AI as a Design Partner: How to Get the Most Out of AI Tools to Scale Your Process
Summary
I am a Senior Product Designer at a large tech company, leading the Video Gen AI and Growth programs. This talk is a case study about leveraging AI tools to scale and systematize your design process. Some examples include creating better and more thorough user journey lists that capture all types of users, reducing the risk of excluding some users. I will also talk about how to have a Systems Design mindset about UX programs, including how to scale your work across teams and organizations for broader impact.
Key Insights
-
•
Generative AI can help product creators scale inclusive design by systematically generating user journeys based on diverse and intersecting dimensions of identity.
-
•
Product inclusion means centering marginalized voices and can be applied at every phase of product creation for broader belonging.
-
•
Systematic design relies on three pillars: documentation of critical user flows, collaborative ideation (like design sprints), and synthesis/prioritization of insights.
-
•
Designing for 'average users' overlooks large populations with diverse abilities, including 1 in 7 people with disabilities and an aging population with hearing loss.
-
•
Prompt design for generative AI requires detailed task steps, persona definitions, output format examples, constraints, and iterative refinement for best results.
-
•
Dimensions of identity include visible and hidden traits whose intersections create complex user identities to be intentionally incorporated into user flows.
-
•
AI can accelerate affinity clustering and abstraction laddering in design sprints, compressing hours of team work into minutes.
-
•
AI should augment, not automate, the design process due to inherent biases in training data, such as racial or gender bias.
-
•
Refining AI-generated outputs through iteration and human oversight is critical to ensure meaningful and inclusive design outcomes.
-
•
Using AI-generated inclusive user journeys can inform more diverse recruitment strategies in user research, backing a more inclusive design validation process.
Notable Quotes
"If you do not intentionally, deliberately, and proactively include, you will unintentionally exclude."
"The majority of consumers say that it’s important that the companies they buy from actively promote diversity and inclusion."
"Sometimes we have ideas of average users, but there are many different abilities to account for that are large parts of the population."
"You want to outline the tasks or steps in detail, define personas, give examples, set constraints, and refine iteratively when prompting AI."
"These AI models are not one hundred percent perfect, so you must stress test the output and watch out for bias."
"Previously, creating user journeys for millions took hours, now generative AI can do it in minutes."
"You can use AI for affinity clustering to find common themes from large idea sets in minutes rather than hours."
"Design ops could take responsibility for managing prompt libraries but it’s not a lot of maintenance once set up."
"Using AI-generated user journeys can help recruit a more inclusive set of participants for user research."
"You want to augment your design process with AI, not entirely automate it, because the models still have biases and imperfections."
Or choose a question:
More Videos
"Design is a very powerful role and at Airbnb people are ready to engage in it as a collective practice."
Rebecca GimenezWork in Progress: Service Design at Airbnb
December 3, 2024
"Designers can be first responders, not just in digital but in real disaster situations."
Lada GorlenkoTheme 2 Intro
June 9, 2022
"Research Ops needs an operational brain — it’s not the kind of brain researchers usually carry."
Brigette Metzler Dana ChrisfieldResearch Repositories: A global project by the ResearchOps Community
August 27, 2020
"Find an unindicted co-conspirator in your company with a problem you can help solve, and the rest will follow."
Discussion
June 9, 2017
"User research in government is often done without knowing what it’s called, and people aren’t always empowered to do it."
Sarah Brooks Jennifer PahlkaFireside chat with Sarah Brooks and Jen Pahlka
October 21, 2021
"Conducting retrospectives on research processes helps us identify bias, recruitment challenges, and improve methodology continuously."
Lisa Spitz Nikki BrandBuilding Trust Through Equitable Research Practices
November 18, 2022
"EMRs and EHRs have terrible user experience and are ripe for design innovation, similar to FinTech years ago."
Theresa NeilDesigning for Wellness: Specializing in Healthcare
May 22, 2024
"What if we trained Midjourney on our own style? That felt more ethical and right for our project."
Maverick Chan Claire LinFrom Doodle to Demo: AI as Our Storytelling Partner
October 23, 2025
"If there isn’t safety and connection, you get a culture of transaction and silence that kills innovation."
Alla WeinbergDesign Teams Need Psychological Safety: Here’s How to Create It
September 8, 2022
