Emerging principles for using AI in Design: What the product design team at Miro has learned from deeply integrating AI in their workflow
This video is featured in the AI and UX playlist.
Summary
All of us are experimenting with using AI in our daily work. It is difficult to write prompts, the first output is never right, AI outputs can feel quite shallow, and then there is inertia. We get it, we all yearn for familiarity in our tools and processes – but the reality is that AI is rapidly changing how design gets done. In this interactive session, design and product leaders from Miro will share their real world boards and examples of how they have been using AI. We will cover all stages of the design process – from discovery and roadmapping to design and delivery. We will end with a collective reflection on the emerging principles for using AI for design work.
Key Insights
-
•
AI is shifting design research from primarily primary user interviews to more synthesis of secondary research using tools like AI-generated mind maps.
-
•
Miro users employ AI to cluster large amounts of data, like survey responses, to speed up thematic analysis.
-
•
AI-assisted prototyping tools can transform sketches or screenshots into interactive, shareable clickable prototypes within minutes.
-
•
Designers can now bring code-like interactivity (e.g., CSS, React code) into early prototypes without directly coding themselves.
-
•
Prototyping with AI helps designers collaborate more closely and earlier with engineers, improving design handoff and alignment.
-
•
Non-designers and product managers are empowered by AI tools to create and edit visual mockups, reducing dependency on designers.
-
•
Visual communication enhanced by AI fosters better cross-functional alignment and makes complex concepts accessible to diverse teams.
-
•
AI tools still require precise prompts and patience due to limitations like AI forgetting previous context (goldfish syndrome).
-
•
Current AI prototyping workflows often produce disconnected artifacts not fully collaborative yet, showing room for integration improvement.
-
•
Miro is actively experimenting with embedding AI features throughout the product development lifecycle, including AI prototyping and collaborative editing.
Notable Quotes
"AI is not just speeding up what I used to do, it's changing what I used to do."
"AI can act like a super eager intern who's very confident but sometimes gets things wrong."
"You can take a quick sketch, put it in an AI agent, and ask it to bring it to life."
"Design handoff is really about cozying up with engineers and getting closer to the final product."
"Now it's really accessible for everyone, not just designers, to do visual thinking using these tools."
"I can convert a screenshot into an editable mockup right inside Miro without bothering a designer."
"Visual communication is still really important—it's always better to show rather than tell."
"We need to let go of perfectionism and favor efficiency when using AI in product work."
"AI prototypes can get lost on Slack because they're not always collaborative or integrated yet."
"There’s never been a better time for designers to get their hands on tools that seemed far away before."
Or choose a question:
More Videos
"OKRs can sometimes suck the oxygen out of the room if they focus only on bottom-line results, missing process and experience."
Bria Alexander Benson Low Natalya Pemberton Stephanie GoldthorpeOKRs—Helpful or Harmful?
January 20, 2022
"Innovation is not a spice that you sprinkle on and suddenly magical new things come out."
Jeff GothelfInnovation Studios: the Engines of Enterprise Experimentation
May 14, 2015
"SAFe is very developer-centric and was originally designed for construction—the code production part of software."
Jack MoffettSAFe or Sorry?
May 29, 2019
"Evals are the key to knowing when an AI’s output is good enough."
Peter Van DijckBuilding impactful AI products for design and product leaders, Part 1: The new product journey
July 16, 2025
"The team doesn’t understand who’s responsible for what or the difference between a design manager and a design lead."
Dianne QueReal Talk: Proving Value through a Scrappy Playbook
October 23, 2019
"Align on what you’re looking for before the interview to evaluate non-traditional candidates fairly."
Discussion
June 9, 2017
"Operational success cannot always be quantified through numbers; people are messy and complicated."
Amy ThibodeauOpening Keynote: Process and Ambiguity
October 23, 2019
"The organization’s website structure often mirrors its internal organizational structure and decision-making."
Sheryl Cababa Alexis OhThinking in systems to address climate with Sheryl Cababa
June 12, 2024
"Fear is in the air as AI seems to be coming for our jobs, but fear doesn’t suit us—we are too optimistic, too creative, and too valuable."
Brendan JarvisIt was the Best of Times. It was the Worst of Times.
September 25, 2024
Latest Books All books
Dig deeper with the Rosenbot
How do enterprises balance qualitative and quantitative tools while integrating AI into UX research workflows?
Who are natural allies for healthcare UX professionals inside complex healthcare systems, and how do you engage them?
What is automation bias and how can UX design mitigate its risks in AI-augmented clinical decision support?