AI-assisted UX research synthesis and stakeholder reporting

I had a conversation last week that stayed with me.

A mid-level designer I know told me they had been experimenting with AI for about six months.

When I asked how they were using it day to day, they said, “mostly for writing UX copy.”

That is not unusual.

Most of the advice designers see is either a tool demo or a broad prediction about the future of the industry. There is much less discussion about the ordinary tasks where AI can save 30 or 40 minutes during a normal workday.

Here are a few places where it has been useful in my own work.

I use it to generate content options for states I might otherwise rush through.

Error messages, empty states, loading copy and less common edge cases often get left until the end of a project. I can give a model the feature context, review several options, and then write the final version myself.

It helps me get past the blank page without handing over the decision.

I also use it to organise messy research transcripts.

I do not ask for conclusions. I ask it to identify tensions, repeated concerns and questions that were never resolved.

The interpretation is still mine, but I spend less time sorting through thousands of words before I can begin thinking about what they mean.

Another useful task is drafting the background section of a design spec.

Explaining why a decision was made can take longer than making the decision itself. A rough first draft gives me something to correct, clarify and shape into language the rest of the team can use.

None of these tasks replaces design judgment.

They reduce the amount of attention I spend on work that is repetitive, slow or difficult to start.

Using AI only as a writing assistant is useful, but it is a small part of what it can do.

A better place to start is to look at the tasks you repeat every week and ask which parts need your judgment, and which parts are mostly setup.

Where have you found a use for AI that has actually become part of your regular workflow?

#productdesign #uxdesign #aifordesigners

A short, honest field guide to using AI across the UX/UI workflow — from research to shipping — without losing the judgment that makes design good.

A few years ago, if someone had told me that AI would become a part of almost every design project I worked on, I probably would have laughed. Like many designers, I believed great products came from creativity, empathy, and experience — not algorithms.

Then I started experimenting.

On my last product design project I went all-in with my AI workflow, and I wanted to share it here. Maybe it's useful to someone, and I'd love to get some tips to improve it.

I went from nothing to a fully working dashboard (6 pages, realistic data, all features functional) in days. Including UX research throughout the entire process. That's 5x faster than before.

Here's what my AI workflow looked like:

Discovery research
Stakeholder interviews and a user interview on the current tool. I record and transcribe every conversation. Then I use my own Claude skill to clean up those transcripts, summarize them and pull out to-dos. That output goes into 2 documents: 1 cleaned-up transcript, which I can still search through later. And 1 with a summary + to-dos.

Design exploration
I made 3 design directions in Figma (partly in Claude Design), discussed them with the team and stakeholders, and picked 1.

Prototype & testing
I then built a working prototype, still based on a lot of assumptions. Showed it to users. Again transcribed every conversation and ran it through my skill. That output goes straight into prompts for Claude Design.

Iterating
adjusted the design based on what I heard. Showed it again, transcribed again, prompted again. Research and design stop happening one after the other and start happening seamlessly alongside each other.

Live testing
I used Netlify to publish the prototype on a free link. Users shared their screen during a call, and I could watch and ask questions. It had fake data they could actually edit themselves, and immediately see the effect on the dashboard. It was simply a fully working dashboard.

Handoff to dev
once the design was fully signed off, I built it out further with Claude Code and handed it over to the developer via Github.

Result
5x faster than half a year ago. Not because AI takes over the work, but because the distance between insight and iteration gets a lot smaller. And I spend way less time on write-ups, re-reading, and typing.

Curious if this sparks any ideas to add (or drop) from this workflow!
And if you want to use my transcript skill, I can send it!

Artificial intelligence has completely changed the way I think about design.

Not long ago, creating wireframes, designing user flows, and building polished UI screens were some of the most valuable skills a designer could offer. Today, AI can generate interfaces, suggest layouts, write UX copy, create icons, and even build interactive prototypes within minutes.

When I first saw what AI was capable of, I had the same thought many designers did:

“Will UI/UX designers still be needed?”

The more I explored AI, the more I realized I was asking the wrong question.

The truth nobody wants to hear: AI is still too expensive to replace most designers. I know every day there seems to be a new AI update, a new tool, or another headline telling us that AI is coming for our jobs. If you’re a designer, it’s easy to feel anxious when you see all of that. But from my experience using AI extensively in my workflow, we’re not there yet.

One thing many people don’t talk about is the cost.
For AI to truly replace a human designer, you need access to the best models, the right tools, premium subscriptions, APIs, tokens, automations, and infrastructure. When you start adding all of that up, it becomes expensive very quickly. In many cases, it’s still cheaper to pay a skilled human than to build and maintain a fully AI-driven workflow.

More importantly, AI still needs direction.
Every time I use AI for design work, the quality of the output depends heavily on my input. It depends on my thinking, my experience, my judgment, and my ability to guide it. AI doesn’t magically know what users need, what business goals matter, or what trade-offs should be made. I often describe AI as a junior designer. It’s fast. It’s helpful. It can generate ideas, speed up research, and help execute tasks. But it still needs supervision. It still needs someone to tell it what good looks like.

The real opportunity right now isn’t AI replacing designers.
The opportunity is for designers who know how to use AI, replacing designers who don’t. So instead of spending your energy worrying about being replaced, spend that energy learning how to work with these tools. Learn prompting. Learn automation. Learn how to integrate AI into your process.

Because today, AI works best when it’s paired with human judgment.
And that human judgment is still incredibly valuable.

Does UX still matter — or is AI making us obsolete?

AI generates layouts in seconds. Writes microcopy on demand. Analyzes user data faster than any research team.

So why do we still need UX designers?

Here's what AI already does better than you:
→ Generate 5 layout variants in 30 seconds
→ Write 10 error message alternatives on command
→ Summarize 15 interview transcripts in minutes
→ Spot patterns across thousands of data points

Impressive. But here's what AI can't do:
Empathy isn't computable. AI does sentiment analysis. It can't sense why a 63-year-old goes silent during a usability test — not from confusion, but from shame.

Context has no data model. AI doesn't know your CEO said "mobile-first" because he got a new iPhone. It doesn't know your engineering team is burned out and every design change is political.

Ethics require conviction. AI optimizes for whatever goal you set. If that goal is "more clicks," it will suggest dark patterns without blinking. A designer asks: Should we?

Saying no is a skill. AI always delivers an answer. Even when the right answer is: We're solving the wrong problem.

The designers who thrive aren't the ones pushing pixels. They're the ones asking questions before designing answers.

AI makes you faster. It doesn't make you smarter, more empathetic, or braver. That's still on you.

I've packed everything I've learned in 24 years of design into one interactive platform — methods, tools, Nielsen's 10 heuristics, a glossary, and a section on how to actually use AI in your UX workflow.
→ https://lnkd.in/gHT-zJ44
#UX #AI #ProductDesign #UserExperience #DesignLeadership

I've been sharing a lot about AI-powered product design workflows — what I try, what I actually use in my own work, and what sticks.

Every time I post, someone asks for tutorials or a deeper walkthrough. So I finally put it all in one place.

The guide covers everything I've tested so far - design workflow across 7 modules:
→ UX Research & Synthesis → UX Strategy & Methodology → Visual & UI Design → Content & Copy → Handoff & Documentation → Design Systems (coming soon) → Claude Skills

If you've been curious about how to bring AI into your design practice in a way that's actually useful, this is for you.

Link in the comments 👇

There’s a lot of noise around AI in design. Some say it will replace designers. Others dismiss it entirely. After three months of deliberately integrating AI tools into my daily workflow, my view is more nuanced—and more interesting than either extreme.
AI did not make me less of a designer. But it permanently changed how I design.

AI tools won't replace UX Designers.

But designers who ignore AI will be replaced by those who don't.

Here's how I'm using AI in my UX process right now (without losing the human touch):

🔍 Research synthesis Dump interview notes into AI → get themes in minutes, not hours. I still validate every insight but I save hours of grunt work.

✍️ First-draft microcopy AI gives me 10 variations of a button label or error message. I pick, refine, and make it actually sound human.

🗺️ User journey mapping I use AI to spot gaps in a journey I've been staring at too long. Fresh (artificial) eyes catch what tired human ones miss.

🧪 Usability test prep AI helps me draft screener questions and discussion guides 3x faster. More time for actual conversations with users.

The goal isn't to hand over your design thinking. It's to free up more time for your design thinking.

What's one AI tool that's genuinely changed how you work as a designer? 👇

#uxdesign #aiindesign #ai #userexperience #productdesign #designtools