Claim OwnershipBehind the Craft
Subscribed: 33Played: 522
Subscribe
© Peter Yang
Description
Expert interviews and guides to help you level up as a product leader and creator fast.
85 Episodes
Reverse
As VP of Alexa, Daniel builds product for 600M Alexa devices. He had a great answer to my tough question: “Why has it taken so long to add AI to Alexa?” and then gave a live demo of what an AI-powered Alexa looks like. We also had a great chat about how to apply Amazon’s working backwards process to build useful AI products.Daniel and I talked about:(00:00) The real reason Amazon delayed adding AI to Alexa(03:21) Live demo: Alexa uses AI to book Warriors tickets under $100(09:21) Which AI model(s) power Alexa behind the scenes?(11:50) How to build AI products using Amazon's PR/FAQ process(18:30) Speed vs quality: When to ship fast vs when to wait(23:00) Why Amazon pairs "invent" and "simplify" together(26:00) The future of AI voice assistants beyond your homeThanks to our sponsors:Amplitude: See all your feedback in one place https://amplitude.com/ai-feedback?utm_campaign=fy25q4-ai-feedback-launch&utm_source=newsletter&utm_medium=organic-social&utm_content=creator-economyLinear: The best platform for AI agents https://linear.app/partners/behind-the-craftGet the takeaways: https://creatoreconomy.so/p/an-inside-look-at-what-alexa-can-do-with-aiWhere to find Daniel:X: https://www.linkedin.com/in/danielrausch/Website: http://alexa.amazon.com/📌 Subscribe to this channel – more interviews coming soon!
Xinran is a top AI instructor who has taught 100s of product teams how to design and prototype with AI. He shared 5 practical techniques to avoid generating AI slop — from side-by-side exploration to reverse prompting to component libraries — that you can start trying today. If you want to level up on AI prototyping, this is a must watch.Xinran and I talked about:(00:00) The 5 gaps in vibe coding that lead to generic designs(04:28) [Step 1] Custom GPT generates perfect specs before prompting(12:04) [Step 2] Magic Patterns canvas for side-by-side iteration tracking(15:56) [Step 3] Inspiration command generates 4 unique designs instantly(20:45) [Step 4] Mix-match components across prototypes with Subframe(24:10) [Step 5] Toggle between AI mode and manual design editing(28:34) Reverse prompting: Make AI extract your design system(32:19) Pair component libraries with instructions to avoid AI slopGet the takeaways: https://creatoreconomy.so/p/a-proven-5-step-system-to-prototype-apps-with-ai-xinran-maWhere to find Xinran:Newsletter: https://designwithai.substack.comLinkedIn: https://www.linkedin.com/in/davidmaxinran/📌 Subscribe to this channel – more interviews coming soon!
1Tanay is the CEO and co-founder of Wispr Flow, my favorite app to dictate to AI 10x faster than typing. I asked him to do a live tutorial on how to get the most out of AI voice dictation, how his brain-to-text device reads your thoughts without speaking, and how he built an AI product that has 70% annual retention (unheard of!) by NOT focusing on ARR.Tanay and I talked about:(00:00) Why typing 5 hours a day is killing your productivity(06:29) Live tutorial: Using voice to draft emails, write code, and more(09:19) The brain-to-text device that reads your thoughts without speaking(16:24) How to teach Wispr Flow your writing style across every app(22:05) Why Tanay studies gaming instead of software for inspiration(29:03) "I told my board: We're killing ARR as our North Star metric"(31:36) Why "agents" is the dumbest term in AI (and what matters instead)(35:55) What motivated young Tanay to steal his mom's laptop to code Thanks to our sponsors:Bolt: Create stunning apps and website with AI https://bolt.fyi/peter-yangLinear: The best platform for agents https://linear.app/partners/behind-the-craftGet the takeaways: https://creatoreconomy.so/p/full-tutorial-how-to-use-voice-ai-to-write-and-code-faster-wispr-flow-tanay Where to find Tanay:LinkedIn: https://www.linkedin.com/in/tankots/Get Wispr Flow: https://ref.wisprflow.ai/peter-yang📌 Subscribe to this channel – more interviews coming soon!
As the head of design at Cursor, Ryo is at the cutting edge of designers who ship code instead of mocks. He showed me how he built a retro OS with AI and did a live demo of adding a new feature using Cursor’s new agent mode. We also covered how to avoid AI design slop and how the Cursor team reached $29B valuation without full-time PMs.Ryo and I talked about:(00:00) Why designers should go directly to code(02:06) Building a retro calculator app in one shot with plan mode(08:04) How Ryo manages multiple AI agents at once in Cursor(15:18) How Cursor builds without PMs and who does the PM work instead(16:43) How to avoid creating purple AI design slop (it’s not prompting)(20:01) Inside RyOS: A beautiful retro operating system built with AI(30:22) How to turn vague ideas into detailed specs with Cursor(37:47) The fastest way for PMs and designers to learn CursorThanks to our sponsors:Reforge: AI prototyping tool for product builders - https://reforge.com/peterLinear: The best platform for AI agents - https://linear.app/partners/behind-the-craftGet the takeaways: https://creatoreconomy.so/p/design-to-code-with-cursor-head-of-design-ryo-luWhere to find Rio:X: https://x.com/ryolu_Website: https://ryo.lu/📌 Subscribe to this channel – more interviews coming soon!
Ami is the one of my favorite product leaders, period. In my new episode, she breaks down why shipping fast beats the best strategy, how to build simple products that win, how to ask AI for brutally honest feedback, and more. Ami led product at Faire and WhatsApp, but above all she just has great, practical advice for all builders.Ami and I talked about:(00:00) Why perfect strategy + poor execution = a waste of time(05:21) The ChatGPT prompt to get brutally honest feedback (11:19) Do the simple thing first (build for the most tired person)(16:51) The one question Ami asks to test every product decision(25:35) Why your annual plan is probably a waste of time(32:40) How to short-circuit slow approval processes as a PM(36:47) Ami's Monday ritual to protect her calendar for deep work(42:01) The future of PM: Jack-of-all-trades utility players(46:36) Parenting in the AI era and how to teach resilienceThanks to our sponsors:Composio: Use AI to take action across 500 apps https://getrube.link/peterLinear: Try the platform for AI agents https://linear.app/partners/behind-the-craftGet the takeaways: https://creatoreconomy.so/p/7-counterintuitive-lessons-from-whatsapp-head-of-product-ami-voraWhere to find Amy:LinkedIn: https://www.linkedin.com/in/amvora/Newsletter: https://amivora.substack.com/📌 Subscribe to this channel – more interviews coming soon!
Colin has taught 1000s of students how to build SaaS apps with AI. In this episode, he showed me exactly why my vibe coded prototype was insecure and how to convert it into a real SaaS app with auth, payments, and more. If you want to learn to build SaaS apps in 40 minutes with Cursor and Claude Code, then this episode is for you.Colin and I talked about:(00:00) The 7 components that every real SaaS app needs(01:44) Client, server, database: What most prototypes miss(08:57) Live demo: Adding Stripe, auth, and databases to my photo app(16:45) Why starting with templates beats prompting from scratch(20:30) The Supabase security flaw in most vibe coded apps(25:35) Why AI shouldn't touch your database directly(35:00) 4-steps to ship a real SaaS app that people will pay for(38:15) Why tech credentials no longer matter (and what does instead)Thanks to our sponsors:Composio: Use AI to take action across 500 apps https://getrube.link/peterLinear: Try the platform for AI agents https://linear.app/partners/behind-the-craftGet the takeaways: https://creatoreconomy.so/p/full-tutorial-turn-your-prototype-into-a-real-saas-app-ai-colin-matthewsWhere to find Colin:LinkedIn: https://www.linkedin.com/in/colinmatthews-pm/Course: https://maven.com/tech-for-product/vibe-code-your-next-side-project📌 Subscribe to this channel – more interviews coming soon!
Wade is the co-founder and CEO of Zapier. We’re both sick of everyone calling everything an “AI agent” so we had some real talk about what actually works instead. Wade gave me a practical demo of his AI workflow that triages 100+ emails to 10 and shared exactly how to find automation opportunities on your calendar.Wade and I talked about:(00:00) Why most people asking for agents actually want workflows(01:25) The AI automation spectrum explained with real examples(05:16) Live demo: Wade's email agent that triages 100+ emails down to 10(13:27) The difference between APIs vs MCPs(18:52) Making Zapier AI-first: Why the CEO memo isn’t enough(24:08) Wade's response to AI influencers saying "RIP Zapier"(32:09) How Zapier tests for AI fluency in job interviews(35:31) How to identify what to automate with AI in your calendarThis episode is brought to you by Vellum.Use the code AIAGENTS25 to get 25% off your first 3 months with Vellum: https://vellum.ai/?utm_source=podcast&utm_medium=paid&utm_campaign=PeterYangPodcast📌 Get my top 10 takeaways: https://creatoreconomy.so/p/ai-agents-clearly-explained-in-40-minutes-zapier-wade-fosterWhere to find Wade:X: https://x.com/wadefosterWebsite: https://zapier.comSubscribe to this channel – more interviews coming soon!
Everyone calls their AI product an “agent” but Notion’s actually live up to the hype. It took Akshay (Notion’s co-founder) and Ryan (AI lead) 2 years of failure to build agents that can create databases, respond to Slack, and more. We had a great chat about their most surprising lessons from building the best AI agents for work.We talked about:(00:00) What it really took to build agents that actually work (01:38) Live demo: Watch a database build itself in real-time (04:56) How Akshay writes docs by just talking to AI 90% of the time (20:15) The real difference between AI slop and useful AI agents (34:43) Personalizing agents with custom memory and instructions (39:59) Live demo: Building a custom Notion agent for Slack (49:03) What Notion looks for when hiring AI-native buildersGet the takeaways: https://creatoreconomy.so/p/how-notion-built-the-best-ai-agents-for-work-akshay-ryanWhere to find:Akshay: https://x.com/akothariRyan: https://x.com/_ryannystromNotion AI agents: https://www.notion.com/blog/introducing-notion-3-0📌 Subscribe to this channel – more interviews coming soon!
Josh is the the VP of Gemini, Google Labs (NotebookLM), and AI Studio and widely considered one of Google’s most beloved leaders. In our interview, he demoed how to get the most out of Gemini and NotebookLM, the startup culture inside Google, and where he thinks Gemini is headed next.We talked about:(00:00) How Josh brings startup hustle to Google(01:19) Live demo of Nano Banana's top image use cases(07:12) Using NotebookLM to turn 70 sources into talking slides(12:36) How Google Labs shipped Flow TV in 86 days(18:20) The #1 way to move fast in big companies(22:02) What Josh looks for when hiring (hint: side projects)(31:32) Why we won't be typing to AI chatbots in the future(38:44) Gemini's future as a proactive assistant that knows your lifeGet the takeaways: https://creatoreconomy.so/p/inside-gemini-and-notebooklm-how-google-is-shipping-non-stop-josh-woodwardWhere to find Josh: X: https://x.com/joshwoodward Website: https://gemini.google.comhttps://labs.googlehttps://aistudio.google.com/📌 Subscribe to this channel – more interviews coming soon!
Today, I want to share a new episode with Ryan Carson.Ryan is a serial founder who has developed an amazing 3-file system to vibe code without frustration that has 5,000+ stars on Github. In our interview, he demoed adding a new feature to his production app by using AI to create a spec, generate atomic tasks, and build automated tests for each task.Ryan and I talked about:(00:00) Why his 3-file AI coding workflow works so well(03:22) Explaining each file: PRD, atomic tasks, test-driven development(08:02) Live demo: Building a new feature from scratch(22:32) How to practice test-driven development to avoid bugs(34:18) How to get AI to be your tutor to become more technical(42:03) Pain pills vs vitamins: Why divorce is a great AI business(45:23) How to start a one-person company with AI's helpGet the takeaways: https://creatoreconomy.so/p/full-tutorial-a-proven-3-file-system-to-vibe-code-production-apps-ryanWhere to find Ryan:X: https://x.com/ryancarsonWebsite: https://www.ryancarson.com/📌 Subscribe to this channel – more interviews coming soon!
Today, I want to share a new episode with Hamel Husain.Hamel has trained 2,000+ PMs and engineers from companies like OpenAI, Anthropic, and Google on how to run AI evals. In my new episode, he shares a free master class on how to build evals for a real AI agent in just 50 minutes using a simple spreadsheet. I learned a lot from Hamel and I think you will too.Hamel and I talked about:(00:00) What the most valuable part of evals is(01:25) Live walkthrough: Analyzing 100 real production traces(09:50) Creating the eval criteria using a simple spreadsheet(24:44) Why binary pass/fail ratings beat 1-5 scores every time(28:52) The agreement metric trap that fools most PMs(30:08) True positive and negative rates explained(36:00) How to set up continuous evals in productionGet the takeaways: https://creatoreconomy.so/p/ai-evaluations-crash-course-in-50-minutes-hamel-husainWhere to find Hamel:X: https://x.com/HamelHusainWebsite: https://hamel.dev/📌 Subscribe to this channel – more interviews coming soon!
Today, I want to share a new episode with Meaghan Choi.As the design lead for Claude Code, Meaghan not only designs new features but also ships code on a regular basis. She showed me her exact design to code workflow along with her top 3 use cases for Claude Code. This interview is a must-watch if you’re a designer or PM who dreams of shipping to production. Meaghan and I talked about:(00:00) Why shipping to prod as a designer feels "terrifying and magical"(02:36) Top 3 design workflows with Claude Code(07:20) How designers can get engineers to let them ship code(11:06) Live demo: From Figma design to working code in minutes(19:10) Custom Claude.md files to make AI work for designers(22:47) How Anthropic ships features in days, not months(28:22) Meaghan's favorite Claude Code shortcuts and pro tips(33:58) The future of design roles in an AI-native worldBrought to you by:Linear — The operating system for AI agents. Get 6 months free of Linear Business here: https://linear.app/behind-the-craftWhere to find Meaghan:X: https://x.com/meag_han_cWebsite: http://clau.de/peteryang📌 Subscribe to this channel – more interviews coming soon!
Today, I want to share a new episode with Cat Wu.Cat is the product lead for Claude Code and I got her to share how one of the most AI-native teams in tech actually works. Highlights include getting user feedback every 10 minutes, going straight to prototypes instead of docs, and designers checking in code directly. Cat also shared her 3 best Claude Code tips and what’s next for the product.Cat and I talked about:(00:00) The process behind the best Claude Code features(05:00) How engineers can own features from idea to launch(10:04) Getting feedback every 10 minutes from 1000+ users(14:00) How designers and PMs can ship production code(19:58) How the Claude Code team does AI evaluations(29:04) 3 tips from Cat to get the most out of Claude Code(30:12) Why your Claude.md file is so important (33:32) What's next for Claude Code Thanks to our sponsor: Lorikeet: The AI concierge that gets it done lorikeetcx.ai/peter My top 10 takeaways: https://creatoreconomy.so/p/inside-claude-code-how-an-ai-native-actually-works-cat-wuWhere to find Cat:X: https://x.com/_catwuWebsite: https://www.anthropic.com/claude-code📌 Subscribe to this channel – more interviews coming soon!
Today, I want to share a new episode with Alex Finn.Alex is a founder who has built a complete “Claude Life” operating system to automate research, curate AI news, analyze brain dumps, and more. I asked him to walk through exactly how to set up this system using Claude Code slash commands and sub-agents in just 25 minutes.Alex and I talked about:(00:00) How Alex uses Claude Code to automate his life (04:18) Inside "Claude Life" — Alex’s life operating system(05:29) The newsletter research agent that saves hours weekly(09:09) How to use custom slash commands and sub-agents (14:41) The most important skill that everyone needs in 2025(18:01) Brain dump analysis to find new content pillars(21:14) Daily brief agent that aggregates AI newsGet the takeaways: https://creatoreconomy.so/p/full-tutorial-build-an-ai-life-copilot-with-claude-code-alex-finnWhere to find Alex:X: https://x.com/AlexFinnXWebsite:https://www.creatorbuddy.io/📌 Subscribe to this channel – more interviews coming soon!
Today, I want to share a new episode with Nan Yu (Linear’s Head of Product).Despite only having 2 PMs, Linear has scaled to over 15,000 companies including OpenAI and Ramp. In our chat, Nan and I did a fun exercise to rank what PM skills still matter in the AI era and he also demoed Linear’s new AI agents that can write code, triage tickets, and analyze customer feedback.Nan and I talked about:(00:00) Why Linear is a billion dollar company with just 2 PMs (03:22) Ranking PM skills: What survives vs gets disrupted by AI(11:10) Why strategy is actually being disrupted by AI(21:51) The new skills PMs must build: context and agent management(26:57) Craft vs speed: Linear's 10% rule for shipping fast(38:09) Live demo: Using MCP to analyze customer feedback instantly(53:04) Delegating entire backlogs to AI agents with one command(57:12) Linear's future as an operating system for human-AI collaborationGet the takeaways: https://creatoreconomy.so/p/ranking-every-pm-skill-what-still-matters-gets-disrupted-by-ai-nan-yu-linearWhere to find Nan:X: https://x.com/thenanyuWebsite: https://linear.app/📌 Subscribe to this channel – more interviews coming soon!
Today, I want to share a new episode with Aman Khan.The best way to learn about AI evaluations is to watch 2 PMs build them live from scratch. In our new episode, Aman and I walk through creating evals for an AI customer support agent — from labeling a golden dataset to aligning LLM judges. This is the complete beginners AI eval course you've been waiting for.Aman and I talked about:(00:00) What are AI evals and how to get good at them (02:52) The 4 types of AI evaluations everyone should know(06:08) Live demo: Building evals for a customer support agent (10:29) Using Anthropic's console to generate great prompts (15:13) Creating the evaluation criteria(17:40) Adding human labels to the golden dataset (31:05) Scaling evals with LLM-judge prompts (38:21) How to align LLM judges with human judgmentGet the takeaways: https://creatoreconomy.so/p/complete-beginner-course-on-ai-evaluations-aman-khanWhere to find Aman:X: https://www.linkedin.com/in/amanberkeley/Website: https://arize.com/📌 Subscribe to this channel – more interviews coming soon!
Today, I want to share a new episode with Lee Robinson.Lee is the VP of Developer Experience at Cursor and a legend in his field. While most people are still vibe coding, Lee showed me how to build apps properly using planning, test-driven development, AI agent workflows, and more. This is a must-watch tutorial for beginners who want to learn how to build with AI the right way.Lee and I talked about:(00:00) How the way we build software is fundamentally changing(03:49) Live demo: Building a music tracking app with Cursor(5:17) The critical setup phase most people skip (tests, git, linting)(16:03) Foreground vs background agents and when to use each(27:34) How to create cursor rules that compound your workflows(37:31) Why experienced engineers shouldn't fear AI tools(42:19) Essential advice for PMs who want to learn technical skills(44:48) How Cursor builds products without any PM(47:18) The future of generalist engineers in an AI worldGet the takeaways: https://creatoreconomy.so/p/cursor-tutorial-for-beginners-from-cursor-head-of-ai-education-lee-robinsonWhere to find Lee:X: https://x.com/leerobWebsite: https://leerob.com/📌 Subscribe to this channel – more tutorials coming soon!
Today, I want to share a new episode with Ben Erez.Ben is a former Meta PM who has helped 100s of people ace their PM interviews and land their dream jobs in tech. I got him to show me exactly how to ace product sense interviews and build an AI-copilot that his students say feels like having a "calibrated interviewer that's available 24/7."Ben and I talked about:(00:00) The current state of the PM job market(02:07) The exact structure of the product sense interview(08:58) How to build your AI interview co-pilot step-by-step(12:36) Live demo: AI co-pilot walking through a Meta interview question(13:33) Why Ben designed the AI to be the candidate, not the interviewer(25:23) How to prioritize the right user segments and problems to solve(32:13) The biggest mistakes candidates make when challenged by interviewersThis episode covers how to build a simple AI co-pilot from scratch, but you should also check out Ben’s advanced interview AI co-pilot: https://www.benerez.com/copilotGet the takeaways: https://creatoreconomy.so/p/how-to-build-an-ai-co-pilot-to-ace-your-pm-interviews-ben-erezWhere to find Ben:LinkedIn: https://www.linkedin.com/in/benerez/Website: www.benarez.com📌 Subscribe to this channel – more interviews coming soon!
Today, I want to share a new episode with Jeremy Epling.Jeremy is the CPO of Vanta and former VP of Product at Github. He showed me the exact template that he used to get his entire team to prototype with AI, his favorite AI workflows for PM work, and why now might be the best time to be an IC PM. We also did a deep dive on how Vanta ran AI evaluations for their new AI agent.Jeremy and I talked about:(00:00) Why prototypes beat PRDs (01:43) The exact template that got his entire PM team prototyping(05:14) From prototype to product: live demo of Vanta’s AI agent(08:56) How to run prototype-first product reviews(12:47) Top AI workflows that save Jeremy hours each week(19:08) Is now the best time to be an IC PM?(25:03) Advice for big tech PMs facing industry changes(30:35) Separating the hype from craft for AI products(36:16) Deep dive on AI evaluations for AI agentsWhere to find Jeremy:LinkedIn: https://www.linkedin.com/in/jeremy-epling-j40/ Website: https://vanta.com Get the takeaways: https://creatoreconomy.so/p/how-to-get-your-team-to-start-prototyping-with-ai-jeremy-vanta📌 Subscribe to this channel – more interviews coming soon!
Meng is the founder of Aura, an AI prototyping tool for designers. He has spent 100s of hours using AI to create beautiful designs that don’t look like generic AI slop. Watch as he shares his exact process in this episode — from prompting to layouts to animations, and more without having to code.Timestamps:(00:00) Why most AI websites look generic and how to fix it(01:19) Comparing prompts across V0, Lovable, and Aura(06:42) Using references and templates instead of blank prompts(08:54) Building a great website prompt from scratch(16:51) Why AI should augment, not replace your creativity(22:43) Adding testimonial sections and scrolling animations(29:40) How to add Spline 3D backgrounds step-by-step(36:12) The 90/10 rule: When to use AI vs manual tweaksGet the takeaways: https://creatoreconomy.so/p/use-ai-to-create-beautiful-designs-meng-toWhere to find Meng:X: https://x.com/MengToWebsite: https://aura.build/📌 Subscribe to this channel – more interviews coming soon!
Comments
Download from Google Play
Download from App Store
United States