The secret to better AI prototypes: Why Tinder's CPO starts with JSON, not design | Ravi Mehta
Ravi Mehta, now a product advisor, has built and scaled products used by millions. His past roles include Chief Product Officer at Tinder, Entrepreneur in Residence at Reforge, and senior product leadership positions at Facebook, TripAdvisor, and Xbox. In this episode, Ravi demonstrates his data-driven approach to AI prototyping that produces dramatically better results than traditional "vibe prototyping." He also shares his structured framework for generating professional-quality images in Midjourney that look like they were shot by a professional photographer. *What you’ll learn:* 1. Why most product managers and designers are “vibe prototyping” with AI and getting mediocre results 2. How to use JSON data models instead of design systems as the foundation for better AI prototypes 3. A simple three-part framework for structuring Midjourney prompts to get professional-quality photos 4. How to use Claude and Unsplash’s MCP server to generate realistic data and images for your prototypes 5. Why real data (not Lorem Ipsum) is critical for getting meaningful feedback from stakeholders 6. The film stock “cheat code” that instantly elevates your AI-generated photos *Brought to you by:* Google Gemini—Your everyday AI assistant: https://ai.dev/ Persona—Trusted identity verification for any use case: https://withpersona.com/lp/howiai *Where to find Ravi Mehta:* Website: https://www.ravi-mehta.com/ Reforge: https://www.reforge.com/profiles/ravi-mehta LinkedIn: https://www.linkedin.com/in/ravimehta/ X: https://x.com/ravi_mehta *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 Ravi and data-driven prototyping (02:31) The problem with “vibe prototyping” in product development (04:18) Spec-driven prototyping vs. data-driven prototyping (05:27) Demo: Spec-driven approach to prototyping (08:26) Limitations of the basic AI prototype approach (11:24) The data-driven prototyping approach explained (12:08) Demo: Data-driven prototyping (17:45) Creating a prototype with the generated JSON data (23:33) Comparing the quality difference between approaches (26:44) Modifying the prototype (28:53) Benefits of this approach (34:40) Structured Midjourney prompting (36:20) The subject-setting-style framework for better image prompts (44:27) Using camera metadata to refine your results (48:54) Lightning round and final thoughts *Tools referenced:* • Claude: https://claude.ai/ • Reforge Build: https://www.reforge.com/build • Midjourney: https://www.midjourney.com/ • Unsplash MCP: https://github.com/okooo5km/unsplash-mcp-server-go?utm_source=chatgpt.com *Other references:* • Reforge AI Strategy Course: https://www.reforge.com/courses/ai-strategy _Production and marketing by https://penname.co/._ _For inquiries about sponsoring the podcast, email jordan@penname.co._
