Agents in production from a designer's perspective
Hosted by Jason Liu and David Kim
What you'll learn
Shipping agents: a designer's journey
How design thinking shapes agent development from concept through production deployment and iteration
Eval infrastructure & observability for designers
Why these technical systems matter for design decisions and how they enable better agent experiences
Real lessons from building Loop
Concrete examples of design challenges, wins, and failures when creating a production AI agent
Why this topic matters
Designers are essential to making AI agents people actually want to use. Understanding evaluation and observability from a design lens helps you make smarter product decisions and work better with engineers. Learn how design thinking shaped Loop's production journey and gain practical insights to ship your own agents successfully.
You'll learn from
Jason Liu
Consultant at the intersection of Information Retrieval and AI
Jason has built search and recommendation systems for the past 6 years. He has consulted and advised a dozens startups in the last year to improve their RAG systems. He is the creator of the Instructor Python library.Â
David Kim
Design engineer, Braintrust
Engineer turned designer. Passionate about developer tools and experiences.
worked with
Go deeper with a course
Featured in Lenny’s List
Systematically Improving RAG Applications

Jason Liu
Staff machine learning engineer, currently working as an AI consultant
Keep exploring