Log in or create a free Rosenverse account to watch this video.
Log in Create free account100s of community videos are available to free members. Conference talks are generally available to Gold members.
Rapid AI-powered UX (RAUX): A framework for empowering human designers
Summary
UX and content designers often find themselves with incomplete research, limited budgets, and the pressing need to validate concepts quickly. How can you effectively create personas and journey maps under these constraints? Enter the power of AI. In this session, Noz Urbina will unveil a unique and proven methodology that leverages AI to craft personas and journey maps from incomplete data. Or if you’re blessed with good research, it provides a way to synthesize it to create more and richer personas, maps, and therefore, designs, than you’d ever have time for otherwise. This approach both helps designers do more with less using AI, and provides a foundation to validate assumptions, rally stakeholders quickly. Therefore putting them in a better place to secure the budget you need for comprehensive human-led research. What you’ll learn: See the transformative power of AI in the realm of UX and content design, making the abstract tangible for designers and stakeholders alike. Discover a unique methodology that uses AI to create fleshed-out personas and journey maps from whatever your starting point or budget. Learn how to accelerate the creation of initial or draft maps that validate assumptions and engage stakeholders.
Key Insights
-
•
ROCKS is an AI-driven framework designed to empower human UX and content designers, not replace them.
-
•
Traditional persona and journey mapping are often fragmented across conflicting documents; AI can unify and synthesize these sources efficiently.
-
•
Journey maps should be framed as sequences of user questions over time, prioritized by emotional intensity and context, rather than linear task flows.
-
•
AI personas can be generated, iterated, and simulated interactively, enabling better empathy and collaborative design decisions.
-
•
Separating AI assistants into roles—data assistant, UX assistant, and persona sims—clarifies workflows and improves design output quality.
-
•
Human oversight is critical to validate AI outputs, especially to avoid hallucinations or inaccurate research synthesis.
-
•
Defining a bot’s context, job description, and required skills upfront streamlines AI-driven workflows and reduces unnecessary chatty responses.
-
•
Skills designed for bots can chain together tasks, integrate external databases, and perform complex operations, making AI practical for enterprise environments.
-
•
ROCKS can proactively recommend reuse of existing content and design assets, thus improving efficiency and reducing redundant work.
-
•
The long-term vision is an AI super assistant that integrates cross-functional business data, delivers strategic insights, creates content, and manages tasks automatically.
Notable Quotes
"We’ve trapped the genie in a bottle, but we don’t know what to ask it."
"Traditional journey maps are useless diagrams that don’t capture the real emotional and contextual complexity."
"Talking in first person increases empathy and leads to better design outcomes."
"AI doesn’t create much new; it accelerates the process and frees humans to focus on uniquely human work."
"Personas and journey maps usually live in different places, conflicting and hard to maintain—ROCKS aims to fix that."
"Stop just throwing AI at the end of the process; integrate it strategically across the whole product and content lifecycle."
"Every AI conversation thread is important; mixing contexts confuses the AI."
"You have to verify key data points carefully because AI can hallucinate details in critical areas."
"Skills are modular tasks that bots can perform, triggered by specific commands or inputs."
"The vision is a super design assistant that talks to all your data systems, suggests content, writes proofs of concept, and puts tasks into Jira."
Or choose a question:
More Videos
"UX researchers tend to focus on the experience after features are approved, missing the chance to validate earlier."
Michaela MoraAdvanced Concept Testing Approaches To Guide Product Development and Business Decisions
March 11, 2022
"You owe it to your organization and your team to grow the practice while staying true to your vision."
Rob Mitzel Sébastien MaloThe Tale of Two Companies: Building a Successful UX Practice in a Century-Old Enterprise
January 8, 2024
"If you use AI tools, ask for five different ways to do something, not just one, to force exploration."
Dan Mall“Ask Me Anything” with Dan Mall, Author of Upcoming Rosenfeld Title, Design that Scales
October 2, 2023
"If people are looking for lunatic asylum or Austin State Hospital, they should both be findable, but presented appropriately."
Bryce Benton[Demo] AI-powered UX enhancement: Aligning GitHub documentation with USWDS at Austin Public Library
June 4, 2024
"The word intelligence in artificial intelligence leads many to read more into the technology than is actually there."
Frances Yllana Jorge Arango Maria Taylor Briana ThomasThe Big Question about Impact: A Panel Discussion
September 24, 2024
"If something makes you feel unwelcome, the code of conduct explains how to engage with staff to resolve issues."
Bria Alexander Louis RosenfeldWelcome
January 8, 2024
"Designers should not be left to figure things out alone as we grow faster."
Ebru NamaldiDesigning the Designer’s Journey: Scaling Teams, Culture, and Growth Through DesignOps
September 11, 2025
"Stop writing so much email and do real work."
Joshua GravesWe Need To Talk: Managing Ludicrous Requests at Work (Part 3 of 3)
May 12, 2025
"We prioritize speaking with people who are most in need of support so we can better understand and design for all potential users of PFML."
Lisa Spitz Nikki BrandBuilding Trust Through Equitable Research Practices
November 18, 2022
Latest Books All books
Dig deeper with the Rosenbot
Why is prior authorization such a persistent problem and how can patient-centered solutions be designed around it?
In what ways can AI tools accelerate value delivery in design operations, and what pitfalls should be avoided?
How can smaller or solo research teams scale insight sharing in large organizations?