AI for UX: Getting Started

By admin
Summary: Use generative-AI tools to support and enhance your UX skills — not to replace them. Start with small UX tasks and watch out for hallucinations and bad advice.


Jakob
PERSON

recently wrote that the

UX
ORG

field needs to urgently engage with AI. This is partly because usability improvements are sorely needed for current

AI
ORG

tools but just as much because UX work can be vastly improved through the appropriate use of AI.

Luckily, many members of the

UX
ORG

community agree and have asked us how to use AI in UX work.

Kate
PERSON

turned the question around and asked her LinkedIn followers what they would recommend for UXers who have not used AI in their work until now. The post received

more than 40
CARDINAL

responses with good advice, and this article is based on this crowdsourced wisdom combined with our own experience. Thank you to everyone who contributed to the great conversation in that thread.

On This Page:

Disclaimer

This article presents our current advice. The most general points will likely remain true for

years
DATE

, but the specifics will change as AI tools change. We recommend some resources in this article, but those recommendations should not be taken as an endorsement. We don’t agree with everything in these resources, nor do we expect them to necessarily still be the best in the future.

Also, note that the images in this article look quite different from

NN/g
ORG

’s typical design style — that’s because we used AI image generators to create all of the illustrations in this article.

Why Use AI in UX Work?

You can use AI to:

Increase your productivity

Improve the quality of your work

of your work Enhance your current skillset

Increased Productivity and Improved Quality

Many studies have shown that business professionals produce deliverables faster using AI. For example, consultants at an elite consulting company increased productivity by

33%
PERCENT

and the rated quality of their deliverables by

40%
PERCENT

when using AI.

Enhance Your Skills


Doris Lin
PERSON

gave us the great metaphor of AI as a sidekick to UX professionals. It speeds up the process and strengthens our results, allowing us to get more UX work done, but it doesn’t replace the need for human judgment. The symbiosis between humans and AI delivers higher quality than either can achieve alone. Thus,

AI
ORG

has the power to augment human skills.

The ultimate reason for any individual UX professional to learn

AI
ORG

is

Jakob
PERSON

’s

second
ORDINAL

law of

AI
ORG

, which says: You won’t lose your job to AI, but to someone who uses AI better than you do. Given the substantial performance gains with AI, you don’t stand a chance without it. This will be even more true in the future as the

AI
ORG

tools improve.

AI Is Safest for Experienced UX Professionals

All UX professionals should use AI: it’s helpful at any level of seniority and for many tasks within the

UX
PRODUCT

lifecycle (including research, design, and writing). (And our research shows that the majority of

UX
ORG

professionals already use it.)

An essential element in getting full value from

AI
ORG

is to include a heavy dose of human judgment in the workflow for

three
CARDINAL

reasons.

Humans Must Select Ideas Suggested by AI

The

AI
ORG

’s ability to make ideation virtually free is invaluable: AI generates as many ideas as you want in no time. In contrast, human ideas require extensive effort to produce.

The flip side to infinite ideation is the increased need for curation. Not all ideas produced by

AI
ORG

will be useful. Humans need to winnow down the many of these to the few that bear further exploration and implementation. Picking the winner from a bunch of ideas requires judgment and knowledge. As a result, it’s best done by senior

UX
ORG

professionals, who have built up experience the old-fashioned way.

Hallucinations Can Be Convincing

The

second
ORDINAL

reason for human judgment is to catch “hallucinations,” where the

AI
ORG

makes false assertions with great confidence. As long as the

AI
ORG

’s output is subjected to human review, hallucinations will not damage your results, but you must carefully watch out for them. While it’s mostly great that AI is a talented copywriter producing well-written and convincing text, its aptitude for good writing will fool inexperienced users into believing its expertise generalizes to everything else. Bad advice will appear to be the product of carefully considered analysis, as opposed to a hallucination emerging from the haze of an opium den.


Bias Lurks
PERSON

in

Training Data

ORG

Current AI also exhibits some bias because it reflects its training data, which came mostly from the internet. While the internet contains plenty of good information, it also has unpleasant, inaccurate, and downright false information. This is true for the field of

UX
PRODUCT

as much as for any other field — not all UX advice available online is good advice.

In addition, even good sources primarily reflect

Western
NORP

countries, particularly

English
LANGUAGE

-speaking cultures. This Western lens presents challenges, particularly for product teams that serve an international market. Taking

Wikipedia
ORG

as a simple proxy for the wider internet, here’s the number of words it contains in a few languages:


English
LANGUAGE

:

4.3 billion
CARDINAL

words across

6.7 million
CARDINAL

articles


German
NORP

:

1.5 billion
CARDINAL

words across

2.8 million
CARDINAL

articles


Danish
NORP

:

91 million
CARDINAL

words across

294 thousand
CARDINAL

articles

Hindi:

55 million
CARDINAL

words across

159 thousand
CARDINAL

articles


Swahili
LANGUAGE

:

12 million
CARDINAL

words across

79 thousand
CARDINAL

articles

Tips for Junior UXers Getting Started with AI

You should experiment with using AI in your work even if you’re new to UX. However, you must be particularly careful in judging its output. Remember that generative AI is particularly good at crafting responses that sound reasonable and true, even when they are not.

Follow these tips to avoid making mistakes when using AI for UX work:

Treat AI tools as a starting point. For example,

UX
ORG

is a field notoriously full of jargon. Generative-AI bots like ChatGPT can teach you about different UX terms, techniques, or tools.

For example,

UX
ORG

is a field notoriously full of jargon. Generative-AI bots like ChatGPT can teach you about different UX terms, techniques, or tools. Ask for sources and links. Currently, most generative-AI bots don’t automatically cite their sources, but you can ask them to. Ask for links to those sources as well, and doublecheck the information provided. (

Beware
ORG

, he offered sources may be inaccurate or nonexistent — ChatGPT once cited a nonexistent NN/g employee when we asked for its sources.)

Recommended AI Tools

There are many

AI
ORG

tools, with even more coming on the market

weekly
DATE

. But in the beginning, keep it simple — ChatGPT and

Midjourney
ORG

are good starting points.

ChatGPT

Start with

ChatGPT
ORG

’s free version

first
ORDINAL

. However, once you begin using AI more frequently, we strongly recommend the paid subscription to get the newest version (currently v.4), which is much better than the older, free version (v.

3.5
CARDINAL

). A

ChatGPT
ORG

subscription includes both the chatbot (currently the best text-generation AI tool) and the image-generation tool DALL-E 3, which is very good, though not as good as

Midjourney
PRODUCT

.


Midjourney
PRODUCT

If your work involves visual design, we also recommend a subscription to

Midjourney
ORG

, which has a wide range of useful image-oriented features and, among all the available AI image generators, produces the most beautiful artwork. Unfortunately, the current version of

Midjourney
ORG

has atrocious usability, which makes it unnecessarily hard to learn, though rumor has it that a better version is on the way.

How to Use AI

The primary way you interact with AI tools like ChatGPT and

Midjourney
ORG

is through prompts — written questions or commands that help the tool understand what you want. Crafting these prompts can be challenging, especially when you’re just getting started. To get the best possible results:

Provide ample context in your prompts

Ask for multiple options

Iterate on the output

Build a prompt library

Provide Ample Context

UX people are infamous for answering any question with “It depends!” The reason is that the best solution is highly dependent on the context. In particular, the answer always depends on who the users are and what tasks they perform.


Vinay Maurya
PERSON

advised that most of the time you ask AI for something, you should add the context to the prompt. For example, if you want to have ChatGPT help you craft a research plan, you’ll need to give it lots of details — the type of study, the target audience, research budget, timeline, and so on.


Arnav Dhanuka
PERSON

recommended that prompts include a persona, a task, and relevant background info. As an example of this idea,

Florian Bölter
PERSON

wrote:

Whenever I ask for microcopy, I describe the circumstances of where this copy appears and what it essentially needs to convey so AI knows all constraints.

These details can be provided in a few different places:

In

one
CARDINAL

very specific and long initial prompt

In a sequence of several prompts

In

ChatGPT
ORG

’s custom instructions

ChatGPT’s custom-instructions feature allows you to specify information that you always want it to consider. You can use the custom instructions to avoid including the more general elements of your context in every prompt if you consistently work in a given domain with the same kinds of users.

You can also instruct ChatGPT to ask you followup questions for any missing details that would help it produce your desired output.

In most cases, you should employ very specific prompts for the best UX results. But for generating ideas, there is value in using concise, even single-word prompts that leave most of the interpretation open to the

AI
ORG

’s whims. This strategy is useful during initial ideation, where you want wild ideas (that you can winnow based on human judgment). If you feed the AI one word, you will often find that it delivers results you would never have thought of. This is particularly useful for visual design. Yes, most of these ideas will be terrible, but there are some gold nuggets in those

one
CARDINAL

-word hills.

Ask for Multiple Options

Whenever you have to write a document or draft a design, that blank screen is intimidating.

Raghuvamsi Ayapilla
PERSON

,

Chris Callaghan
PERSON

, and

Ayushi Choudhary
PERSON

all recommended employing AI for the

first
ORDINAL

draft of your document — in

seconds
TIME

, you’ll have a nearly complete deliverable.

Don’t deliver this

first
ORDINAL

draft to your client or stakeholders. Treat the AI’s output as a starting point for you to edit.Editing is much easier than creating from scratch, so this simple procedure is one of the main ways AI enhances productivity in

UX
ORG

work.

Do not ask the

AI
ORG

to produce just

one
CARDINAL

document or

one
CARDINAL

design. Instead, ask it to give you

three or
CARDINAL


five
CARDINAL

versions. Use prompt language like Give me

5
CARDINAL

wildly different versions of

XXX
ORG

. Ideation is free with AI, so you can employ it for many more steps in the

UX
ORG

workflow than would be economical if you had to get a group of

UX
ORG

colleagues into a room for a brainstorming session.

Iterate on the Output

Many contributors stressed the necessity of ongoing refinement when working with AI. The process of using AI (especially prompt generation) is iterative and requires adjustments to finetune the outcomes. Don’t be satisfied with the outcome of your

first
ORDINAL

prompt. Techniques like accordion editing and apple picking can be used to tweak AI output for better results:

Accordion editing: Users adjust the length of the

AI
ORG

-generated text iteratively by expanding and compressing the

AI
ORG

’s output.

Users adjust the length of the

AI
ORG

-generated text iteratively by expanding and compressing the

AI
ORG

’s output.

Apple
ORG

picking: Users reference elements in previous AI responses to modify the following prompt.

Less systematically, experiment and ask the AI for changes. As you gain experience, you will better understand how to get the best results for your types of work products.

Build a Prompt Library


Arnav Dhanuka
PERSON

recommended that you build up a prompt library with the exact wording of prompts that have worked well for your scenarios. This library will save you a lot of typing, especially for specifying common UX contexts. But it will also remind you of fruitful alternatives if your

first
ORDINAL

prompting attempt doesn’t achieve your desired results.

As an example, the illustration of an acorn at the end of this article was generated by

Jakob
PERSON

with the prompt neo-impressionism expressionist style oil painting, smooth post-impressionist impasto acrylic painting, thick layers of colorful textured paint –ar 16:9 –s 20, which he often uses for his illustrations.

Specific UX Tasks for AI

Here are some ideas from our respondents for specific

UX
ORG

work that

AI
ORG

can help with.


Design

Research

ORG

Write user interview questions (

Doris Lin
PERSON

)

Sentiment analysis for initial theme finding (

Lawrence Williams
PERSON

)

Analyze user feedback: Identify the most common pain points mentioned in the following user feedback: [feedback]. (

Vinay Maurya
PERSON

)

Rewrite research reports to be clearer for your audience, who are often not UX specialists (

Mohammad Fejlat
PERSON

)

Content

Write text efficiently, such as for emails, concepts, or posts, based on outlines you provide (

Vicky Pirker
PERSON

)

Improve UX writing: Make the following text more concise and user-friendly: [text] (

Vinay Maurya
PERSON

)

For this very article, we used AI for

two
CARDINAL

simple tasks that feature frequently in most UX work: (a) to structure and pull out themes from the comments

Kate
PERSON

received, and (b) to quickly generate illustrations.

What AI Can’t Do

AI can do a lot for UX work, as we have outlined. But beware of the hype: some people claim that AI tools can replace designers, researchers, or even users.

You can show the

AI
ORG

a user-interface design by uploading screenshots or mockups and ask for a critique. This is a helpful step because the

AI
ORG

sometimes mentions new things you may have not considered. But AI-derived design critiques are dangerous because many of its insights are wrong, even if they are argued in polished language, with reference to established usability principles. AI can be highly convincing and still be wrong. If you are an experienced

UX
PRODUCT

professional, you can hopefully distinguish hallucinated redesign recommendations from sound redesign recommendations and use the latter for inspiration. But junior

UX
ORG

staff should probably avoid using AI for design critiques.

Here’s an example of a design analysis that went well:

Jakob
PERSON

was pondering which illustration to use for the

LinkedIn
ORG

post of a recent article. He uploaded

3
CARDINAL

candidates to

ChatGPT
ORG

and asked for its recommendation. Here’s the chosen image and what ChatGPT had to say:

AI cannot replace user research with real users. It can give you plenty of ideas for issues to look for in a usability study, but it can’t predict what your customers will do. For better or worse, humans are unpredictable beings, especially when it comes to complex behaviors like the use of a real-world interface. Even more important, the “knowledge” of the current

AI
ORG

tools reflects the assumedly “typical” human behaviors. Your specific user groups likely have very different backgrounds, needs, and motivations than the “typical” human — that’s the whole reason we conduct research with our own users.

Most UX methods must be grounded in reality – that is, supported by real data from real users. AI can help with structuring and interpreting this data, though the interpretations must be doublechecked based on your UX expertise. But if you ask AI to make up the data, the interpretations quickly become useless or outright misleading.

Do You Need to Know How AI Works?

This article is about the applications of AI in UX projects. However, we are often asked whether UX professionals need to understand the inner workings of AI. The answer is: mostly no. Just as with other tools, you don’t have to know how they were built to use them. To use a statistics package, you don’t need to know the mathematical formula for the normal distribution or the code for computing a t-test. To design a website, you don’t need to be a front-end developer or a back-end developer. Nor do you need to know

SQL
ORG

, HTML, or JavaScript.

Along the same lines, you don’t need to know the workings of diffusion models to coach a beautiful image out of

Midjourney
ORG

, nor do you need to understand large language models to make ChatGPT summarize a lengthy document in

10%
PERCENT

of the word count. We don’t recommend spending your scarce time on an extended study of

AI
ORG

theory and technology.

However, UX professionals benefit from understanding related disciplines and the underlying technology used to build their designs. Using a statistics package without knowing basic statistics concepts is positively dangerous. Understanding what developers do and how they deal with technology constraints will improve the chance that your design vision will be implemented in a real product.

Similarly, UX professionals should understand the basics of

AI
ORG

. This knowledge will help them communicate with technical colleagues and discover ways to overcome AI limitations. Basic AI knowledge is also necessary for using

AI
ORG

in advanced

UX
PRODUCT

projects, such as

GE
ORG

’s analysis of qualitative user comments at scale, which turned these comments into trackable and actionable quant data.

There are many educational resources available to pick up AI basics. For a popular introduction,

Zahra Rahman
PERSON

recommended the

PBS
ORG

show

Crash Course Artificial Intelligence
ORG

, which can be watched on

YouTube
ORG

for free in

about 4 hours
TIME

. For more depth, she also recommended

MIT
ORG

’s

8-week
DATE

course Designing and

Building AI Products and Services
ORG

($

2,625
MONEY

). If this price makes your wallet go ouch,

Suzanne Williams
PERSON

recommended

IBM
ORG

’s free

SkillsBuild
ORG

series of AI courses.

Finally,

Google
ORG

has a series of free courses about AI technology, which focuses a bit too much on

Google
ORG

’s offerings but can still be useful.

Stay Updated: Recommended Newsletters

AI constantly changes, so whatever you learn now will soon be outdated. It’s still worth starting now because the experience and understanding you build will help you make sense of future developments and build better and faster mastery of any new tools or features.

We recommend subscribing to the following newsletters for regular updates and for analyses that contextualize new AI developments better than what you’ll get from mainstream news media:


Nielsen Norman Group’s
ORG

newsletter. Weekly, we publish new articles and videos about UX in general. We currently have many AI research projects in the works, meaning that more fresh AI content will be published soon.


Jakob Nielsen’s
PERSON

newsletter (“

Jakob Nielsen
PERSON

on

UX
ORG

”).

Jakob
PERSON

’s newsletter publishes his articles on the intersection of AI and UX and are thus highly targeted for your needs.


Maginative
NORP

. This is a website covering

AI news
ORG

. We recommend subscribing to the

weekly
DATE

newsletter, which carries a roundup of the

week
DATE

’s main developments.


Ethan Mollick
PERSON

’s newsletter (“

One Useful Thing
WORK_OF_ART

”).

Mollick
PERSON

is a business school professor, and his newsletter focuses on making AI useful in business in general, so it’s not specifically about UX. But it’s an incredibly useful newsletter because of his insights and commitment to staying on the bleeding edge of AI developments. This newsletter is often where you find the

first
ORDINAL

good analysis of new

AI
ORG

features’ impact on business users. In any case,

UX
ORG

is used in business;

UX
ORG

professionals are business professionals, and

UX
ORG

leaders are business leaders. So, most of

Mollick
ORG

’s advice does apply to you, even if he doesn’t use UX language.

You should also follow

Jakob
PERSON

and

Kate
PERSON

on LinkedIn for our updates, recommendations, and conversations. Finally, you should curate additional newsletters and influencers to follow, if they appeal to your specific interests and circumstances — there are plenty to choose from.

Start Now, Start Small

In

a few years
DATE

, it will be essential to be highly skilled at using AI as the technology improves and business adaptation spreads. You must start now because it requires

those few years
DATE

to become highly qualified and experienced later. You will see immediate gains in your work productivity and creativity, but your future is even more important. Any day you don’t use

AI
ORG

is a day you undermine your career prospects by dropping further behind those

UX
ORG

professionals who are going all in and gaining AI experience rapidly.

We recommend starting now but starting small. As

Vinay Maurya
PERSON

wrote,

Don’t try to use AI to solve your biggest UX problems right away. Start with smaller tasks, such as generating user personas or writing microcopy.

Within

a few months
DATE

of practice, you will build enough skill and confidence to tackle medium-sized AI-based activities. And within

a year
DATE

, you will probably turn to AI for help with most of your UX work. Just remember to retain that all-important human judgment.

A key benefit of starting small is that it’s less intimidating. This means that you can start

today
DATE

, which you should.