Rosenverse
The Pygmalion Effect: In Which a Vibe Coding Experiment Becomes a Million Lines…

Log in or create a free Rosenverse account to watch this video.

Log in Create free account

100s of community videos are available to free members. Conference talks are generally available to Gold members.

The Pygmalion Effect: In Which a Vibe Coding Experiment Becomes a Million Lines…

Thursday, August 14, 2025 • Rosenfeld Community

This video is featured in the Josh's test playlist playlist and 1 more.

Share the love for this talk
The Pygmalion Effect: In Which a Vibe Coding Experiment Becomes a Million Lines…
Speakers: Christian Crumlish
Link:

Summary

What started as intuitive "vibe coding" with AI assistants quickly revealed why UX professionals need systematic Information Architecture approaches more than ever. Christian Crumlish will share his journey building Piper Morgan, an AI product management assistant, and the hard-won lessons about when design instincts need systematic support. You'll discover why IA principles guide AI system design, how UX professionals can extend their design impact through AI-assisted prototyping, and practical frameworks for maintaining human advocacy when everyone can generate interfaces. Bring curiosity about UX's evolving role—leave with systematic approaches for staying essential.

Key Insights

  • Vibe coding lets non-developers create functioning software quickly by describing it in natural language to AI bots.

  • Without foundational architecture and systematic methods, vibe coding leads to fragile, unmaintainable 'spaghetti' code.

  • AI bots often agree with any idea, which can be dangerous if users don't critically oversee outputs—a phenomenon dubbed the 'rocket to Mars' anti-pattern.

  • Christian found it essential to split AI assistants into personas with distinct roles to maintain clarity and reduce confusion.

  • Systematic verification, test-driven development, and documentation are vital pillars to produce reliable software with AI assistance.

  • Working hands-on with AI coding agents increased Christian’s empathy and understanding of engineers' daily challenges.

  • Modern UX and IA are indispensable in AI software development to mediate between human needs and machine capabilities.

  • Embedding ethical guardrails and values like kindness directly into AI system architecture can prevent harm and misuse.

  • Future AI solutions may favor smaller, domain-specific language models orchestrated via overarching frameworks rather than monolithic large models.

  • Despite the hype, AI-assisted development is still early-stage, requiring disciplined human oversight and patience for meaningful results.

Notable Quotes

"I thought I could skip the architecture step, but I ended up with spaghetti code that broke constantly."

"These bots will say yes to all your ideas, whether they're good or bad—that's the rocket to Mars anti-pattern."

"If I stop doing it, it stops, and I'm the human in the loop, or the monkey in the middle."

"I’ve created dedicated personas in the bots, like a chief of staff and lead developer, to keep roles clear."

"Verification first — always check existing docs and models before asking the bots to build anything new."

"Working with AI made me understand what engineers go through with setups and debugging."

"Vibe coding turns the conversation 'should designers code?' on its head — now designers can just talk to bots."

"All of us have at least some facility in adjacent disciplines now because of AI assistance."

"The bots can produce large amounts of code quickly, but many lines are test or documentation code, not production."

"Ethics needs to be baked into the architecture upfront, not tacked on later after you've built something powerful."

Ask the Rosenbot
Lisa Gironda
Opener: Chief of Staff–An unexpected journey
2024 • DesignOps Summit 2020
Gold
Anna Nguyen
Why Our Voice of the Customer is Better Than Yours
2022 • Advancing Research 2022
Gold
Vanessa Varin
Tools are moments. Capabilities compound.
2026 • Designing with AI 2026
Conference
Bria Alexander
Day 2 Welcome
2024 • DesignOps Summit 2024
Gold
Louis Rosenfeld
Opening Remarks
2023 • Design in Product 2023
Gold
Florence Okoye
AfroFuturism and UX Research
2023 • Advancing Research 2023
Gold
Louis Rosenfeld
How AI will Change DesignOps Tooling
2023 • DesignOps Summit 2023
Gold
Kritika Sony
Moving AI offscreen: Exploring failures, constraints, and recovery in physical game design
2026 • Designing with AI 2026
Conference
Dane DeSutter
Beyond the Console: The rise of the Gamer Experience and how gaming will impact UX Research across industries
2024 • QuantQual Interest Group
Peter Morville
The Architecture of Understanding
2015 • Enterprise UX 2015
Gold
Jay Bustamante
Navigating the Ethical Frontier: DesignOps Strategies for Responsible AI Innovation
2023 • DesignOps Summit 2023
Gold
Ali Jeffery
How DesignOps Helped Enable Wall Street to Work Remotely
2020 • DesignOps Summit 2020
Gold
Mohammad Hossein Jarrahi
Contextuality problem: Exploring the Benefits of Qualitative and Quantitative Research
2023 • QuantQual Interest Group
Paul Bakaus
Killing the handoff: Iterating design live in the browser on real production code
2026 • Designing with AI 2026
Conference
Jon Fukuda
Design Planning and Management Support
2023 • DesignOps Summit 2023
Gold
Janelle Estes
UX Research Trends
2021 • Advancing Research Community

More Videos

Shipra Kayan

"AI prototypes can get lost on Slack because they're not always collaborative or integrated yet."

Shipra Kayan Robert Kortenoeven Eileen Tang

Emerging principles for using AI in Design: What the product design team at Miro has learned from deeply integrating AI in their workflow

June 11, 2025

Daniel Gloyd

"Design research often acts like scientists with clipboards rather than humans in conversation."

Daniel Gloyd

Designing From the Inside Out: How Method Acting Can Inspire Design Research

February 12, 2026

Louis Rosenfeld

"LinkedIn Learning is mostly training, but here you want help in the moment, answers to your questions."

Louis Rosenfeld

You’ve got Gold! A Rosenverse demo with Lou Rosenfeld

June 9, 2026

Brad Orego

"Research is a freight train barreling through the company — build the stations and rails first with operations or risk derailment."

Brad Orego Ned Dwyer

Bringing Customer Research to More Internal Teams

March 10, 2022

Christian Crumlish

"When I was head of product, I wasn’t enough of a domain expert or business model expert to scale the company."

Christian Crumlish Aditi Ruiz Johanna Kollmann Catt Small

Morning Insights Panel

December 6, 2022

Etienne Fang

"We lead ourselves, our peers, and our stakeholders; leadership happens at all levels and in all settings."

Etienne Fang

The Power of Care: From Human-Centered Research to Humanity-Centered Leadership

March 10, 2021

Sam Proulx

"Simulation or personas can never replace testing with real users to build empathy and get accurate results."

Sam Proulx

Understanding Screen Readers on Mobile: How And Why to Learn from Native Users

June 6, 2023

Anna Poznyakov

"How do we continuously provide value throughout the product development cycle without overindexing on just one type of research?"

Anna Poznyakov Richa Prajapati

Get The Most Out Of Stakeholder Collaboration—and Maximize Your Research Impact

March 12, 2021

Peter Van Dijck

"It's cognitively easier to evaluate the work somebody else did than to do it yourself. That's why LLMs can evaluate LLMs."

Peter Van Dijck

Building new AI skills: Creating outsized UX value with evals

June 10, 2026