Designing AI-first products on top of a rapidly evolving technology
This video is featured in the AI and UX playlist.
Summary
This talk addresses the distinct challenges of designing AI-first products when the foundational technology is advancing at an unprecedented pace. We will discuss the practical implications of this rapid evolution on the design process and share our insights into creating effective user experiences in such a dynamic environment.
Key Insights
-
•
AI models evolve faster than previous tech revolutions, requiring adaptive product development.
-
•
Effective AI products use evals—automated tests on real data—to continuously measure quality.
-
•
Retrieval augmented generation and tool use are practical architectural tricks to reduce AI hallucination.
-
•
AI experiences must account for user trust despite AI’s confident but sometimes inaccurate outputs.
-
•
Human factors like worker anxiety about job security are critical to address in AI adoption.
-
•
Cross-disciplinary teams are essential in AI design due to the space’s novelty and uncertainty.
-
•
Prompt engineering skills grow best through extensive real use rather than frozen techniques.
-
•
Planning AI products with expectations of improved capabilities 6-9 months ahead optimizes outcomes.
-
•
Cultural acceptance of AI use inside organizations must be actively encouraged to avoid user hiding.
-
•
User testing of AI products still requires old-school observation combined with analytics and evals.
Notable Quotes
"You can’t have good AI without good information architecture."
"Everything’s changing really quickly—if you don’t revise your plan in a few months, you’re building for a world that’s already outdated."
"Hallucinations are when AI makes up stuff—it's a fundamental property of these models."
"Retrieval augmented generation is just adding results from a search into the model’s context to make it more grounded."
"Agents are models using tools in the loop, calling normal software functions as part of their process."
"People tend to trust AI a lot because it seems very confident—even when it’s not always accurate."
"Workers are often worried about layoffs and their value when AI speeds up their process, while executives like the efficiency gains."
"You should get good at prompt engineering by using AI a lot, not by memorizing outdated tricks."
"Building evals is like building tests to know if your AI system is good enough, and you can rerun them as models improve."
"User testing for AI still means watching people use it, plus collecting analytics and running evaluations."
Or choose a question:
More Videos
"I started at absolute zero with climate knowledge and now I have clarity, confidence, credibility, and ability to contribute."
Sara ConklinA UXer’s 12-Month Journey from Climate Concern to Climate Credibility
June 26, 2025
"We didn’t explain the philosophy behind the design ops activities, so others didn’t understand why some activities couldn’t be done outside design."
Benjamin RealShowing the Value of DesignOps by Not Having a DesignOps Team
October 21, 2020
"We must create spaces that allow nature to thrive within our cities."
Lena ShenkarenkoCollaborative Wireframing for Creating Team Alignment and Shipping Better Products
October 21, 2020
"Building trust should absolutely be a core value for design ops teams aiming to steward knowledge effectively."
Maria TaylorKnowledge is Power: Managing the Lifeblood of the Design Org
October 3, 2023
"You begin research from the end—from the future to the future—asking communities to share their envisioned future first."
Liz EbengoThe Burden on Children: The Cost of Insufficient Post-Conflict Services and Pathways Forward
December 4, 2024
"Sharing small, incremental updates about research progress provides visibility and makes people appreciate the craft behind the work."
Roberta Dombrowski Sam Duong WoloszynskiMaking Research a Team Sport
March 11, 2022
"At Anthropic, 80% of the code merged to production is now written by Claude."
Rikki TeetersConcept to code: Transforming ideas into functional products with Kiro
June 10, 2026
"Look for the commonality in our definition of inclusion rather than the differences."
Saara Kamppari-MillerTheme Three Intro
September 9, 2022
"Handwritten notes have no boot up time, and that immediacy helps enter deeper flow states."
Jorge ArangoThe Best of Both Worlds: How to Integrate Paper and Digital Notes (1st of 3 seminars)
April 5, 2024
Latest Books All books
Dig deeper with the Rosenbot
What are the risks and benefits of transparency in organizations adopting AI technologies?
How can design guidelines and brand semantics be encoded to help AI and engineering teams work together?
In what ways do rough sketches invite iteration rather than defensiveness compared to polished diagrams?