Neueda

Insights

How UX Teams Can Leverage AI While Still Designing for Humans

gareth dunlop instructor headshot Written by Gareth Dunlop

AI for UX teams

This might be the first article on AI you’ll read this year that doesn’t start with the usual “AI won’t take your job” cliché. Instead, it’s for UX professionals who want to make sure AI becomes an asset in their work—helping them create more effective, human-focused designs.

AI offers tremendous opportunity for efficiency across most aspects of the UX lifecycle, including capturing and analysing user data, synthesis, output creation and storytelling. It is particularly adroit at carrying out the heavy cerebral lifting which leaves designers with sore heads and confines them to darkened rooms after a heavy day of synthesising ambiguous, voluminous and sometimes contradictory information.

Making AI a Practical Part of UX Design

Implementing UX-relevant AI tools as part of a design process is like having access to a perfectly motivated, hardworking, never-complaining, whip-smart recent MBA grad who never gets sick, is never in a bad mood and never misses a deadline. The grad isn’t ready to be sent in to face the board, and there is a naivety (and even some inaccuracies) in some of the work he does, but the sheer volume of heavy lifting that he does means that when used smartly, he can do all the foundational legwork. This leaves the AI-empowered UX practitioner loaded with everything she needs to review and structure what she’s learned from AI and perform brilliantly in front of the board.

This idea of ‘legwork then polish’ aligns closely with how UX practitioners think and act, as it first establishes direction of travel and lo-fidelity thinking before it develops fully polished artefacts and hi-fidelity outputs. This means that there is lots for our perfectly motivated MBA grad to be doing within already established processes. AI therefore doesn’t replace thinking, or problem solving, or creativity or personality, rather it replaces the labour from which they are achieved.

There are three areas in particular, where AI can replace labour, drive efficiency and increase effectiveness.

ai training for ux teams

Capturing and analysing user data

Making sense of the chaos of early insight gathering

Because Large Language Models (LLMs) are so adept at interpreting large volumes of unstructured information, they are ideal for the early discovery phases of UX projects, where UX teams are often focused contextualising their work. Sources of insight are often eclectic – formal and informal, internal and external and across multiple formats. See below an example of a typical bundle of insight and relevant content which a team might encounter as they start a new programme of work:

· some industry research the client commissioned three years ago which has some relevance but isn’t as relevant as it was

· Forrester and Gartner reports related to their industry and where the market is moving

· target customer description in PowerPoint format

· internal documentation and business modelling, in Word, Excel and PowerPoint formats

· analytics from a current product

· customer survey from a current product

This is food and drink to a product such as Google’s Notebook LM, which can receive the content in any format, synthesise it, and generate outputs such as key findings, a mind-map and even a podcast mimicking a host and a subject-matter expert discussing the information.

Gaining direct user insight via voice (or text) interface

AI’s contribution to research doesn’t have to be constrained to synthesising pre-existing sources of insight. AI can engage with users to ask them their opinion and sentiment at a high level related to an experience such as booking a hotel, applying for a mortgage or researching insurance. Users can engage with an AI prompt either by typing, or with voice, allowing a UX team to gain user insight at scale. What once involved inviting users into focus groups and 1-1 interviews now involves sending them some instructions and a link, for them to engage with the questions on a smartphone.

While this approach naturally brings with it compromises and trade-offs, it does allow UX teams to garner user sentiment at scale efficiently, and as AI can also synthesise the findings, identify key themes and recommendations for next steps.

Structuring content for consumer-focused websites

Card sorting and tree testing remain the go-to research methods in the UX professional’s armoury when wanting to design information architecture and user flow. While those techniques will continue to be important for more niche sectors, the difference between card-sort-led navigation systems and AI-designed navigation systems for mainstream areas is diminishing all the time. This means that AI has the potential to generate ‘good enough’ menu systems to get a product to the stage where it is ready to launch and iterate. A recent study on the Best Buy website illustrated that when its product range was synthesised through an AI model there was 100% overlap in terms of categories and 63% to 77% overlap in terms of where products were placed.

Helping to design research

AI is particularly useful for providing a baseline for usability testing scenarios and tasks (including an ice breaker, introduction and exit questions). The recommendations the LLMs provide often need refinement and checking, but the outputs will get a user researcher to 90% of test design relatively effortlessly.

Research synthesis outputs

Personas

By the time you read this blog post, the entries here could be out of date.  Github Copilot is evolving quickly, and there are newer features coming online at regular intervals. But the point of this blog post is to say that it can do more than you probably realised – and it can be a real productivity boost.  It really is revolutionising the way that we write code. The role of the developer is becoming one where we spend more time thinking and less time typing, but producing greater volumes of higher quality code.

Just before finishing this article I had a meeting with a colleague where they told me they had asked Copilot to produce some architecture diagrams for their project, and they were impressed with the results… so I’m off to try that next!

User journey mapping

The user journey map is a critical artefact for many UX projects because it centres the project team around the user and describes an experience through their eyes. User journey maps generated by LLMs aren’t ‘production ready’ but they provide an experienced UX professional with a head-start and initial structure from which to flesh out a more complete artefact.

Storytelling and storyboarding

The user journey map is a critical artefact for many UX projects because it centres the project team around the user and describes an experience through their eyes. User journey maps generated by LLMs aren’t ‘production ready’ but they provide an experienced UX professional with a head-start and initial structure from which to flesh out a more complete artefact.

AI for UX teams training at Neueda

At Neueda, we’re already seeing how AI can empower UX teams to innovate faster and stay focused on what matters: the human experience. Our AI for UX Teams programme is designed to help your team integrate AI tools seamlessly into the UX process—enhancing productivity, accelerating discovery, and ensuring that your designs stay human-centered.

Learn more

Success Stories

Explore our AI case studies

See stories

Get in touch

Find out more about how we help enhance your UX team’s AI skills

This field is for validation purposes and should be left unchanged.
Consent

Share Insight

Related Insights

AI upskilling women at screen
Insights Briefing

Beyond the Training Event: A New Model for AI Upskilling

The pressure on organisations to build AI capability has never been greater, yet many enterprises are discovering that training alone does not lead to meaningful adoption or measurable business value. The real challenge is not simply teaching people how AI tools work - it’s embedding AI into the way people actually work. That requires a fundamentally different approach to upskilling, behaviour change, and organisational enablement.

Read full insight
See all insights