Create a Winning UX/UI Portfolio: Optimize with AI

Your portfolio is like a friend who can speak  highly of you to any potential employers or   clients. I want to fall in love with how you  present your stuff. These are your technical   tasks. I'm not just looking at your technical  expertise; I'm interested in your journey. The   one thing, in my opinion, that beats empathy is  experience. I want to see the thinking. I'd look   for evidence of them having built components, them  having an understanding of what components are,   and if you can do that, then the world's your  oyster. That's really kind of what I look for. I want to see the thinking process. I want  to see why some decisions were abandoned or  

why some directions were abandoned and what was  chosen instead. I would say, for me, it's not that   important what methodology exactly you're using,  but I would still love to see that, of course. But   the more important part is that you can argue why  you decided to move in that way, and that "why"   should not be based on assumptions, not "because  I felt like" or "because I had a feeling that."

That doesn't go in my book. You need to have some  objective language in use that clearly explains   that this is objectively better. And again, you  can always say, "Well, drop-downs are faster," or   "This is faster." Well, ideally, you would need  to have data to prove that. The more thinking,   the better. I mean, personally, I have sometimes  situations where somebody would just draw a   solution on paper and give it to me, and as long  as I can follow and understand what the process  

was like and why this thing has been chosen,  that's all I need. That's fine; that works for me. If you're looking for a job, most of the time  what you want to convey through your portfolio   is that you've reached the competency levels. To  do that, I would say any kind of project or any   kind of format to show that you've done the work  will work. It could be a fake project; it could be  

a real project. Sometimes it doesn't even have to  be linked to a Figma prototype, because I know we   tend to be very, very obsessed with tooling. For  example, I have someone that I've been mentoring   who had a past experience in video editing.  Something they've been doing is actually working   in a clinical office to enhance the engagement  with patients. To do this, they actually made  

a bunch of videos of the doctors just to feel a  bit more approachable, so it's not just a screen   between the patients and the doctor. To me, that  is user research. This is also understanding the   problem, the creative ideas, and yes, maybe the  outcome is a video and it's not a screen design.   But if he has this project and some UI exercise,  then yes, for me, he'll be able to do UX work. A few things, and I'm trying to answer  this fast, okay. Work on some components,  

even if it's just for your own products. Show  that you have an understanding of what component   design is. Then I would work quite hard on a  couple of aspects, and these are hard skills,   by the way. I'd focus on learning about  typography, spacing, all that good visual   design stuff because it is important in  design systems. And then finally, work   on your writing skills. Being able to communicate  well, especially written communication, is really  

valuable. I'd look for evidence of them having  built components, them having an understanding   of what components are, of what a design system  is. And yeah, just try and read about it. I'm not looking for anything polished; that  is just the end product. I'm interested in   your journey. So it doesn't matter if you're  junior or senior, I want to see your process:   how to go from one step to the other, what is the  problem, how do you approach presenting it in a  

way which is user-facing, how do you write feature  specs, how do you take it to a wireframing state,   how do you create low-fidelity, high-fidelity  user interfaces. Anything you are building   should not be based on an opinion. You  should give me data. You should say,   "I did this because I did competitor benchmarking.  This is what worked in other games. People connect   better with characters, so it was a good way  to introduce that meta feature." But also,   what did you do? Even if you are just a  student, did you build that prototype,   and did you do some kind of mock testing with  another player just to say, "I also tested it  

with somebody who's never used this feature.  This is the feedback I've got." Show me your   process, show me your journey, show me your  objectivity. That is what I want to look at. On a junior level, if you are applying for  mid or senior level, I'm not just looking at   your technical expertise, which I know you  will have. I also want to see soft skills:   how good are you at collaborating, how good  you are at taking criticism and feedback,   how good you are at defending your decisions,  how good you are at taking initiative,   how good you are at aligning your stakeholders.  So my general rule of thumb is everybody who's  

hired needs to be good, including a director,  because I have to get hands-on also many times.   They should have solid or technical skills  with potential, but the higher up you go,   I want to also see more of your soft skills:  leadership, collaboration, and all that stuff. I think the biggest thing is storytelling.  To me, basic skill. That's the beauty of it.  

I think a lot of this stuff is sketching, it's  whiteboarding, it's customer interviewing, it's   being able to speak with a variety of team members  and get them all to a single story that actually   makes sense to the customer. Really being able  to balance opposing viewpoints and say, "Well,   let's make two prototypes. Great, it seems like  we can't come to an agreement. Let's make one like   this and one like this and test it." I've done it  many times in my life, but if you've ever done any  

prototyping or any kind of sketching or ideation,  that is just kind of your basic technique,   just taken to the next level. And with AI, there  are so many Legos for you to play with and so much   opportunity. And if you can do that, then the  world's your oyster. That's really kind of what   I look for: being able to do all these things, but  also facilitate this discussion about how far you   can take it. And of course, everyone's got some  Figma skills. I don't think you need to be a huge  

Figma jockey for this thing. Once you've come up  with the idea, it's just a matter of documenting   using your design system components. Hopefully,  you do have a design system; I hope you do, all right. My advice for portfolios,  whether it's design systems or not,  

is the same. You should tell the story of  the project. So don't think that a design   system project versus a different type of  project has to be structured differently   or has to be structured in a specific way. Focus  on the milestones that happened in that project,   the challenges that you overcame, and what you  delivered, and tell that story. That should help   you to just have a consistent story arc and really  focus on the project dictating the case study,  

not you having to fit every project  into a very cookie-cutter format. In portfolios, if I were to apply for  a job, I would not just be like, "Oh,   I've done this little AR app and I've done  this little VR project," but I would make sure   how it connects to the users and who this was  designed for. One of my projects that I would  

personally lead with if I were to apply for a job  is probably this inclusive gym that I've created.   It was a smaller project for me. It's not in my  main research portfolio, but it allows children   in wheelchairs to exercise and play games with  each other. Actually, from an AR perspective,   it's not particularly technically challenging  or hard, but at least it would demonstrate how   I think about this space and what kinds  of AR and VR solutions I want to create.

Where I see my responsibility. In a design portfolio, I'm a very visual person,  so I want to fall in love with how you present your stuff and with the style,   with your typography. Typography, that's the first thing I see  in the portfolio. If you're not taking good care   of your typography with your character length,  your line height, hierarchy, all that stuff,  

that's already like I'm done with you. I don't  want to see you; I don't want to know anything   about you. Get out of here. No, it's just like,  in the web, everything we do as designers,   a lot of it is text. Most of it is text. So I  look for that care and attention to detail in   a portfolio. That's the first thing I notice,  and actually, it's not because I'm looking for   it. It just instantly pops for me. I see it's  like, "Ooh, ah." It's like, "Ah, you tried. You  

tried. Close." I know it's cruel, but sometimes  if you have a lot of portfolios you're seeing and   you don't have a lot of time, you're just looking  for excuses to close that window. You're looking   for excuses to filter out people. That sounds  cruel, I know, but that's how recruiters work.   They have to filter out people because they may  have a lot of options, and they're just looking  

for excuses. So don't give them that excuse. I'm  going to say something a little bit controversial:   don't write the whole design process, all  that thing like that cookie-cutter template   design process that I'm pretty sure you didn't  even follow. You just reverse-engineered it   and put it there in your portfolio. Tell  me a story. I want to be entertained. I know that sounds now even cliché. It's all about  storytelling, but it really is. We're humans,  

and we just want to gather around the fire and  be told a story before we go to sleep. And in these stories, you can be the hero. All the  challenges that you went through, "Oh man, we   tried this and it didn't work, but that allowed me  to learn, and then I overcame my challenges, and   I became the hero of this story." You can be the  hero of that story. It can be your user. When you  

were doing user testing, you found out something.  Tell that story of that person. It could be maybe   it is actually the company. They were struggling  and they were trying to get to a new market or   something. Tell me that story. I want to be  entertained. We all want to be entertained. If   I'm going to be looking at your portfolio, you  better have good typography and a nice story. Empathy is really, really important, right?  We talk about empathy a lot as user-centered  

designers, as human-centered designers. But the  one thing, in my opinion, that beats empathy is   experience. Portfolio-wise, specifically, I  really want to see a breadth of experience   there. The reason why is that I think more than  anything, if you have worked for startups and also   larger enterprise companies, if you've worked  on mobile products and you've also worked on   desktop products, if you worked for enterprise  systems and consumer-facing products, B2B, B2C,  

that means that you've seen a range of different  needs of the user. And that also means that in   entirety, when you're working on these different  projects and you're consuming the research that   it takes to build these products, you're in a  place where you really understand what the user   needs. So if you have actually experienced what  the business needs and also what the user needs,  

if you've experienced how to toggle between the  two, then I can look at that and I can be like,   "Well, you look like you can learn a  lot." With AI, especially for ethical AI,   what I think needs to be done is that there  needs to be a lot more assessment and quality   on designers that showcase a breadth of learning  and a breadth of implementation of that learning. When I'm interviewing people, or especially  when I'm teaching, what I typically like to  

do is I like to really, really encourage  my students to go in and just explore the   world and explore the ways that they can  implement strategies in different ways,   and also fail. That's a really big part of  being a designer. I don't even consider the   vocabulary of failure as something that I  have in my book because I don't consider   it failure. I just consider it, "Oh, it's a  learning lesson. We just learned something."

Before showing you an end to an AI-powered design process. That still happens under human guidance, which is the key point in this conversation. Let's go quickly over how AI can help us. So for ones that can decrease cognitive load, aid decision making by processing large volumes of data, can help us automate repetitive tasks such as formatting images or resizing text.

It can help us by providing more insights into human behavior and usage patterns. Also, with creating prototypes or mockups, all kinds of visual assets, it can spot usability issues and so on. AI can help us at every step of the design process. Covering our blind spots, augmenting our thinking, making us more efficient if we use it correctly. Here's how an end to end design process augmented by AI may look like. But the key to reading this schema are how I prefer to look at it:

there's always a person orchestrating this. The future in which AI could generate a cohesive, coherent, reliable and relevant design process end to end is a very distant future for now, and there's an impetuous need for someone governing over this process, applying critical thinking and showing intentionality at every stage of the design process. Also, because AI shows multiple limitations

on each of the steps shown in the schema. Nielsen Norman Group published an article unpacking the limits that currently surround the use of AI in research. To understand the context of their analysis. You need to know that there are currently two type of AI powered research tools we currently see on the market: insight generators and collaborators. AI Insight generators. These tools summarize user research sessions based only on the transcripts.

Since they don't accept any kind of additional information (context, past research, background information about the product and users and so on), they can be highly problematic in how they generate and present those summaries. While there are some workarounds like uploading background information as session notes to be added to the analysis, it's not the right framing for the source and it's not going to reflect correctly in the analysis and generation. Humans would be much better at this. The scoping and systems

thinking required to understand the interpretation landscape AI collaborators. These work similar to insight generators, but they're slightly better because they accept some contextual information provided by the researcher. For instance, the researcher might show to the AI some human generated interpretation to train it. The tool can then recommend tags for the thematic analysis of the data in addition to session transcripts, collaborators can also analyze researchers notes

and then create themes and insights based on input from multiple sources. But even though they appear to be a bit better, they're still significantly limited and pose a lot of problems, if not used with the right mindset and caution. The limitations they've identified and expand on in detail are: most AI tools can't process visual input, and the biggest problem with that is no human or AI tool can analyze usability testing sessions by the transcript alone.

Usability testing is a method that inherently relies on observing how the user is interacting with the product. Participants often think-aloud describing what they're doing and thinking. Their words do provide valuable information. However, you should never analyze usability tests based only on what participants say. Transcript-only analysis misses important context in user tests because participants don't verbalize all their actions don't describe every element in the product. Not always have a clear understanding or mental model of the product.

So for now, Nielsen Norman's group recommendation is do not trust AI tools that claim to be able to analyze usability testing sessions by transcripts alone. Future tools able to process video visuals will be much more useful for this method. Another problem is the limited understanding of the context. This remains a major problem. AI insight generators don't yet accept the study goals or research question insights or tags from previous

rounds of research, background information about a product or the user groups, contextual information about each participant, new user versus existing user, the list of tasks or interview questions. There is also a problem with the lack of citation and validation, which raises multiple concerns and problems. The tools aren't able to differentiate between the researchers notes and the actual session transcript. A major ethical concern here. We must always clearly separate our own interpretation or assumptions from what the participants said or did.

Another problem with the lack of citation is that it makes verifying accuracy very difficult. AI systems can sometimes produce information that sounds very plausible, but is actually incorrect. Unstable performance and usability issues are another problem. None of the tools they tested had solid usability or performance. They reported outages, errors and unstable performance in general. And then there's the problem of bias. According to Reva Schwartz and her colleagues, AI systems and applications can involve biases

at three levels: systematic, statistical and computational and human biases. AI must be trained on data which can introduce systematic such as historical and institutional and statistical biases, like a dataset sampling that is unrepresentative enough. When people are using a AI-powered results in decision making they can bring in human biases like anchoring bias. So bias can creep into research efforts on multiple levels,

and these tools don't yet have the mechanisms in place to prevent that. I wanted to discuss the limitations reported in the article in detail, because I believe we can easily extrapolate and expand them beyond just research tools. Most of these problems will be observable on other types of AI companions in the design process. Biases in image generation, limitations in being offered context, other kinds of input limitations, not accepting files or images,

output vagueness, generic results, and so on. So I think that this is a necessary frame to keep in mind when interacting and designing with the help of AI. Tools are not very reliable yet and accurate. So take everything they produce with a grain of salt and apply critical thinking at all times.

Some voices, like Harari, are raising fair  and important concerns about the dangers of AI   and the uncontrolled way in which the industry is evolving at such a rapid pace. However, even AI reluctants talk about the unquestionable benefits that AI can bring to our lives; some of which being: *improving healthcare* – AI can support better diagnosis, identify health problems earlier, with more accuracy.

AI can predict the spread of disease, identify sick patients before they infect others. And it plays a significant role in drug  discovery and pharmaceutical advancements. *Better education* – with the help of AI, everyone can now have their personal learning assistant, one that can adapt learning to match each student's goals, strengths, weaknesses, background, and so on. *Reduce impact on the environment* – AI can help us tackle environmental challenges by

optimizing resource usage, monitoring climate change, and predicting environmental disasters. For example, AI can optimize energy usage in buildings or traffic flow in cities to reduce carbon emissions. *Smarter agriculture* – AI is being used to increase crop yields and optimize farm operations through precision agriculture. This involves using AI and other technologies to monitor crop health, predict weather patterns, and make farming more sustainable. *Safer transportation* – AI plays a significant role in the development of autonomous vehicles

which have the potential to make transportation safer and more efficient. AI can also *optimize logistics and supply chain operations*. And on an *individual level*, which also obviously adds up and expands on a societal level. AI is making us more productive. It can augment our natural capabilities and overall makes us better smarter workers – and thinkers.

While doing all of the positives I've  mentioned, it also creates new businesses, new roles and new type of innovation. Sure, it's also replacing a lot of roles, and that's a fair, legitimate worry in the AI public discourse space. But all industrial and technological revolutions have had similar fears in common. And in the end, the world simply reshifted and rearranged in a new order of opportunities.

The stages of the UX process are  not singular in offering opportunities for enhancing our ways of working. We can also look into automating side process things such as productivity or collaboration. I would personally start with the parts that we're naturally not very good at or the ones we don't enjoy doing. Who  wouldn't be excited to get rid of some of the menial tasks?

So, here are some ideas for using AI  in our design work: Creating icons with Midjourney; generating presentations with tools such as Tome or Beautiful.AI; stock imagery with Midjourney, DALL-E, Stable Diffusion; color palettes with Chroma; writing documentation with Notion AI, writing with Grammarly, and many other options. The landscape of AI tools is rapidly changing. So many new capabilities pop up every week. The best best way to explore ways of optimizing your work is to go to

platforms like Futurepedia and see what's new, play around with the tools, learn and experiment on your own. I choose to set aside 2-3 hours  in my calendar every week, AI playground time, where I simply experiment as much as I can with whatever I stumble upon. It may be something worth trying.

Having a content strategy is the opposite of  designing or writing something at random.    When you have a content strategy, you will study, plan, and  develop the content so that it aligns with your   goals and your target audience. For example, if  you want to be hired in the fintech industry, you   will want to show more of the dashboard work that  you've done or anything done on complex design.