Dear subscribers,

Today, I want to share a new episode with Ashley.

Ashley is the VP of Product at OpenAI for health and this is a very special episode for me. We talked about how we both use AI to help our parents fight cancer — including preparing for doctor visits, researching treatments, and coping with our emotions as caregivers. Both of Ashley’s parents got diagnosed with cancer in a single week and it was really inspiring to hear how she took care of them.

Ashley and I talked about:

• (00:00) How her dad’s cancer led Ashley to OpenAI

• (07:15) Why I talk to AI more than my own mom

• (09:41) Are doctors annoyed when patients bring AI research?

• (14:17) Is AI really about to cure cancer?

• (19:12) Should you trust ChatGPT with your health records?

• (25:38) How ChatGPT caught a risky treatment before it was given

• (28:00) Why hospitals still use faxes and CDs

• (36:16) What Ashley types into ChatGPT during her dad’s appointments

• (41:09) Making time for your parents with a demanding job

I’m proud to partner with Granola

I use Granola to record my mom’s medical conversations, with her care team’s permission. Having notes we can revisit later helps us keep track of what was said, the decisions we made, and what to follow up on.

Try Granola for Free

Top takeaways I learned from this episode

1. “Both of my parents got diagnosed with cancer within a week of each other.” Ashley took a month off from work to take care of them after and doesn’t regret it. She also emphasized taking time off for yourself as the caregiver: “Even with AI, you have to make sure that you’re budgeting time for your own mental health.”

2. “Are you deluding yourself that you’re actually that busy?” Ashley had an always-on life until her parents got sick. Now she blocks time for her dad’s appointments, even as a busy executive at OpenAI. “I’m lucky that not once have I ever gotten pushback at work about this.” When she started making time for her parents, she realized, “Maybe some of those work meetings didn’t need me there.”

3. Share how you’re dealing with cancer and people will come out to help. For example, a friend’s father-in-law helped Ashley find the Stanford specialist who became her dad’s doctor. “You don’t know [who can help] until you share,” she said. I’ve found the same with my mom: Sharing her situation has helped me connect with oncologists and experts.

4. “I didn’t feel like I was in the driver’s seat of what was most important to me, which is my father’s life.” Ashley was weighing surgery and radiation for her dad, but his lung and heart specialists weren’t set up to share information and she had to piece it together herself. Give AI the patient’s full medical history and use it to have informed discussions with their medical team.

5. Give ChatGPT your medical records to flag possible conflicts before treatment. Ashley recounted how her former boss, Fidji Simo, caught a conflict using ChatGPT right before treatment. Her doctor hadn’t seen the relevant history elsewhere in her record. Ashley has seen multiple cases of this happening.

6. Do your homework before the appointment. Ashley uses ChatGPT to new therapies for his lung disease before doct appointments. She could then ask his doctor about the therapies to get his opinion on whether they’re viable options.

7. “What question should I be asking right now?” Ashley keeps ChatGPT open during her dad’s telehealth appointments. When the doctor mentioned “left wedge resection,” she looked up the unfamiliar lung-surgery term on the spot. “I’d sort of be educating myself, and then I could make better use of the time.”

8. Give your parent’s records their own space in ChatGPT. Ashley uses project-only memory to keep her dad’s records separate from her own health conversations. She also gets her dad’s consent before uploading records and redacts details he wants kept private.

9. Keep one care summary you can pull up under pressure. My /fuck-cancer skill keeps a one-page Google Doc on my mom’s care and Ashley described how she has a similar doc that keeps track of her parents’ latest medications, lab results, appointment notes, and more to discuss with their care team.

10. Have ChatGPT check for new research every week. Set up a recurring task in ChatGPT for your condition and ask it to search ClinicalTrials.gov and other research sources for new trials and treatments. My /fuck-cancer skill does this for free out of the box.

Watch the episode now and subscribe if you enjoyed the interview.

Dear subscribers,

Today, I want to share a new episode with Jaclyn.

Jaclyn is a product director at Google Labs and we had a great chat about how Gemini 4 changed her product job, how she keeps AI slop out of her team’s docs and products, and how she’s raising three kids with AI’s help. Gemini 4 Carbon is currently the best model in the world based on benchmarks, and it was fun to get a sneak peek into how Google’s own product leaders use it internally.

Jaclyn and I talked about:

• (00:00) How Gemini 4 changed the PM job at Google

• (02:11) Should it even exist? How Google Labs picks what to build

• (09:16) The doc rule that keeps AI slop out of Google Labs

• (10:45) Which Labs experiments graduated into the Gemini app

• (12:53) Why Google Labs never treats a killed experiment as failure

• (17:43) Code is free, so what’s actually worth building?

• (24:00) Her 5-year-old is the creative director of their AI podcast

• (26:30) Best screen time for kids: Creation, not consumption

I’m proud to partner with Wispr Flow

Wispr Flow is the most accurate AI voice dictation tool I’ve tried, and now it supports meeting notes too. Wispr’s new speech model, Canto, also has best-in-class performance for dictation in real-world conditions. Get 1 month free with my link.

Get 1 Month Free

Top takeaways I learned from this episode

1. “It shouldn’t take someone longer to read your doc than it took for you to write it.” Writing is thinking and Jaclyn believes that outsourcing writing to AI is a big mistake. AI can be a thought partner, but you should firmly be in the driver’s seat. AI-written docs are a waste of everyone’s time and Jaclyn expects her PMs to be able to defend every statement themselves.

2. “It’s no longer about can you build it, it’s about should it even exist?” When code is free, deciding what to build is the job. You can rebuild many products if you “throw a couple of agents at it over a weekend” but that doesn’t mean you should. Instead, aim higher to build products, not features, that make a real difference in customers’ lives.

Read more

Dear subscribers,

Today, I want to share a new episode with Jake Moran.

Jake is my go-to expert for creating and editing videos with AI. In our episode, he demoed how he prompts Claude and HyperFrames to make incredible videos for product launches, long-form tutorials, and shorts. We also covered the key terms that you need to learn to guide AI to make the right edits.

Jake and I talked about:

• (00:00) Video editing 101 to get Claude to make what you want

• (06:14) Parakeet: A free local model for accurate cuts

• (08:40) Hook viewers with zooms, B-roll, and whip pans

• (13:37) Demo: A launch video built from three screenshots

• (18:41) Launch videos in 4 parts: Hook, context, payoff, brand

• (20:39) Claude added Jake’s AI avatar without being asked

• (23:28) Jake’s AI edit of my raw YouTube video

• (29:25) How to copy any video’s style using AI

• (36:17) Draw feedback on the frame instead of typing

I’m proud to partner with Wispr Flow.

Wispr Flow is the most accurate AI voice dictation tool I’ve tried, and now it supports meeting notes too. Wispr’s new speech model, Canto, also has best-in-class performance for dictation in real-world conditions. Get 1 month free with my link.

Try Wispr Flow for Free

Top takeaways I learned from this episode

First, watch this 43 second video that Jake made with AI in our episode:

Here are my top takeaways on exactly how he made this:

Read more

Dear subscribers,

Today, I want to share a new episode with Anthony Pompliano.

Pomp and I worked together at Facebook a decade ago before he became an investor, best-selling author, and public company CEO with an audience of 3.3M. We had a great chat about how to build an extraordinary career and life and how he’s building Silvia, an AI CFO for independent investors, to take on the AI labs.

Pomp and I talked about:

• (00:00) Why Pomp never had a career plan

• (04:43) Why an audience is the best way to win

• (10:33) Paid work trials instead of job interviews

• (18:35) Hire for revenue, not margins

• (20:32) Silvia: An AI CFO for investors

• (25:00) How AI found a great tax strategy

• (32:05) How a team of under 10 plans to compete with the AI labs

• (35:58) Pomp’s latest take on Bitcoin

• (39:21) How Pomp teaches his four kids to solve problems

I’m proud to partner with Riverside

Riverside’s new MCP lets me prep episodes, edit recordings, create clips, and schedule posts to multiple video platforms, all from ChatGPT and Claude. You can also use it to host webinars, create brand videos, and much more.

Try Riverside for 1 Month Free

Top takeaways I learned from this episode

Pomp’s career playbook

1. Here’s a brief history of Pomp’s fascinating career. He never had a 10-year plan. Instead, each move solved his biggest problem and set up the next one:

   • Learn the skill you’re missing: His first two startups failed to scale, so he joined Facebook to learn growth.

   • Get an audience first to get deal flow: He wanted to invest but didn’t know the next generation of founders, so he built a 2.4M following on X by going deep on Bitcoin.

   • Show up every day: In May 2018, he started a daily newsletter that began as crypto news. He still writes it himself every morning, and it now has 270,000+ subscribers.

   • Start small to test fit: He and his partner started with a $3.5M fund and took no management fee. Pomp has since invested in 300+ private companies.

   • Solve your own problem: Pomp was tired of updating his personal finance spreadsheet by hand every week. As AI took off, his team turned it into Silvia, an AI CFO for independent investors.

Read more

Dear subscribers,

Today, I want to share a new episode with Micky.

Micky is a full-stack engineer who has taught 100K+ people how to build with AI. In our episode, he walked me through his 4-step agentic engineering workflow to avoid pumping out slop: Isolate every task, build to a clear structure, prove via validation loops, and ship after agents review your PRs or escalate to you for a manual look.

Micky and I talked about:

• (00:00) Why most software factories pump out slop

• (02:06) Step 1 (Isolate): How to run multiple agents at once

• (07:18) Step 2 (Build): Give agents a structure to build on

• (10:44) Step 3 (Prove): Build agentic validation loops

• (16:48) The one step Micky never hands to agents

• (21:30) Step 4 (Ship): Getting agents to review PRs reliably

• (28:20) Why Micky doesn’t write specs

• (33:08) Comparing Astra and Fable for coding

• (43:08) Are AI skills obsolete with today’s models?

I’m proud to partner with Wispr Flow

There are many AI voice dictation tools out there, but Wispr Flow has been the most reliable one I’ve used. My kids also love using it to build games and apps with Codex and Claude Code. Get a month free with my link below.

Try Wispr Flow for Free

Top takeaways I learned from this episode

Micky’s 4-step agentic engineering workflow

1. Use Micky’s 4-step workflow that makes agents prove their work before you merge. Micky’s “software factory” is his AGENTS.md file plus a handful of skills:

   • Isolate. The new-feature skill gives each agent its own copy of the code on a separate worktree, so that you can run multiple agents in parallel.

   • Build. The code-structure skill writes code based on service-layer architecture with explicit inputs and structured returns.

   • Prove. The evidence-driven-testing skill has the agent screen-record itself testing the app to compare the before and after states for a change.

   • Ship. The greploop skill uses Greptile, an AI reviewer, to test and improve the PR until it scores 5/5 with zero unresolved comments. Micky then usually reviews the PR himself before shipping.

   • Everything Micky ships to real users moves through these four steps.

How Micky makes agents earn his trust

Read more

Dear subscribers,

Today, I want to share a new episode with Sam.

Sam is the co-founder of Granola, the AI meeting notes app now valued at $1.5B. Granola has helped me survive (and even enjoy) countless meetings, so I was excited to learn how Sam uses AI to show up prepared. We also talked about building an AI company without the 996 grind and what design means when agents skip your app.

Sam and I talked about:

• (00:00) The AI brief Sam now relies on before every new meeting

• (01:27) “What did I miss?”: Granola’s most used recipe

• (03:45) Why Granola hides the transcript despite user complaints

• (09:37) A Granola recipe to get feedback from founders

• (13:54) Why Sam feels a pang of sadness when agents skip your UI

• (19:30) Why Sam’s Figma use fell to 20% and how Granola stops slop

• (26:14) Nacho: The agent every Granola employee asks first

• (30:58) Why most people stop improving their product way too early

I’m proud to partner with Google AI Studio

Google AI Studio was my go-to prototyping tool when I was a product manager. You can use it to generate three versions of your product, add visuals with Google’s Nano Banana model, and publish them to a custom URL for customer feedback. It’s an easy, free way to move from prompt to something your team or customers can try.

Try Google AI Studio for Free

Top 10 takeaways I learned from this episode

Design principles for the AI era

1. Design for your user’s most stressful moment. Granola is built for the space between back-to-back meetings, when you’re late and forget who you’re meeting next. One of Sam’s principles is “Be calming: Granola should lower your blood pressure.” This has led to decisions like explicitly hiding the live transcript.

2. Design for agents using your app or product first. Sam felt “a pang of sadness” as a UI designer when people defaulted to using Granola through MCP and the API instead of the app. He resisted at first but now recognizes that many enterprises simply won’t adopt a tool that doesn’t plug into their internal agents. Some users will stick with the UI while others go through MCP, so design for both.

Read more

Dear subscribers,

Today, I want to share a new episode with Peng and Lauren.

Peng and Lauren are the lead designer and engineer for Grok Bot at SpaceXAI. In our interview, they showed me 14 bots that they use for work and life, from a design bot that helps Peng turn a single design into a user flow to an entire team of engineering bots that help Lauren ship faster.

Peng, Lauren, and I talked about:

• (00:00) The bots that the Grok Bot team actually uses

• (01:23) Peng’s chief of staff bot buys supplies and lists gear

• (06:31) Putting PM, design, and eng bots in the same room

• (10:07) A bot that turns photos into dioramas on Peng’s website

• (14:16) How Lauren’s bots test their own work before merging

• (17:59) Dr. Eggbot, a bot that designs and audits your bots

• (21:27) The assistant bot that booked Lauren’s multi-city trip

• (25:22) Eng bots that sometimes land PRs before Lauren reads them

• (38:59) How to trust your bots with more work, one skill at a time

I’m proud to partner with Granola

The world’s best teams, including Ramp, Linear, Replit, Brex, and more, use Granola to take notes and focus more in meetings. I’ve tried many meeting apps myself but keep coming back to Granola. It literally helps you take time back in your day.

Try Granola for Free

Top takeaways I learned from this episode

How the Grok Bot team uses Grok Bot

1. Build the design system and one keyframe, then let your design bot scale it. Peng’s design bot connects to Figma through Figma MCP and uses a skill that describes how his files are set up, plus his design system’s colors, type, and spacing. “I will do the first 5%,” Peng said. He builds the system and one keyframe, then asks the bot to extend it into every screen of the flow.

2. Make an eng lead bot to manage your other eng bots. Lauren hands big projects to her eng lead bot, Matcha. Matcha doesn’t do work itself. Instead, it breaks down the project for other eng bots to execute on. Each eng bot then spins up coding agents in the cloud, letting Lauren run “really massive agent swarms.”

Read more

Dear subscribers,

Today, I want to share a new episode with Ethan.

Ethan is the product lead for ChatGPT Finances at OpenAI and he previously co-founded Digit, which helped more than 10 million people save over $9 billion. In our interview, he shared 6 practical ways to use ChatGPT to find wasted spending, prep for taxes, maximize credit card rewards, and model major financial decisions. I’m confident at least one of these use cases will save you money today.

Ethan and I talked about:

• (00:00) ChatGPT Finances can save you money right now

• (03:37) Use case 1: Cancel recurring subscriptions

• (09:37) How ChatGPT protects your financial data

• (18:03) Use case 2: Find tax savings proactively

• (24:58) Use case 3: Cut ETF and mutual fund fees

• (26:20) Use case 4: Maximize credit card rewards

• (28:20) Use case 5: Model income and taking time off

• (31:05) Use case 6: Decide whether to rent or buy

• (34:00) How to set up recurring finance checks

• (36:58) Shipping 47 product updates in one week

I’m proud to partner with Wispr Flow

There are many AI voice dictation tools out there, but Wispr Flow has been the most accurate one I’ve used. My kids also love using it to dictate prompts to Codex and Claude Code so they can build games and apps. Try it out with my free link below.

Try Wispr Flow for Free

6 ways to use ChatGPT Finance to save money now

1. Negotiate or cancel recurring subscriptions. Use this prompt to ask ChatGPT to review your recent subscriptions and suggest ways to help you negotiate or cancel them:

2. Find tax savings proactively. After you connect your bank and investment accounts to ChatGPT, you can ask it to proactively audit and optimize your taxes. Personally, it has been a massive timer saver for me in my conversations with my accountant. Start with this prompt:

Read more

Dear subscribers,

Today, I want to share a new episode with Pedro, the co-founder and CEO of Brex.

Pedro is widely respected as one of the most AI-pilled CEOs. In our interview, he explained why most people are building agents wrong and how to build them as AI employees instead, each with a specific job, skill, manager, and budget. He also gave a live demo of how he still uses OpenClaw to stay on top of his $5B business and life.

Timestamps:

• (00:00) Build AI employees, not AI agents

• (05:23) Why Pedro spends half his time reviewing work

• (12:32) Live demo: Jim, Brex’s AI recruiting employee

• (21:24) Why Brex makes engineers build with AI in interviews

• (22:33) CrabTrap: How to stop AI employees from leaking data

• (27:30) The tokenmaxxing bill is coming. Here’s how to control it

• (40:45) Live demo: Pedro’s OpenClaw system runs his life

I’m proud to partner with Riverside

A webinar shouldn’t be a one-and-done event. Riverside lets you plan, stream, record, edit, and repurpose everything in one tool. You can host live Q&As and polls, capture every speaker in 4K, then turn the recording into clips, recaps, newsletters, and social posts with AI’s help. Use my code PeterYang to get one month free.

Try Riverside for Free

Top takeaways I learned from this episode

Build AI employees, not AI agents

1. Build an AI agent like you’re onboarding an employee. Give your agents the same operating constraints as a good employee:

   • Job: Own one clear outcome.

   • Skills: Include specific instructions and constraints.

   • Manager: Escalate to the human manager if unclear.

   • Budget: Spend only tokens based on what the outcome is worth.

2. Jim (Brex’s AI recruiter) is an example of what an AI employee looks like. Jim’s job is to help recruiters find quality job candidates. His skills include sourcing candidates, filtering inbound applications, and running analytics for any job. He can access Greenhouse and LinkedIn and escalates to a human when he’s unsure.

Read more

Today, I want to share a new episode with Sue Khim.

As the co-founder of Brilliant, Sue is building an AI tutor to help kids think for themselves. In our interview, she shared why better grades at school don’t always reflect learning and gave a demo of how AI can guide kids to understand problems instead of getting the answer. This episode is a must-watch if you’re a parent.

Watch now on YouTube, Apple, and Spotify.

Sue and I talked about:

• (00:00) Why AI should make kids think harder

• (01:34) Why test scores are down while grades are up

• (09:41) Koji: An AI tutor that won’t give you the answer

• (18:05) Why humans design lessons and AI builds them

• (22:25) Primitives: The building blocks behind Brilliant’s AI

• (29:30) Testing AI lessons with simulated students

• (32:10) Measure learning, not lesson completion

• (34:39) Sue’s rule for competing with the big AI labs

• (39:10) How to raise kids who enjoy doing hard things

This episode is brought to you by… Linear

Linear is the tool of choice for over 40,000 AI-native teams ranging from startups to enterprises. Many of today’s leading AI companies, including OpenAI, Cursor, and Cognition, use Linear to run product development end-to-end with agents. Try it for free with my link below.

Try Linear for Free

Top 10 takeaways I learned from this episode

How AI can help kids learn

1. “Using AI to skip learning is like bringing a robotic arm to the gym to lift weights for you.” I told Sue I feel this temptation too: It’s easier to ask AI to solve a problem than to understand how to solve it myself. When teaching kids to use AI, teach them to ask it for questions and hints that help them work out the answer instead of just asking for the answer.

2. Even a good explanation can do the thinking for your child. From Sue: “Cheating and explanations are closer than you’d think.” Both can let a child skip working through a problem themselves. When your child gets stuck, ask them to explain their thinking before you explain the answer. Give them a chance to discover what they’re missing.

3. Help your kids get absorbed in their interests. Sue pays attention to how deeply her kids explore their interests. It could be monkey bars, chess, or magic tricks. The aim is to experience the effort and satisfaction of improving, without treating learning as something you do to please adults. “It should feel hard to learn something new.”

Read more

Dear subscribers,

Today, I want to share a new episode with Amol Jain.

As head of product engineering at Replit, Amol has a firsthand look at which vibe-coded apps become real businesses. He showed me three apps built by non-coders that reached six figures, then did a live demo of his 4-step process to take an app from prototype to production, including security, monetization, and distribution.

Watch now on YouTube, Apple, and Spotify.

Amol and I talked about:

• (00:00) He built an app in 3 days that made $100K+ in month one

• (02:08) Three vibe-coded apps that became real businesses

• (08:04) What six-figure vibe-coded apps have in common

• (12:31) Live demo: Turn an AI interview coach into a real business

• (13:59) Steps 1 and 2: Publish the app and make it secure

• (17:50) Steps 3 and 4: Add payments and optimize SEO

• (21:35) How to replace expensive SaaS with internal tools

• (28:22) What software survives when code costs almost nothing

• (31:02) Why value is moving from models to apps

I’m proud to partner with Riverside

I’ve used Riverside for years to record my podcast thanks to its reliable, high-quality recording tools. But now I use it for much more than recording. Riverside has evolved into an end-to-end platform with AI editing, clip generation, streaming, and publishing tools. Try Riverside to go from concept to publish, all in one place and use my code PETERYANG at checkout to get one month free.

Try Riverside for Free

Top 10 takeaways I learned from this episode

1. Three vibe-coded apps that became real businesses with non-technical founders:

   1. Pep AI: A mobile peptide tracking app built by Cedric that reached 10K users and $60K in its first month.

   2. GenAIPI: An AI enterprise training agency built by Jon in 3 days that made $180K in 6 weeks.

   3. TryNearby: A marketplace that connects local businesses and creators built by Yousef with 120+ paying restaurants.

2. All three founders had durable advantages beyond coding, such as:

   1. Expertise: Pep AI came from Cedric’s knowledge of the peptide and GLP-1 community.

   2. Access: GenAIPI came from Jon’s experience and contacts selling AI training to enterprises.

Read more

Today, I want to share a new episode with Shreya and Hamel.

Shreya and Hamel teach the industry-leading AI evals course taken by 4,500+ students from OpenAI, Google, and more. I asked them to do a live audit of the evals that I built for my creator skills. They then walked through how anyone can use their free Error Discovery skill in Claude Code to turn feedback into useful evals. If you want a practical, up-to-date primer on AI evaluations, then this episode is for you.

Watch now on YouTube, Apple, and Spotify.

P.S., I asked Shreya and Hamel to give 25% off the next cohort of their AI evals course that’s starting on 9/5. It has 4.7 stars with 900 reviews, which is almost unheard of on Maven. Check it out and get your company to expense it if you can!

Get 25% Off the Course Now

Shreya, Hamel, and I talked about:

• (00:00) Why AI evals are completely different now with the latest models

• (02:30) Demo: Live audit of the evals that I built for my AI skills

• (05:14) Top-down vs. bottom-up evals and why AI sucks at the latter

• (08:16) Spinning up AI agents to grade each eval criterion

• (14:32) Demo: Using Shreya’s AI skill to run evals in Claude

• (23:46) How to review output labels to identify failures

• (34:37) How to turn failures into reusable evals

• (43:19) Where human judgment is still needed

I’m proud to partner with Wispr Flow

When I’m building with Claude Code, I use Wispr Flow to dictate all my prompts instead of typing. It’s more accurate than other AI voice dictation tools and saves me hours every week. Try it out for free with my exclusive link below.

Try Wispr Flow for Free

Top 10 takeaways I learned from this episode

Live audit of the evals for my AI skill

1. There are two types of evals: top-down and bottom-up. When I asked Shreya and Hamel to audit the evals that I built for my podcast production skill, they found strong top-down evals, but almost no bottom-up evals.

   1. Top-down evals are rules that you define upfront. Mine include “Is every takeaway 240-330 characters?” and “Does each give plain, useful advice?”

   2. Bottom-up evals are failures found by comparing AI’s output with my final edits. With these evals, it’s important not to overfit to a few examples.

2. Compare 10–20 past examples before turning a failure into an eval. Hamel and Shreya encouraged me to run my podcast production skill on at least a dozen past interviews to compare AI’s output with my final edits. They shared a free Error Discovery skill that Claude Code and Codex can use to define evals based on this data.

Build useful evals using this free skill in 5 steps

Shreya and Hamel built a free Error Discovery skill that anyone can run in Claude Code or Codex to define useful evals based on your data. The skill walks you through this process:

Below is a link to the skill and a walkthrough of each step:

Read more

Today, I want to share a new episode with Riley Brown.

Riley is a top AI creator and founder of Agent Native. In this episode, he showed me how he uses Codex to run his entire content business from creating engaging thumbnails to writing viral video hooks. Riley also shared his full AI stack including some lesser-known tools to edit videos, draw diagrams, and more.

Watch now on YouTube, Apple, and Spotify.

Riley and I talked about:

• (00:00) How Codex runs Riley’s 1.5M+ follower content business

• (03:16) Demo: Using Codex to create animations and B-roll

• (07:28) Demo: How Codex can reverse-engineer a top YouTube hook

• (13:24) The BRENS framework to turn an idea into a strong hook

• (17:24) Demo: Riley’s AI stack for diagrams, thumbnails, and posts

• (22:01) How Riley creates so much content every week

• (25:41) Demo: Using Codex and Paper to create viral YouTube thumbnails

• (35:01) How to set up AI agents to find content ideas proactively

I’m proud to partner with Google AI Studio

Google AI Studio was my go-to prototyping tool when I was a product manager. You can use it to generate three versions of your product, add visuals with Google’s Nano Banana model, and publish them to a custom URL for customer feedback. It’s an easy, free way to move from prompt to something your team or customers can try.

Try Google AI Studio for Free

Top 10 takeaways I learned from this episode

1. Remix proven thumbnails with Codex and Paper’s AI design tools. Riley creates winning YouTube thumbnails entirely using AI as follows:

   1. Ask Codex to collect thumbnail formats from top YouTube channels in Paper.

   2. Use Paper’s image-generation features to mix his face with a proven format.

2. Riley’s AI stack helps him run his entire YouTube video creation process. In addition to Codex, Riley uses a few lesser-known AI tools to research topics, draft hooks, draw diagrams, create animations and B-roll. Here’s his stack:

   1. Research topics using Codex and Supadata, which can efficiently pull transcripts for top-performing YouTube videos in a few seconds.

   2. Draw diagrams using Wispr Flow and Excalidraw. He dictates directions to the Excalidraw MCP to turn into diagrams that frame his videos.

Read more

Today, I want to share a new episode with Nan Yu and Jacob Shumway.

Nan and Jacob built Linear Agent, which has transformed how the $1.25B company gets work done. In this episode, they walk through how they built an AI agent from the initial memo to launch, including how to give it tools to find the context it needs and how to design evals that make the agent more reliable. If you want a concrete, behind-the-scenes example of how to build a production agent end to end, this episode is a must-watch.

Watch now on YouTube, Apple, and Spotify.

We talked about:

• (00:00) What’s holding AI agents back as models improve?

• (00:51) Three things every good agent needs

• (03:00) Demo: The internal memo that started Linear Agent

• (09:50) The biggest mistake to avoid when building agents

• (11:29) Demo: From Slack to code in 6 minutes with the agent

• (17:01) When prototyping, “use the biggest model until it works”

• (24:02) Give agents tools to find context, not more context

• (34:07) The first thing to do before building an agent

I’m proud to partner with Oceans Talent

I’ve been working with Char, my assistant from Oceans Talent, for about six months. What stands out about his work is that he doesn’t just use AI tools. Instead, he actively builds and maintains AI workflows to help me run podcast post-production, draft show notes, make video clips, and more.

If you want to hire AI-fluent operators who can help you take back your time at 70% less than the cost of a US hire, book a call at oceanstalent.com/peter.

Get Started for Free

Top 10 takeaways I learned from this episode

1. The first step to building a good agent is to map the actual workflow. Identify where work starts, which systems hold context, what actions complete the job, what “done” means, and where a person needs to review. If work starts in Slack, make Slack the on-ramp instead of forcing users into a separate chatbot.

2. Give agents tools to find context instead of stuffing context into the prompt. Jacob’s advice: “Give it as little instruction as possible, to be honest. Give it the tools to load context. Don’t give it context.” Start small, then let the agent pull only the instructions and data it needs for the current task.

Read more

Today, I want to share a new episode with Karan.

Karan is the co-founder of Nous Research, the company behind Hermes, the #1 personal agent and AI app on OpenRouter. We had a great chat about why open-source AI must win and how Hermes gets better the more you use it. Karan also shared a live demo of how he used Hermes to modify his favorite childhood game.

Watch now on YouTube, Apple, and Spotify.

Karan and I talked about:

• (00:00) How Hermes differs from Claude Code and Codex

• (02:20) Why every AI model now sounds exactly the same

• (11:16) How to stop AI from saying “you’re absolutely right”

• (15:16) How Hermes creates skills without bloating its context

• (16:40) The open vs. closed-source debate on AI safety

• (23:40) Using one Kanban board for humans and AI agents

• (26:45) Demo: Rebuilding a childhood Sonic world with Hermes

• (36:07) How two Discord friends started Nous Research

• (42:40) How Hermes became its own biggest contributor

I’m proud to partner with Linear

You can now use Linear Agent to edit documents and project descriptions or set up loops to keep them updated automatically as your code changes. Linear makes agent edits transparent through author attribution and version history.

Try Linear for free

Top 10 takeaways I learned from this episode

How to make Hermes work for you

1. The “personal” in personal agent is not the model. Instead, it’s the agent’s memory of your conversations and the skills that you’ve built with it. Karan barely notices any difference in Hermes’ personality when he swaps models because his agent has accumulated so much context about him. The model is interchangeable, but the context layer is what you should cherish and preserve.

2. Customize Hermes’ soul.md to the personality that you want. After using Hermes for 6+ months now, I’ve customized its soul.md to have:

   • Core truths like be genuinely helpful and avoid sycophancy.

   • Boundaries like respecting my privacy especially in any group chats.

   • The right vibes that make it fun to talk to.

   Here’s my complete soul.md that you can copy and paste into Hermes or another AI agent to improve its personality:

Read more

Today, I want to share a new episode with Jason Liu.

Jason is a DevEx engineer on the Codex team. In our episode, he showed me how he runs his entire workday using Codex, from his chief of staff thread for Slack and email to setting up long-running tasks that have verifiable goals. Jason wrote the official OpenAI handbook on how to get the most out of Codex, so don’t miss this episode.

Watch now on YouTube, Apple, and Spotify.

Jason and I talked about:

• (00:00) The only job left after AI can do the work

• (02:40) Turn pinned threads into long-running workspaces

• (05:50) Build a chief of staff across Slack, email, and Linear

• (10:12) Teach Codex to write like you for every audience

• (13:33) Mine past sessions for new skills and workflows

• (20:01) How Codex revised a launch video while Jason was out

• (24:23) Build a drum practice site around how you learn

• (25:59) Goal, plan, and worklog for long-running Codex tasks

• (33:52) Why taste starts with knowing what feels wrong

I’m proud to partner with Google AI Studio

Google AI Studio was my go-to prototyping tool when I was a product manager. You can use it to generate three versions of your product, add visuals with Google’s Nano Banana model, and publish them to a custom URL for customer feedback. It’s an easy, free way to move from prompt to something your team or customers can try.

Try Google AI Studio for Free

Top 10 takeaways I learned from this episode

Build a Codex system that improves itself

1. Build a chief of staff Codex thread that manages your email, Slack, and more for you. At 9 am, 1 pm, and 5 pm, Jason’s chief of staff thread reviews his Slack, emails, Twitter DMs (through browser use), and Linear before surfacing priorities with links and draft replies. Here’s a prompt you can modify to set this up:

2. Ask Codex to look at your past sessions to build new skills and workflows. Codex has memory of all your past conversations, so the best way to save time is to ask it to find workflows from your manual iterations that it can build new skills to automate. Here’s a prompt you can paste to do this right now:

Read more

Today, I want to share a new episode with Thariq Shihipar.

Thariq works on the Claude Code team, and I’ve wanted to see how he builds for a long time. In our episode, he showed how to use /goal to keep Claude working, how he plans with Claude to remove unknowns before building, and how he runs a team of agents in Slack. He also shared why his team cut Claude Code’s system prompt by 80% and how he creates polished launch videos with Claude.

Watch now on YouTube, Apple, and Spotify.

Thariq and I talked about:

• (00:00) Goals, loops, and workflows to make Claude work longer

• (04:48) Live demo: Creating a polished video with Claude

• (08:17) Plan by removing unknowns before you build

• (14:32) How Anthropic uses HTML artifacts for planning

• (18:35) Running parallel Claude tasks through Slack

• (27:34) Using separate creator and verifier sub-agents

• (31:08) How Thariq stays focused while Claude works in parallel

• (34:07) Why Anthropic cut Claude Code’s system prompt by 80%

• (37:01) How to become more technical when AI writes the code

I’m proud to partner with Wispr Flow

When I’m building with Claude Code, I use Wispr Flow to dictate all my prompts instead of typing. It’s more accurate than other AI voice dictation tools and saves me hours every week. Try it out for free with my exclusive link below.

Try Wispr Flow for Free

Top 10 takeaways I learned from this episode

1. When a better AI model is released, the first thing you should try is to remove instructions. Thariq and the Claude Code team cut Claude Code’s system prompt by 80% because hard rules and examples were constraining newer models. When a new model is released, audit your CLAUDE.md and skills to remove deterministic instructions.

2. Plan with Claude to discover and remove unknowns. Before building his one-shot video workflow, Thariq asked Claude to explain how voice transcription tools like Whisper could fail. This helped him clarify the plan before getting Claude to create the video. Perhaps the most important learning here is that he actually reads the plan manually instead of just trusting AI.

3. Use /goal only if you have a verifiable finish line. I asked Claude to “/goal Build me a great game” and the results were…not great. Thariq shared how to use /goal to create polished videos with Claude by providing a verifiable end state (e.g., a rendered video). Here’s the exact prompt he used to create the video in one shot:

Read more

Get instant access

Dear subscribers,

Today, I want to share a new episode with Jared Zoneraich.

Jared is a Builder in Residence at Cognition, the team behind Devin. He showed me why teams often overbuild their first agents, and how simple prompts, better tools, and self-testing work together instead. Then he demoed one manager agent breaking down a task, directing 10 cloud agents, and deciding what a human needs to review.

Watch now on YouTube, Apple, and Spotify.

Jared and I talked about:

• (00:00) Why teams overbuild their first AI agent

• (02:50) Let the model cook before adding rules

• (03:16) Why tools matter more than better prompts

• (10:51) Why you should build evals after shipping

• (16:06) What cloud agents can do that local agents can’t

• (20:30) How to get one agent to manage other agents

• (25:39) Demo: One agent launches a team of 10

• (28:03) How agents prove their work before you review it

• (33:18) The best tasks for agent teams to work on

I’m proud to partner with Riverside

I produce a podcast every week and it used to take me at least 10 hours to record, edit, cut clips, write posts, and publish everywhere. Riverside has cut that time by half.

In addition to recording at 4K local with clean audio, I can also now edit using the transcript, add captions, make clips, and create and publish social posts all from one place. Riverside is trusted by teams like Spotify, Microsoft, and Vercel and you can try it for one month free at creators.riverside.com/PeterYang with code PeterYang.

Try Riverside for Free

Top 10 takeaways I learned from this episode

How to build great AI agents

1. Start by expressing your intent to the model in a simple prompt. “Let the model cook” by expressing your intent and constraints clearly instead of forcing it to follow deterministic instructions.

2. Give the model relevant tools to pull context. “Tool engineering” is giving the model ways to search your code, read logs, run tests, open the app, and inspect what it changed.

Read more

Get instant access

Dear subscribers,

Today, I want to share a new episode with Rohan Varma.

As a product manager on OpenAI Codex, Rohan has a firsthand look at how one of the most AI-native teams in the world works. He showed me how he uses Codex to automate work from Slack replies, prototype designs with image generation, replace stale PRDs with live sites, and more. Watch this episode if you’re tired of all the nonsense around “AI PM” and want to see how a real one actually operates.

Watch now on YouTube, Apple, and Spotify.

Rohan and I talked about:

• (00:00) Codex can do so much more than you think

• (01:53) Use Codex to pull context from Slack, docs, Linear, and email

• (03:28) How Codex flips planning from docs to demos

• (13:14) Demo: Do the task once with Codex, then automate it

• (14:30) Demo: Trigger Codex automations from Slack replies

• (17:26) Demo: Use Image Gen to explore design variants fast

• (19:58) Demo: Turn any Codex thread into a reusable skill

• (29:55) Demo: Turn project context into a shareable Site

• (33:33) Use one Codex thread to manage other Codex threads

• (37:18) Aim to be 10x more ambitious than feels reasonable

I’m proud to partner with Oceans Talent

I’ve been working with my Oceans Talent Executive Assistant for 3 months now and he’s helped me streamline my entire content pipeline from research to podcast post-production. He builds his own AI skills to save both of us hours every week. He’s more than an assistant and runs the whole system.

Oceans Talent places vetted, AI-fluent Executive Assistants who go beyond inbox and calendar, with backgrounds in marketing, operations, and finance so they can run your projects and own outcomes. Book a call today to get your first month free.

Get Started for Free

Top 10 takeaways I learned from this episode

Set up Codex as your work layer

1. Connect Codex to the tools where your work already happens. Rohan connects Codex to Slack, Notion, Linear, Gmail, Drive, and other tools. The magic starts when it can pull context from multiple connected tools and navigate to webpages that it has permission to access.

2. Use Codex to get up to speed on any project fast. Rohan said he can get added to a project last minute and quickly catch up by asking Codex to gather the Slack history, docs, Linear issues, email, and Drive context he is allowed to access.

3. Codex handles the manual work so PMs can spend more time with users. Since Codex can handle the manual PM work around information synthesis and follow-ups, Rohan has more time now to spend meeting enterprise customers and teams.

Automate the repetitive work

Read more

Today, I want to share a new episode with Jess Yan.

As product lead at Anthropic, Jess has a first-hand look at how Anthropic teams are moving from prompting AI to building long-running agents that work overnight. In our episode, Jess showed me how to build a Claude analytics agent from scratch, then covered how Anthropic PMs use agents internally to understand the codebase, monitor customer feedback, and make better product decisions.

Watch now on YouTube, Apple, and Spotify.

Jess and I talked about:

• (00:00) AI agents that work while you sleep

• (03:46) Claude Managed Agents help for long-running tasks

• (05:22) Demo: Building a Claude analyst agent from scratch

• (09:28) Traces: How to see where an agent got stuck

• (15:11) Evals: How agents grade their own work

• (20:20) 5 ways in which Anthropic PMs use agents internally

• (28:06) Processing a 4,000-company waitlist with agents

• (32:50) To build your first agent, focus on helping one person

• (36:54) What changes when agents can work overnight

Evan helps you be the most prepared person in a meeting

Evan is built to prepare you for high-stakes meetings. It pulls context from your apps, does CIA-level research on every attendee, and hands you a presidential-style briefing before you walk in. Built for founders, sellers, VCs, and anyone whose meetings are consequential, because showing up unprepared isn’t just awkward, it’s costly.

Get Your First Briefing Now

Top 10 takeaways I learned from this episode

Jess and I covered two topics in the interview:

1. How Anthropic PMs use agents internally

2. How to build long-running Claude agents

How Anthropic PMs use agents internally

Anthropic PMs use agents internally for at least five PM workflows:

1. Understanding the codebase. Instead of asking engineers what shipped or how something works, Jess can inspect pull requests, deployments, and product behavior directly. “Access to our codebase has been the biggest unlock for me.”

2. Synthesizing user feedback from multiple channels. Jess has agents monitor customer Slack channels to get more signal before deciding what to build next.

Read more