Skip to content
How I AIHow I AI

How this Yelp AI PM works backward from “golden conversations” to create high-quality prototypes

Priya Badger, a product manager at Yelp, shares her innovative approach to designing AI-powered products by starting with example conversations rather than traditional wireframes or PRDs. In this episode, she demonstrates how she uses Claude and Magic Patterns to prototype Yelp’s AI assistant features—from exploring conversation flows to designing user interfaces. *What you’ll learn:* 1. How to use example conversations as your first “wireframe” when designing conversational AI products 2. A step-by-step workflow for using Claude to generate and refine sample conversations that guide your AI product development 3. Techniques for creating interactive prototypes with Claude Artifacts that use real LLM responses without complex API integrations 4. How to use Magic Patterns’ Inspiration mode to rapidly explore multiple UI variations for your AI features 5. Why starting with conversations and working backward to system prompts creates more natural AI interactions 6. How to apply these AI prototyping techniques to personal projects to build your AI product management skills *Brought to you by:* GoFundMe Giving Funds—One account. Zero hassle: https://www.gofundme.com/howiai Persona—Trusted identity verification for any use case: https://withpersona.com/lp/howiai *Where to find Priya Badger:* LinkedIn: https://www.linkedin.com/in/priyamathewprofile/ Substack: https://almostmagic.substack.com/ *Where to find Claire Vo:* ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo *In this episode, we cover:* (00:00) Introduction to Priya (02:54) The unique challenges of managing AI-powered products (04:33) Using example conversations as a starting point for design (05:53) Demo: Prompting Claude to generate sample conversations (09:10) Prototyping advice (09:53) Testing with multiple example images and scenarios (15:03) Refining conversations based on qualitative assessment (15:59) Demo: Creating interactive prototypes with Claude Artifacts (21:22) Using Magic Patterns to design the user interface (25:30) Exploring multiple design variations with Inspiration mode (31:02) Quick summary (33:35) How to apply these AI prototyping techniques to personal projects (38:57) Final thoughts *Tools referenced:* • Claude: https://claude.ai/ • Magic Patterns: https://magicpatterns.com/ • Lovable: https://lovable.ai/ • Figma: https://www.figma.com/ • ChatGPT: https://chat.openai.com/ *Other references:* • How to build prototypes that actually look like your product | Colin Matthews (product leader, AI prototyping instructor at Maven): https://www.lennysnewsletter.com/p/how-to-build-prototypes-that-actually _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._

Claire VohostPriya Badgerguest
Oct 20, 202541mWatch on YouTube ↗

At a glance

WHAT IT’S REALLY ABOUT

Yelp AI PM prototypes by reverse-engineering “golden conversations” into interfaces

  1. The episode showcases a practical AI product management workflow that begins with writing (and generating) exemplar “golden conversations” to define the intended user experience before formal requirements.
  2. Priya uses Claude to generate and refine multi-scenario conversations—especially for a new Yelp Assistant feature that analyzes user-uploaded photos for home service requests—then extracts quality criteria and system-prompt direction from those examples.
  3. Next, she turns the conversations into an interactive prototype using Claude Artifacts, enabling realistic testing of response length, latency feel, and overall UX in a chat UI without setting up API keys.
  4. Finally, she explores front-end UI variations in Magic Patterns (including Inspiration mode) to iterate on entry points like “Start with a photo,” emphasizing rapid solution-space exploration and collaboration with design/engineering.

IDEAS WORTH REMEMBERING

5 ideas

Start AI product design from the intended conversation, not the UI.

Priya’s “golden conversations” approach defines what success looks like in the user’s words first, then works backward into prompts, flows, and interface requirements—mirroring the end-user experience early.

Treat variability as a core AI product constraint and design for quality explicitly.

Because LLM outputs differ run-to-run, she focuses on methods to drive consistent quality: multiple examples, qualitative review, and eventually a rubric—aligned with the idea that “evals are the new PRD.”

Use multi-scenario, multimodal examples to uncover gaps and patterns fast.

Testing across diverse images (cracked porch, appliance error codes, wasp nest, bathroom renovation) reveals whether image recognition is robust and whether the conversation flow generalizes across categories.

Iterate conversations by giving targeted critique, then re-generating in bulk.

She provides concrete feedback (be more opinionated with recommendations, avoid asking about budget) and asks the model to rewrite all examples—accelerating convergence on a consistent voice and policy.

Interactive prototypes surface UX issues that text transcripts hide.

In an artifact/chat UI, message length, scrolling, and perceived waiting time (“three dots”) can make acceptable copy feel too long or slow—critical signals before engineering investment.

WORDS WORTH SAVING

5 quotes

So we start with golden conversations. What’s the experience that you’re trying to drive?

Priya Badger

Write an example conversation… and you’re working backwards from that example conversation.

Claire Vo

A lot of people talk about, like, evals are the new PRD. And this is, like, the very early step of getting… to the eval process.

Priya Badger

Sometimes a response that looks fine when you have it in a doc feels really long when you see it in… the little chat bubble.

Priya Badger

I think it’s helpful to actually think about the ways that AI is different than a human.

Priya Badger

AI product management: UI vs behind-the-scenes promptsGolden conversations as requirementsMultimodal testing with diverse imagesQualitative review → rubric/evals thinkingConversation refinement via LLM rewritesInteractive prototyping with Claude ArtifactsUI ideation with Magic Patterns Inspiration mode

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

High quality summaries for YouTube videos. Accurate transcripts to search & find moments. Powered by ChatGPT & Claude AI.

Add to Chrome