(Picture) AI is a mirror looking back at the UX professional: the more skilled you are at UX, the better results you’ll get with AI –- especially when it comes to identifying AI’s weaknesses and applying UX judgment to winnow AI’s ideas into usable product design. (Image by Midjourney.)

Jakob recently wrote that the UX field needs to urgently engage with AI. This is partly because usability improvements are sorely needed for current AI tools but just as much because UX work can be vastly improved through the appropriate use of AI.

Luckily, many members of the UX community agree and have asked us how to use AI in UX work. Kate 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 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.

Disclaimer

This article presents our current advice. The most general points will likely remain true for years, 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’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
• 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% and the rated quality of their deliverables by 40% when using AI.

Enhance Your Skills

Doris Lin 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 has the power to augment human skills.

The ultimate reason for any individual UX professional to learn AI is Jakob’s second law of AI, 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 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 lifecycle (including research, design, and writing). (And our research shows that the majority of UX professionals already use it.)

An essential element in getting full value from AI is to include a heavy dose of human judgment in the workflow for three reasons.

Humans Must Select Ideas Suggested by AI

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

Hallucinations Can Be Convincing

The second reason for human judgment is to catch “hallucinations,” where the AI makes false assertions with great confidence. As long as the AI’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 in Training Data

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

In addition, even good sources primarily reflect Western countries, particularly English-speaking cultures. This Western lens presents challenges, particularly for product teams that serve an international market. Taking Wikipedia as a simple proxy for the wider internet, here’s the number of words it contains in a few languages:

• English: 4.3 billion words across 6.7 million articles
• German: 1.5 billion words across 2.8 million articles
• Danish: 91 million words across 294 thousand articles
• Hindi: 55 million words across 159 thousand articles
• Swahili: 12 million words across 79 thousand 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 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 double-check the information provided. (Beware, he offered sources that 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 tools, with even more coming on the market weekly. But in the beginning, keep it simple — ChatGPT and Midjourney are good starting points.

ChatGPT

Start with ChatGPT’s free version first. 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). A ChatGPT 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.

Midjourney

If your work involves visual design, we also recommend a subscription to Midjourney, 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 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 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 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 recommended that prompts include a persona, a task, and relevant background info. As an example of this idea, Florian Bölter 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 very specific and long initial prompt
• In a sequence of several prompts
• In ChatGPT’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 follow-up 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’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-word hills.

Ask for Multiple Options

Whenever you have to write a document or draft a design, that blank screen is intimidating. Raghuvamsi Ayapilla, Chris Callaghan, and Ayushi Choudhary all recommended employing AI for the first draft of your document — in seconds, you’ll have a nearly complete deliverable.

Don’t deliver this first 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 work.

Do not ask the AI to produce just one document or one design. Instead, ask it to give you three or five versions. Use prompt language like Give me 5 wildly different versions of XXX. Ideation is free with AI, so you can employ it for many more steps in the UX workflow than would be economical if you had to get a group of UX 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 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-generated text iteratively by expanding and compressing the AI’s output.
• Apple 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 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 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 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 work that AI can help with.

Design

• Generate ideas to inspire creativity (Doris Lin)
• Create illustrations for personas and journey maps (Chris Callaghan and Elsa Ruiz)
• Plan out a workshop agenda (Doris Lin)
• Produce text and images for use in prototypes to increase realism and relevancy instead of lorem ipsum (Matt Feilmeier, Doris Lin, and Elsa Ruiz)

Research

• Write user interview questions (Doris Lin)
• Sentiment analysis for initial theme finding (Lawrence Williams)
• Analyze user feedback: Identify the most common pain points mentioned in the following user feedback: [feedback]. (Vinay Maurya)
• Rewrite research reports to be clearer for your audience, who are often not UX specialists(Mohammad Fejlat)

Content

• Write text efficiently, such as for emails, concepts, or posts, based on outlines you provide (Vicky Pirker)
• Improve UX writing: Make the following text more concise and user-friendly: [text] (Vinay Maurya)

For this very article, we used AI for two simple tasks that feature frequently in most UX work: (a) to structure and pull out themes from the comments Kate 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 a user-interface design by uploading screenshots or mockups and asking for a critique. This is a helpful step because the AI sometimes mentions new things you may have not considered. However AI-derived design critiques are dangerous because many of their insights are wrong, even if they are argued in polished language, concerning established usability principles. AI can be highly convincing and still be wrong. If you are an experienced UX professional, you can hopefully distinguish hallucinated redesign recommendations from sound redesign recommendations and use the latter for inspiration. But junior UX staff should probably avoid using AI for design critiques.

Here’s an example of a design analysis that went well: Jakob was pondering which illustration to use for the LinkedIn post of a recent article. He uploaded 3 candidates to ChatGPT and asked for its recommendation. Here’s the chosen image and what ChatGPT had to say: