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 ops’ job is like jazz rules—it provides a framework so creativity can flow without worrying about inventing structure mid-process."
Jim KalbachJazz Improvisation as a Model for Team Collaboration
November 6, 2017
"We look to work with authors we like and enjoy being around because writing a book is a long, collaborative journey."
Louis RosenfeldCoffee with Lou: Should You Write a (UX) Book?
March 7, 2024
"The difference between director and principal often lies in whether you’re inspired more by leading people or focused on outputs and craft."
Catt Small Micah Bennett Brian Carr Jessica HarlleeWhat's Next for ICs: Exploring Staff and Principal Designer Roles
February 22, 2024
"We are really good at finding problems, but the opportunity solution tree helps pick the best ones to focus on."
Marieke McCloskeyUser Science: Product Analytics & User Research
March 11, 2021
"Wonder Studio automatically segments actors, maps their movements to a 3D model, and renders a synthetic avatar video."
Llewyn Paine[Demo] Deploying AI doppelgangers to de-identify user research recordings
June 5, 2024
"Correlation doesn’t imply causation, but sometimes two things happening together do imply a causal mechanism."
Joshua NobleCasual Inference
October 6, 2023
"Choosing the right output depends on the desired outcome—from quick iterations to gaining senior leadership buy-in."
Sara LogelYour Colleagues are Your Users Too
March 29, 2023
"Learning is a marathon, not a sprint, especially in the context of online conferences."
Bria Alexander Louis RosenfeldWelcome
January 8, 2024
"Accessibility isn’t a checkbox you run automated tests for; you must involve people with disabilities to benchmark success."
Sam ProulxOnline Shopping: Designing an Accessible Experience
June 7, 2023
