Advertise on podcast: Behind the Craft

Kieran my favorite Claude Code power user and teacher. In our interview, he walked through his Compound Engineering system that makes Claude Code better every time you use it. This same system has been embraced by the Claude Code team and others. Kieran is like Morpheus introducing me to the matrix, so don’t miss this episode 🙂 Kieran and I talked about: (00:00) The compound engineering loop: Plan, work, assess, compound (03:40) Live demo: The /workflows command to plan your app (13:25) How to use Claude Skills as just-in-time context (25:27) Why you should always ask Claude to ask you questions first (30:00) Live demo: Using Playwright MCP as your AI QA team (35:03) Code reviews by AI agents playing security, architect, and more (40:33) The LFG command: one prompt to go from 0 to production (46:39) Slash commands vs sub-agents vs skills — when to use each Get the takeaways: https://creatoreconomy.so/p/how-to-make-claude-code-better-every-time-kieran-klaassen Where to find Kieran: X: https://x.com/kieranklaassen Website: https://cora.computer/ GitHub: https://github.com/EveryInc/compound-engineering-plugin 📌 Subscribe to this channel – more interviews coming soon!

Peter is the creator of OpenClaw (formerly Molt - the name keeps changing 😅), the hottest AI right now with 2M visitors in a week. In our interview, Peter shared is personal favorite use cases including using Claw to check in to flights, control his home, and more. We also talked about his hot takes such as no plan mode or MCPs. Peter and I talked about: (00:00) “It’s like having a new weird friend that lives on your computer” (03:43) “It sent me a voice message but I never set that up” (09:04) How to install OpenClaw in one line (14:53) “It watched my security camera all night and found this” (16:07) Using OpenClaw to check in flights, change lights, and adjust his bed (19:42) Why 80% of your phone apps will disappear (22:20) Peter’s AI coding hot takes: No plan mode, MCPs suck, and more (36:56) The way to learn AI is to play Thanks to our sponsors: Linear: The AI agent platform for modern teams https://linear.app/behind-the-craft Granola: The AI meeting notes app that saves you hours. granola.ai/peter Replit: From 0 to full stack app in 2 min https://replit.com/?utm_source=creator&utm_medium=organic&utm_campaign=creator_program&utm_content=peteryang 📌 Get the takeaways: https://creatoreconomy.so/p/how-openclaws-creator-uses-ai-peter-steinbergerWhere to find Peter: X: https://x.com/steipete Website: https://openclaw.ai/ Subscribe to this channel - more tutorials coming soon!

Logan is the Product Lead for Google AI Studio. I got him to give us an inside look at how he uses AI Studio to build AI Studio (very meta) and how his team ships at startup speed inside Google. AI Studio is the feature that I rely on the most to do my product job better, so don't miss this tutorial. Logan and I talked about: (00:00) Tour of Google AI Studio's Build mode (06:29) Live demo: Building a social media content generator (09:31) How Logan uses AI Studio to build AI Studio (11:34) Cloning the AI Studio UI in 68 seconds (12:58) Getting AI to show you 5-6 design options in one UI (17:20) Live demo: Building a restaurant finder with Google Maps (21:12) Using annotate mode to give visual feedback (34:09) "There's one mode and the mode is we ship fast" (36:00) What Logan looks for when hiring PMs Thanks to our sponsors: Linear: The AI agent platform for modern teams https://linear.app/behind-the-craftReplit: From 0 to full stack app in 2 min https://replit.com/?utm_source=creator&utm_medium=organic&utm_campaign=creator_program&utm_content=peteryang 📌 Get the takeaways: https://creatoreconomy.so/p/master-google-ai-studio-for-prototyping-logan-kilpatrick Where to find Logan: X: https://x.com/OfficialLoganK Website: https://aistudio.google.com/apps Subscribe to this channel - more interviews coming soon!

Sumeet is the Head of Data at Brex and came personally recommended by the Claude Code team. In our episode, he showed me how to use Claude Code to build a data explorer that lets anyone ask questions and get insights without writing a single SQL query. If you’re tired of analyzing data manually, then this interview is a must-watch. Summit and I talked about: (00:00) How to make Claude Code your data analyst (03:04) Analyzing data with AI: Monitor → Explore → Craft → Impact (10:23) Live demo: Building a startup funding MCP with 3 queries (21:10) Context management: Why your data agent gets confused (26:04) How to connect Claude to Slack and Drive for context (35:00) Demo: Predicting which AI startups will get Series B funding (41:32) Brex stats on which AI coding tools are actually winning Get the takeaways: https://creatoreconomy.so/p/build-an-ai-data-analyst-with-claude-code-sumeet Where to find Sumeet: LinkedIn: https://www.linkedin.com/in/smarwaha/ 📌 Subscribe to this channel – more interviews coming soon!

Tal and Aman are experienced AI PMs so I made us all share our favorite AI product workflows — from writing strategy docs to prototyping with Google AI Studio to building a personal task system with Claude Code. Watch this episode if you want to see 5 real no-BS AI product workflows in 50 minutes. We talked about: (00:00) Our best AI workflows for product work (01:13) Demo 1: Writing strategy docs with Claude Projects (10:21) Demo 2: Prototyping a new feature with Google AI Studio (17:10) Demo 3: Building an AI thinking partner with Obsidian + Cursor (24:06) Demo 4: Managing tasks with Linear MCP (29:01) Demo 5: Building a personal OS with Claude Code and skills (40:06) Context engineering 101 from Aman (48:54) Summary and how you can start today Thanks to our sponsors: Korey: The AI Agent for product developmenthttps://www.korey.ai/ Get the takeaways: https://creatoreconomy.so/p/full-course-the-ai-stack-we-use-for-prototyping-strategy-personal-os-aman-tal Where to find: Tal: https://www.linkedin.com/in/talsraviv/ Aman: https://www.linkedin.com/in/amanberkeley/ Aman's personal OS Github: https://github.com/amanaiproduct/personal-os 📌 Subscribe to this channel – more interviews coming soon!

Teresa is a well-known product coach and author who runs her entire life and business using two Claude Code terminals and a note taking app. It was genuinely mind blowing to watch her use Claude Code to manage her to do list, delegate her research, and write content. Teresa and I talked about: (00:00) Why Teresa uses Claude Code to run her life (03:00) Live demo: The "today" command that builds Teresa's daily to do list (07:00) Working with Claude Code to brainstorm tasks and ideas (14:00) Live demo: Writing a blog post together using plan mode (21:00) How Claude does SEO keyword research for blog posts (26:00) Why Teresa still writes every word herself (but 10x faster) (30:00) Pro tips to manage context so Claude doesn't "get dumber" (36:00) The 3-layer context system: global, project, and reference files (44:00) 3 tips to get started with Claude Code without feeling overwhelmed Thanks to our sponsors: Optimizely: The agent orchestration platform for marketing https://www.optimizely.com/ai/ Get the takeaways: https://creatoreconomy.so/p/build-your-personal-os-with-claude-code-teresa-torres Where to find Teresa: LInkedIn: https://www.linkedin.com/in/teresatorres/ Website: https://www.producttalk.org/ 📌 Subscribe to this channel – more interviews coming soon!

Yana is Head of AI at Amplitude and a good friend. We had some real talk about how to stay scrappy inside a big company, including how to avoid decision by committee and endless internal debates. Yana also demoed her favorite AI workflows to triage her emails and aggregate customer feedback. I think you’ll love our banter 😅 Yana and I talked about: (00:00) "By the time you've debated 2 ideas, I've already shipped 10" (03:21) Think "how would I run this company?" not "what's my job?" (05:22) Why we banned decisions by committee (08:25) Cross-functional now means doing the work, not coordinating it (11:22) Why frustrated users can become your biggest advocates (15:19) Live demo: Using ChatGPT Atlas to triage emails and defuse emotional ones (24:38) AI is still terrible at prompting (and what you can do about it) (28:48) Live demo: Combining qualitative feedback with quantitative data (37:38) Why AI analytics is lagging (and what needs to change) Thanks to our sponsors: Optimizely: The agent orchestration platform for marketing https://www.optimizely.com/ai/ Get the takeaways: https://creatoreconomy.so/p/a-founders-playbook-for-shipping-10x-faster-with-ai-yana-welinder Where to find Yana: X: https://x.com/yanatweets Website: https://amplitude.com/ai-feedback?utm_campaign=fy25q4-ai-feedback-launch&utm_source=newsletter&utm_medium=organic-social&utm_content=creator-economy 📌 Subscribe to this channel – more interviews coming soon!

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 home Thanks 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-economy Linear: The best platform for AI agents https://linear.app/partners/behind-the-craft Get the takeaways: https://creatoreconomy.so/p/an-inside-look-at-what-alexa-can-do-with-ai Where 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 slop Get the takeaways: https://creatoreconomy.so/p/a-proven-5-step-system-to-prototype-apps-with-ai-xinran-ma Where to find Xinran: Newsletter: https://designwithai.substack.com LinkedIn: https://www.linkedin.com/in/davidmaxinran/ 📌 Subscribe to this channel – more interviews coming soon!

Tanay 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-yang Linear: The best platform for agents https://linear.app/partners/behind-the-craft Get 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 Cursor Thanks to our sponsors: Reforge: AI prototyping tool for product builders - https://reforge.com/peter Linear: The best platform for AI agents - https://linear.app/partners/behind-the-craft Get 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 resilience Thanks to our sponsors: Composio: Use AI to take action across 500 apps https://getrube.link/peter Linear: Try the platform for AI agents https://linear.app/partners/behind-the-craft Get the takeaways: https://creatoreconomy.so/p/7-counterintuitive-lessons-from-whatsapp-head-of-product-ami-vora Where 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/peter Linear: Try the platform for AI agents https://linear.app/partners/behind-the-craft Get the takeaways: https://creatoreconomy.so/p/full-tutorial-turn-your-prototype-into-a-real-saas-app-ai-colin-matthews Where 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 calendar This 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-foster Where to find Wade: X: https://x.com/wadefoster Website: https://zapier.com Subscribe 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 builders Get the takeaways: https://creatoreconomy.so/p/how-notion-built-the-best-ai-agents-for-work-akshay-ryanWhere to find: Akshay: https://x.com/akothari Ryan: https://x.com/_ryannystrom Notion AI agents: https://www.notion.com/blog/introducing-notion-3-0 📌 Subscribe to this channel – more interviews coming soon!