{"type":"rich","version":"1.0","provider_name":"Transistor","provider_url":"https://transistor.fm","author_name":"Engineering Evolved","title":"From Napkins to Agents: How AI Rewired Product Design","html":"<iframe width=\"100%\" height=\"180\" frameborder=\"no\" scrolling=\"no\" seamless src=\"https://share.transistor.fm/e/513726c7\"></iframe>","width":"100%","height":180,"duration":2134,"description":"In this episode of Engineering Evolved, Tom sits down with Amelia Prasad, Director of Product at Concept to Cloud, to trace how AI has reshaped the day-to-day of UX and product design. Amelia — who came to product from astrophysics and climate science — walks through the shift from manual research, whiteboards and \"back-of-the-napkin\" sketches to building zero-to-one products directly in Claude Code.It's not a hype reel. Amelia is candid about the friction: learning version control from scratch, bloated six-thousand-line files, the designer-to-developer handoff problem, and the diminishing returns of heavy token usage in tools like Claude Design and third-party wrappers such as Lovable. Her current answer is a marriage of tools — passing work back and forth between Claude Code and Figma via MCP — so prototyping speed and real usability, accessibility and design-system rigour can each live where they belong.They close on what the next 12 months might hold: more human-led user research, not less, and why juniors and design intuition still matter in an industry tempted to hire only senior builders.Chapters00:00 — Welcome & introducing Amelia02:53 — From astrophysics to product design03:33 — The pre-LLM UX workflow: manual research & competitive analysis05:23 — Old-school tooling: Figma, Miro, Maze, pen & paper06:56 — The lost art of napkin sketches and paper prototyping07:57 — Meeting at Princeton: first exposure to LLMs08:52 — AI workflows before AI building: the interview note-taker11:02 — Stepping into Claude Code as a non-developer13:45 — Handing off code on a small team: value and limits15:17 — Guardrails, context and the handoff problem20:02 — Lovable, Cursor and the trouble with wrappers21:05 — Claude Design: token cost and diminishing returns22:45 — Figma's MCP and the two-way handoff24:50 — A suite of tools: knowing when to hand off to which29:06 — Why active engagement in Figma beats waiting on the terminal33:02 — The next 12 months: user research,...","thumbnail_url":"https://img.transistorcdn.com/PxMdoqfN_29mQkukm_nn1W_IIYV1IIAUO08NXqUzges/rs:fill:0:0:1/w:400/h:400/q:60/mb:500000/aHR0cHM6Ly9pbWct/dXBsb2FkLXByb2R1/Y3Rpb24udHJhbnNp/c3Rvci5mbS8wNTI4/MmI4OTJkZTVkNjZi/YTExNjA5ZTFlYjRm/M2U0NC5wbmc.webp","thumbnail_width":300,"thumbnail_height":300}