublishing.com/designing-for-recovery-and-forgiveness-after-ai-mistakes/

Bernardo Palos — Designing interfaces that let users disagree with AI

When designing AI interfaces, creating spaces where users can easily and effectively disagree with the AI is essential for fostering trust, maintaining control, and ensuring user autonomy.

https://palospublishing.com/designing-interfaces-that-let-users-disagree-with-ai/

Chai — Building Trust in AI Systems: Key Principles for Ethical and Reliable AI

Artificial Intelligence (AI) is rapidly transforming industries, offering unprecedented opportunities for innovation and efficiency.

https://www.chaione.com/blog/building-trust-in-ai-systems

Christian Crowley — Agency by design: Preserving user control in a post-interface world

For decades, new layers of abstraction have defined how users interact with technology. Programming languages abstracted away machine code. The command line gave way to the graphical user interface, then to the mobile app and the API. Each shift abstracted more complexity away from the user — but left the human firmly in the loop.

https://a16zcrypto.com/posts/article/preserving-user-control-ai-agents/

Chudi Nnorukam — Progressive Disclosure: Reduce AI Token Usage by 60%

I was burning through $50/month in Claude API costs before I realized the problem. Every session loaded the same 8,000 tokens of context--rules, skills, examples--whether I needed them or not.

https://dev.to/chudi_nnorukam/progressive-disclosure-reduce-ai-token-usage-by-60-4ad7

Cobbai — Transparent AI in Customer Service: Building Trust with Customers

AI transparency customer service is becoming a critical focus as businesses integrate artificial intelligence into their support channels. Customers expect clarity about how AI tools collect, use, and interpret their data during interactions.

https://www.screamingbox.net/blog/designing-ai-interfaces-users-can-trust-how-transparency-ux-and-explainability-build-confidence

Cristian Pineda — Designing for AI Errors: Turning Mistakes into User-Friendly Solutions

Learn key techniques for identifying, addressing, and resolving AI errors while maintaining a user-centered approach. Includes a hands-on Figjam workshop for practical application.

https://www.uxsidequest.com/p/designing-for-ai-errors-turning-mistakes

Darren Yeo — How to be the designer in the AI Loop

Exploring the evolving relationship between humans and AI in product design

https://uxdesign.cc/how-to-be-the-designer-in-the-ai-loop-e14a5fb8c375

Eduard Kuric — Human-Centered Design Through AI-Assisted Usability Testing: Reality Or Fiction?

Could AI assist UX researchers by dynamically asking follow-up questions based on participant responses? Eduard Kuric discusses the significance of context in the creation of relevant follow-up questions for unmoderated usability testing, how an AI tasked with interactive follow-up should be validated, and the potential — along with the risks — of AI interaction in usability testing.

https://www.smashingmagazine.com/2025/02/human-centered-design-ai-assisted-usability-testing/

Erin Young — The Human Side of AI: Control and Choice

Users want control, especially when it comes to new tech. After all, AI is not about replacing humans, but enhancing their capabilities.

https://slideux.com/blog/the-human-side-of-ai-control-and-choice

Honra — Progressive Disclosure for AI Agents: Why Less Context Means Smarter Systems

As organizations race to build AI systems that can reason, plan, and act autonomously, they’re discovering a counterintuitive truth: agents get dumber when you give them too much information upfront.

https://www.honra.ai/articles/progressive-disclosure-for-ai-agents

Jakob Nielsen — Embrace AI’s Uncertainty in UX

AI’s probabilistic nature changes all areas of user experience, impacting users, UX researchers, and designers. This article presents strategies for mitigating the downsides of AI uncertainty while leveraging its potential for creativity.

https://jakobnielsenphd.substack.com/p/ai-uncertainty-ux

Jakob Nielsen — UX must alleviate the cognitive burden of time

Next-generation AI-UX design must deliver human handoff harmony, with seamless transitions between machine execution and user cognition that recognize people’s limited mental processing budgets across different time periods. Includes 23 UX design patterns that support cognitive latency.

https://jakobnielsenphd.substack.com/p/think-time-ux

Jeremy Werner — Building Trust in AI: The Role of Transparency and Accountability

In today’s digital landscape, artificial intelligence (AI) is revolutionizing industries and transforming the way businesses operate. However, with the growing adoption of AI comes an increased need for transparency and accountability.

https://babl.ai/building-trust-in-ai-the-role-of-transparency-and-accountability/

Katarzyna Łanecka — Achieve better UX and design usability by reducing cognitive load

This blog explains how minimizing cognitive load and burnout improves user experience and design usability faster.

https://design.kellton.com/achieve-better-ux

Kateryna Mayka — AI Transparency Through Design: 5 Practical Lessons from the Field

AI transparency isn’t just about algorithms — it’s about design. This article explores five practical lessons from Eleken designer Julia Haievska’s work on the AI marketing platform Aampe, showing how thoughtful UX decisions make AI systems more understandable, reliable, and ethical. You’ll learn how to visualize AI behavior, guide users through complexity, build trust through communication, support learning by doing, and adapt transparency as your product evolves.

https://www.eleken.co/blog-posts/ai-transparency#what-is-ai-transparency-and-why-does-it-matter

Lennart Ziburski — Artificial Intelligence shapes how we think, feel and behave. It drives the decisions that define our future.

We have the responsibility to use this potential for humane technology. Building an AI based on our diverse values and needs requires thoughtful design.

https://uxofai.com/

Magnus Eriksen — Designing AI User Interfaces That Foster Trust and Transparency

We need transparency and ethical design choices to create experiences that clearly show how algorithms work, how systems handle data, and how AIs make decisions—all while addressing concerns such as users’ skepticism, fear of automation, and privacy needs.

https://www.uxmatters.com/mt/archives/2025/04/designing-ai-user-interfaces-that-foster-trust-and-transparency.php

Microsoft — Guideline 10: Scope services when in doubt

Engage in disambiguation or gracefully degrade the AI system’s services when uncertain about a user’s goals.

https://www.microsoft.com/en-us/haxtoolkit/guideline/scope-services-when-in-doubt/

Nitin Agarwal — AI UX Design: Creating Transparency & Trust in AI Products

Ever felt frustrated using an AI product that feels like a black box? You’re not alone. Users crave clarity—knowing why an AI makes certain decisions builds confidence and trust.

https://www.wildnetedge.com/blogs/ai-ux-design-creating-transparency-trust-in-ai-products

Nitin Agarwal — Human-Centered Design for AI: Enhancing UX of ML and Transparency

Ever felt frustrated interacting with AI that just doesn’t get you? If AI interfaces confuse more than help, it’s often because they lack a human touch. That’s where Human-Centered Design for AI comes in. By focusing on real people’s needs and experiences, we can radically improve AI’s UX of ML, boost transparency, and tackle bias handling head-on. Ready to transform your AI interfaces? Let’s dive deep into what makes HCD essential for AI success.

https://www.wildnetedge.com/blogs/human-centered-design-for-ai-enhancing-ux-of-ml-and-transparency

Page Laubheimer — AI Hallucinations: What Designers Need to Know

Plausible but incorrect AI responses create design challenges and user distrust. Discover evidence-based UI patterns to help users identify fabrications.

https://www.nngroup.com/articles/ai-hallucinations/

Pair with Google — Provide paths forward from failure

Show users what steps to take to get back on track

https://pair.withgoogle.com/guidebook/chapters/errors-and-graceful-failures/provide-paths-forward-from-failure

Pavel Samsonov — AI Chatbots Discourage Error Checking

AI hallucinations threaten the usefulness of LLM-generated text in professional environments, but today’s LLMs encourage users to take outputs at face value.

https://www.nngroup.com/articles/ai-chatbots-discourage-error-checking/

Raimund Laqua — Breaking the Illusion: The Case Against Anthropomorphizing AI Systems

Artificial intelligence (AI) has become increasingly prevalent in our lives, and as we interact more and more with these systems, it's tempting to anthropomorphize them, or attribute human-like characteristics to them.

https://www.leancompliance.ca/post/breaking-the-illusion-the-case-against-anthropomorphizing-ai-systems

Robin Dhanwani — Designing for AI Transparency and Trust: Guide (2026)

Explore design strategies to promote AI transparency and trust, ensuring users understand and trust AI decisions.

https://www.parallelhq.com/blog/designing-ai-transparency-trust

Sean Brennan — Human-in-the-Loop Design: When AI Needs a Teammate

Great AI doesn't always mean full automation. Learn how to design workflows where humans intervene at the right time for quality, ethics, or trust.

https://seanbrennan.com.au/blog/human-in-the-loop/

Sukashish Kaur — Designing UX for AI Errors: How to Handle Failures the Right Way

Artificial Intelligence (AI) has quickly evolved from a niche technology to a ubiquitous part of our digital lives. Whether you’re asking Alexa about the weather, receiving recommendations on Netflix, or relying on AI-powered tools in healthcare or finance, AI is making decisions or suggestions on your behalf. But what happens when AI gets it wrong?

https://f1studioz.com/blog/designing-ux-for-ai-errors-how-to-handle-failures-the-right-way/

Scientific Papers

Darren Yeo — AI assistance in enterprise UX design workflows: enhancing design brief creation for designers

The study explores the impact of AI tools on the daily tasks of designers in corporate environments, with a focus on the creation and evaluation processes of design briefs. Given ChatGPT’s advanced natural language processing capabilities and its potential to meet the complex communication and analysis needs of design work, this tool was selected to investigate its application in designers’ workflows.

https://pmc.ncbi.nlm.nih.gov/articles/PMC11588748/

Jovana Davidovic — On the purpose of meaningful human control of AI

Meaningful human control over AI is exalted as a key tool for assuring safety, dignity, and responsibility for AI and automated decision-systems.

https://pmc.ncbi.nlm.nih.gov/articles/PMC9868906/#s2

Lior Fink, Leorre Newman, Uriel Haran — Let me decide: Increasing user autonomy increases recommendation acceptance

The use of algorithm assistance for decision making is vastly increasing in recent years, largely in online settings wherein users receive advice from recommendation systems.

https://www.sciencedirect.com/science/article/abs/pii/S0747563224001122?dgcid=rss_sd_all#bib56

Maria Luce Lupetti, Evgeni Aizenberg, Niek Beckers, Arkady Zgonnikov, Herman Veluwenkamp, David Abbink, Elisa Giaccardi, Geert-Jan Houben, Catholijn M. Jonker, Jeroen van den Hoven, Deborah Forster, Reginald L. Lagendijk — Meaningful human control over ai systems: Beyond talking the talk

How can humans remain in control of artificial intelligence (AI)-based systems designed to have autonomous capabilities? Such systems are increasingly ubiquitous, creating benefits - but also undesirable situations where moral responsibility for their actions cannot be properly attributed to any particular person or group.

https://arxiv.org/pdf/2112.01298v1

P. Jonathon Phillips, Carina A. Hahn, Peter C. Fontana, Amy N. Yates, Kristen Greene, David A. Broniatowski, Mark A. Przybocki — Four Principles of Explainable Artificial Intelligence

We introduce four principles for explainable artificial intelligence (AI) that comprise fundamental properties for explainable AI systems. We propose that explainable AI systems deliver accompanying evidence or reasons for outcomes and processes; provide explanations that are understandable to individual users; provide explanations that correctly reflect the system’s process for generating the output; and that a system only operates under conditions for which it was designed and when it reaches sufficient confidence in its output.

https://nvlpubs.nist.gov/nistpubs/ir/2021/NIST.IR.8312.pdf

Q. Vera Liao, Jennifer Wortman Vaughan — AI Transparency in the Age of LLMs: A Human-Centered Research Roadmap

The rise of powerful large language models (LLMs) brings about tremendous opportunities for innovation but also looming risks for individuals and society at large.

https://hdsr.mitpress.mit.edu/pub/aelql9qy/release/2

Q. Vera Liao, S. Shyam Sundar — Designing for Responsible Trust in AI Systems: A Communication Perspective

With the popularity of complex AI systems used to augment or automate tasks that can affect many people’s lives and have a long-lasting impact, trust is often cited as a key requirement for people to adopt AI technologies.

https://arxiv.org/pdf/2204.13828

Xinye Tang, Haijun Zhai, Chaitanya Belwal, Vineeth Thayanithi, Philip Baumann, Yogesh K Roy — Dynamic Context-Aware Prompt Recommendation for Domain-Specific AI Applications

https://arxiv.org/html/2506.20815v1

Yingwei (Wayne) Xu, Christina G. Chi, Dogan Gursoy, Ruiying (Raine) Cai — Rethinking AI anthropomorphism: A holistic conceptualization and scale across AI systems and service contexts

Building on Gestalt theory, this research introduces a holistic framework for defining artificial intelligence (AI) anthropomorphism, which guides the development of a parsimonious Scale of AI Anthropomorphism (SAIA).

https://www.sciencedirect.com/science/article/pii/S0160791X25003793