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

Upgrade to unlock this live workshop and full access to behindthecraft.com with my best AI courses, skills, tool credits, and workshops.

Get instant access

Here’s the recording and key takeaways from our recent live workshop. Paid subscribers can find all workshop recordings here.

Start with the architecture, not the interface

Read more

Today, I want to share my six-step process to design and build Tastemaker, a website for sharing your favorite movies, TV shows, and games.

You’ll learn how to define the problem, create a design.md, prototype in Claude Design, draft an interactive HTML spec, and build the app with AI.

Watch my 25-minute tutorial to see me cover all six steps live, or keep reading below.

Timestamps:

• (00:00) My six-step AI-native design process

• (00:50) Step 1: Define the user problem before building

• (02:25) Step 2: Get inspired and create a design.md

• (05:00) Step 3: Prototype key screens in Claude Design

• (12:59) Step 4: Create an HTML spec for product, design, and tech

• (17:02) Step 5: Design the core flows, default states, and edge cases

• (20:42) Step 6: Build the app with Claude Code

• (23:07) Recap: Why planning should take at least half your time

I’m proud to partner with Replit

Replit is now available inside Claude Design, so you can design beautiful apps and send them directly to Replit to build. To try it, simply select Share in Claude Design, open the Send to… menu, and choose Replit. Get 3 months of Replit free with code PYANG26 at checkout.

Get Replit for 3 Months Free

1. Define the user problem

I’ve watched thousands of movies and TV shows and played hundreds of video games over the years. But IMDb isn’t a great interface and Letterboxd doesn’t support games.

That’s why I decided to build Tastemaker to share my favorite movies, shows, and games all on one page. To kick off the project, I asked Claude Code to research and define the user problem with this prompt:

Here’s the problem statement Claude came up with:

Note how Claude used my spec skill to find real evidence that other people share the same problem. Of course, if I wanted to turn this into a real business, I would spend more time upfront talking to users to validate the opportunity. But since I’m building this as a personal app, let’s move on to step 2.

Get my /spec skill by upgrading to a paid membership

The last skill that I open-sourced, /no-ai-slop, went viral with 3.1K GitHub stars. I’m just as proud of my /spec skill that I use throughout this tutorial. It creates an HTML spec with the product, design, and tech requirements all in one place. Get it, along with 12+ other hand-crafted skills, by upgrading to a paid membership.

2. Get inspired and create a design.md

A design.md is simply a text file with guidelines for color, typography, spacing, and more. It’s a necessary step to avoid AI generating designs that have that recognizable Claude look.

To create a design.md, I like to start by finding inspiration. Recently, I came across a beautiful app called Monogram and love how it uses color to focus people on the content instead of the UI:

I copied a few of Monogram’s screens into Claude along with this prompt to create the design.md for Tastemaker:

Claude will then create a design.md like this:

For more inspiration, you can also check out Mobbin for app screenshots and designmd.sh for design.md files for popular products.

Quick note: Getting inspiration is different from straight-up copying an app.

I feel comfortable borrowing a little from Monogram’s design because Tastemaker is in a completely different product category.

With the design.md ready, let’s move to Claude Design to prototype the product.

3. Prototype key screens in Claude Design

Claude Design is my favorite AI-native design tool because it feels more like working with a design partner than using a tool.

Tip: You don’t need Fable to prototype with Claude Design. I found Opus perfectly up to the task if you want to save tokens.

Here’s the prompt, along with the design.md, to kick off the Claude Design project:

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’m open sourcing my /no-ai-slop skill that removes 20+ patterns of AI slop from any piece of writing.

I use this skill to edit everything from emails to docs, and I think you’ll love it too.

Get the skill for free on Github

If you find it useful, please consider starring the repository so more people can find it and upgrading to paid to get 12+ other quality AI skills I’ve made for personal advisor, agent-ready specs, viral social posts, and more. Keep reading for:

1. How to install and use the /no-ai-slop skill

2. My 25/50/25 rule for editing with AI

3. Why the dark side of slop is always calling

I’m proud to partner with Linear

I’m using Linear to manage my entire podcast production process with my video editors and it’s been great. With Linear MCP, I can create, edit, and track issues directly from Codex and Claude Code.

Try Linear for free

How to install and use the /no-ai-slop skill

To install the skill, just paste this in Codex, Claude Code, or your favorite AI harness:

Then you can use it in three ways:

1. “/no-ai-slop (text)” to edit your writing. The skill will remove all the AI slop patterns and list what it removed.

2. “/no-ai-slop is this slop? (text)” to detect AI writing. The skill will list all the slop patterns that it found.

3. “draft an AI slop post (text)” for some fun. Use it to generate the most cringe slop as satire like my LinkedIn comment below:

Jokes aside, even the best AI models (e.g., Fable 5 and GPT-5.6) still use most of the slop patterns below that /no-ai-slop will remove:

1. Binary contrasts. “It’s not X. It’s Y.”

2. Throat-clearing openers. “Here’s the thing,” “Let me be clear”

3. Faux-insight setups. “What nobody tells you,” “The part everyone misses”

4. Colon reveals. “The best part: it learns.”

5. Dramatic fragments. “That’s it. That’s the whole thing.”

6. Superficial analysis. “highlighting the team’s commitment to innovation”

7. Importance puffery. “marks a pivotal moment,” “a testament to”

8. Weasel attribution. “experts agree,” “studies show”

9. Synonym cycling. “The agent handles your email. The assistant drafts replies.”

10. Fake-profound endings. “The future isn’t coming. It’s already here.”

Here’s an example of using the skill to detect AI slop on a recent tweet I came across:

My 25/50/25 rule for editing with AI

Substack just shipped AI slop detection to protect readers. They featured my video as an example of how to use AI to edit while still sweating the details.

Basically, I work with AI in the middle 50% of my writing and editing process:

1. First 25%: I start by voice dictating or writing a rough draft without AI.

2. Middle 50%: I use my /newsletter and /no-ai-slop skills to work with AI to clean up the draft. AI helps me find grammar mistakes, improve clarity, and more.

3. Last 25%: I manually go through the piece line by line to make edits without AI.

I’d like to think that the difference between a creator who pumps out slop and a creator who cares about quality is giving a shit about the first and last 25%.

This applies to building with AI too. As Kun (AI builder) shared in our interview, AI handles the middle 50% where most of the code gets written. But you have to care enough about the first 25% (using your taste to shape the requirements) and the last 25% (validating the work) to make a product great.

Why the dark side of slop is always calling

The dark side of just letting AI draft and edit everything is always calling:

1. It’s easier to just give AI feedback to edit than to do it manually. Products like Codex and Claude Code seem to actively discourage you from making manual edits to files.

2. It’s easier to just be lazy and not write at all if AI is not available. For example, I used to be productive on long flights. But lately, I’ve become too lazy to write or edit anything without having AI available.

Perhaps most depressing of all, pumping out slop can drive real results.

Without naming names, I’ve seen some creators publish 10 AI slop posts per hour, every day. Some of those posts go viral and bring them more followers and revenue. But I like to remind myself that:

People who know AI can see the slop coming from a mile away.

A post can perform while still costing you trust with the people whose judgment matters to you. Consider these two examples:

1. Brian Chesky’s account got hacked and posted an obviously AI generated thread. Readers spotted it as AI before anyone confirmed the hack.

   

2. My friend, Alex Cohen, wrote a letter to his employees highlighting that pumping out slop puts an unfair burden on the reader.

Don’t let AI make you dumber and lazier

I’m not going back to editing everything manually, but I also don’t want to lose my ability to think or craft a sentence when there’s no Wi-Fi available.

So I’m going to hold the line at my 25/50/25 writing process. Trust is the only durable asset we all have, and slop hurts trust with the people who matter.

Get my free /no-ai-slop skill on Github and let me know what you think!

Get instant access

Here’s the recording and key takeaways from our recent live workshop. Paid subscribers can find all workshop recordings here.

How Julie’s AI-native design workflow works

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,

I now use ChatGPT Work and GPT-5.6 for almost everything I do on my computer, and I’m going to show you my full setup in this video and written guide.

You’ll learn how to choose the right GPT-5.6 model, connect your apps, manage email and calendar, automate recurring work, build Sites, and more.

Watch my tutorial now for the full 28 min walkthrough, or keep reading below.

Timestamps:

• (00:00) How I use ChatGPT Work for almost everything

• (01:04) Chat vs. Work vs. Codex: What’s the difference?

• (02:22) Which GPT-5.6 model and effort to use

• (03:18) Personalizing ChatGPT Work’s custom instructions

• (06:23) Connect your apps and organize your Work threads

• (09:30) Let ChatGPT manage email and draft replies in your voice

• (13:47) Schedule events and prep for meetings automatically

• (17:19) Automate recurring work with scheduled tasks

• (19:23) Continue your Work tasks from your phone

• (21:01) Publish travel guides, games, and product plans as Sites

I’m proud to partner with Wispr Flow

I use Wispr Flow to dictate first drafts much faster than I can type. It helps me get my ideas down while they’re still fresh, so I can focus on editing. I use it all the time in ChatGPT Work and Codex, and it’s been a huge time saver. Try it for free with my link.

Try WisprFlow for Free

Chat vs. Work vs. Codex: What’s the difference?

Here’s the simplest way to think about the three modes:

1. Chat is the regular ChatGPT we’re all familiar with.

2. Work lets ChatGPT take action in your favorite apps.

3. Codex adds features designed for coding and developers.

Honestly, I’m not a fan of Work and Codex existing as separate modes. As far as I can tell, there are only small differences in the UI and how responses are presented. For example, Codex adds a Pull Request tab that developers can use to review each other’s code.

So I don’t think it makes much difference whether you use Work or Codex. My recommendation is simple:

Use the ChatGPT desktop app which is far more capable than ChatGPT for the web.

Which GPT-5.6 model and effort should you use?

GPT-5.6 comes in three variants (Sol, Terra, and Luna), each with five effort levels from Low to Ultra. So which model and effort should you default to?

Here’s a chart that shows intelligence vs. output tokens for the various options:

Based on this chart and my experience, I recommend that you:

Use GPT-5.6 Sol (medium) for the best balance of intelligence and token use.

I sometimes use Sol (high) for planning, but overall I haven’t noticed much of a difference between that and medium. I almost never use Terra or Luna.

Personalize your ChatGPT Custom Instructions

On a fresh install, I go to Settings → Personalization and set my Custom Instructions to:

1. Teach me technical concepts without using jargon.

2. Challenge my thinking instead of agreeing with every prompt.

3. Remove AI slop phrases and patterns.

Here are my exact custom instructions if you want to copy my setup:

Install plugins to let ChatGPT use your favorite apps

Plugins connect ChatGPT Work and Codex to the apps you use every day.

The screenshot above shows some of the plugins I have installed. I think the bare minimum set is:

• Gmail

• Google Calendar

• Documents, Presentations, Spreadsheets, and Google Drive

Other useful plugins include the PDF plugin for editing PDFs, Slack for messages, Notion for wiki articles, Figma for design, and Granola for meeting transcripts.

Install plugins for any app that you want ChatGPT to use. This is the key setup step that makes ChatGPT Work and Codex your everything app.

Use long-running threads for each type of work

As you use ChatGPT Work more, you may get overwhelmed by all your active projects and threads. To avoid this:

Keep one long-running thread for each type of work.

For example, in my Personal OS project, my threads include:

1. Newsletter to edit all newsletter posts.

2. Social for drafting and making posts for social networks.

3. Podcast to prep and do post-production for interviews.

ChatGPT Work and Codex are very good at compacting long conversations, so you can keep chatting in the same thread without worrying about GPT getting confused.

I also pin my most-used threads, such as my Advisor thread for strategy and business advice and my Chief of Staff thread for email, calendar, and more.

Set up a chief of staff thread for email and calendar

These days, I manage my email and calendar almost entirely through ChatGPT Work and Codex instead of opening Gmail or Google Calendar. Let me walk through how I:

1. Find forgotten follow-ups and subscriptions to cancel

2. Draft email replies that sound like you

3. Manage your calendar and avoid meeting conflicts

4. Get briefed on upcoming meetings

1. Find forgotten follow-ups and subscriptions to cancel

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

OpenAI just made GPT 5.6 available to everyone and I’m here to answer your most burning question:

Is GPT 5.6 better than Claude Fable 5?

The answer is, it depends. 😅

Watch my tutorial to see me test both models head-to-head for building a travel website, 3D Star Fox game, mobile app, and more.

Timestamps:

1. (00:00) GPT-5.6 vs Claude Fable 5 compared

2. (01:45) Build an interactive travel website

3. (05:44) Create a 3D Star Fox-style game

4. (09:39) Edit and publish short videos with browser use

5. (15:10) Plan and build a mobile app feature

6. (19:34) Get personalized life and business advice

7. (22:17) Improve and clean up a personal AI OS

8. (24:37) My takeaway on each model’s strengths and weaknesses

I’m proud to partner with Riverside

Right now, most creators spend 20% of their time creating, and 80% on editing and distribution. Riverside just launched 2.0 to make it easy for me and other creators to turn a single recording into a fully produced content engine across all my channels.

After recording, Riverside uses a team of agents to create clips, schedule social posts, and more. 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 1 Month Free

GPT 5.6 vs. Fable benchmark and cost comparison

GPT 5.6 comes in three models: Sol, Terra, and Luna.

Sol is the flagship model and based on TerminalBench it actually performs slightly better than Claude Fable 5 at coding:

But I think OpenAI’s biggest advantage is model efficiency and cost. GPT 5.6 Sol is 50% cheaper than Claude Fable 5 at API prices:

That’s a big deal because enterprises are increasingly looking for the most cost-effective model. However, benchmarks only tell half the story, let me show you how both models perform on the 6 use cases below:

1. Build an interactive travel website

GPT has historically lagged behind Claude on front-end design so I wanted to see if GPT 5.6 has closed that gap. I’m planning a trip to Japan in December so I gave both models my Google Doc itinerary and the prompt below:

Tip: Ask AI to “add a 3D WebGL element to the hero banner” if you want to create websites with beautiful animated 3D graphics

I ran the same prompt through GPT 5.5, GPT 5.6, and Fable:

1. GPT 5.5 created a functional website but botched the 3D hero image.

2. GPT 5.6 created an animated torii gate and found more relevant photos.

3. Fable 5 created beautiful animated snowflakes in a winter scene.

Watch my video to see how all 3 websites look.

Verdict: Tied because GPT 5.6 has really closed the gap with Fable on frontend design.

P.S. We’ve started hosting regular live workshops in my Slack community for AI builders. Upcoming workshops include:

1. July 17 - AI native design (design.md, components, etc) with Julie Xu

2. July 24 - Building production apps with Colin Matthews

3. August - Deep dive on AI evals with Hamel Husain

All workshop recordings will be shared here for paid subscribers.

Subscribe for Full Access

2. Create a 3D Star Fox style game

Growing up, Star Fox was one of my favorite games on the Super Nintendo. So naturally, I had to ask both GPT 5.6 and Claude Fable 5 to build a fully playable Star Fox level complete with enemies, power-ups, and even a boss battle.

Both produced incredibly impressive results:

Here’s the exact prompt that I used to build these games in one shot:

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

Get instant access

Dear subscribers,

Today, I want to share 18 hot takes on where I think the AI market is headed.

AI is in a weird place right now. The government is restricting access to frontier models, enterprises are becoming conscious of token costs, and everyone’s trying to rebuild their product for agents first instead of humans.

I’ve interviewed dozens of AI leaders and spent far too much time following these topics on X/Twitter. Here are 18 hot takes on where I think AI is headed next:

1. The frontier-only AI stack is collapsing

2. The AI super app era is here

3. Traditional software risks becoming a dumb pipe for agents

4. Cloud agents and collaboration are the next wave

I’m proud to partner with Oceans Talent

My Oceans Talent Executive Assistant started by doing simple admin tasks but has now built his own AI skills to turn podcast episodes into clips, social posts, and more. Sourcing someone this capable on my own would have taken months.

Oceans Talent is execution capacity you can hire this week. They provide vetted, AI-fluent executive assistants with backgrounds in marketing, operations, and finance to run your projects and own the work. Book a call today to get your first month free.

Get Started for Free

The frontier-only AI stack is collapsing

1. Tokenmaxxing at frontier API prices makes no sense. Uber burned through its entire 2026 AI budget in 4 months, Microsoft moved engineers off Claude Code due to cost, and companies are realizing that running everything on frontier models can get expensive fast. Tokenmaxxing makes sense when you’re on a subsidized $200/month plan but is unsustainable at API rates.

2. Companies will rely on a portfolio of models. Coinbase recently cut its AI spend nearly in half by switching engineers to Chinese open-source models like GLM and Kimi. Airbnb and Pinterest have done the same with Alibaba’s Qwen models. I believe that this will be the default path forward — using frontier for high-stakes work and cheaper models for everything else.

   

3. China’s open-source strategy is working. Chinese models are taking market share from frontier models at US companies. China is also building the full AI stack — from energy (e.g., solar, nuclear) to data centers to domestic chips. The Chinese government is planning a $295B investment in AI data centers with at least 80% of the chips built domestically.

4. Frontier labs are in a catch-22 situation. If they release great open-source models, they might undercut their own frontier API revenue. If they gate the best models behind a trusted list, companies will just lean on open alternatives more. The last major US open-source model was OpenAI’s gpt-oss series back in August 2025, which already feels like decades ago in the AI space.

   

5. The US needs to think about its AI strategy holistically. I believe that restricting access to frontier models will only hurt American innovation. Banning US companies from Chinese models won’t work either. Just look at how China took over the global electric vehicle market. To compete, we need the best closed and open models while scaling our energy grid and data centers much faster.

The AI super app era is here

6. Anthropic and OpenAI want to transform all knowledge work. Both labs want to remake how white-collar work gets done with agents. What started with coding has expanded to design, finance, legal, science, and more. Knowledge workers are now adopting Codex three times faster than developers.

7. The race to build the best AI super app is on. Whoever wins it will take massive market share away from pre-AI knowledge work tools. The main players are Codex, Claude, Cursor, and a few others. With browser and computer use, I can already get Codex to handle almost everything I want to do on my computer.

8. OpenAI is well positioned to win the super app race. ChatGPT has 800M+ weekly active users and Codex is arguably the best AI super app right now. OpenAI has a clear opportunity to merge ChatGPT and Codex into one app and push agents into the mainstream. I think this is imminent.

   

9. Anthropic leads enterprise but has a fragmented product suite. Long term, I don’t think it makes sense for Claude, Cowork, Claude Code, and Claude Design to all exist as separate products. Working with Claude needs to feel more like working with a single capable coworker instead of a product suite. Claude Tag, Anthropic’s new agent for Slack, is a step in the right direction.

Software risks becoming a dumb pipe for agents

10. Agents are becoming the default user. Most products are still designed for humans clicking buttons, but agents will very soon read, write, buy, and do a lot more on our behalf. Cloudflare’s data shows that bot traffic to websites already exceeds human traffic. This matches my personal experience — I rely on agents like Hermes and Codex to browse websites and steer traditional apps.

    

11. If your product isn’t built for agents, it might as well not exist. Without clear APIs, documentation, and CLIs or MCPs, agents simply won’t discover your product, and neither will the humans who now lean on agents to find things. That’s why the best AI builders I’ve interviewed are all building for agents first.

12. Existing knowledge work products risk becoming dumb pipes. There’s a dark side to building everything for agents first. Take Google Workspace, for example. If I can just use Codex to edit Google Docs for me, I might never touch the Google Docs interface. Today’s apps risk becoming tomorrow’s dumb pipes for agents, the same way cable became the dumb pipe for internet apps.

13. Adding an AI chatbot to your product isn’t going to save you. A chatbot trapped inside a single app, with only that app’s context, can’t compete with an agent like Hermes or Codex that carries my personal context and gets work done across many apps. For example, I get a daily morning brief from Hermes that pulls info from my calendar, unread emails, and Slack.

14. Pure-play SaaS is losing to services with SaaS bolted on. Companies don’t want another SaaS tool to onboard to and maintain. Instead, they want an outcome delivered to them. Pure-play SaaS will struggle to compete with AI skills that users and teams can build and personalize inside their favorite AI super app.

    

Cloud agents and collaboration are the next wave

15. Startups can compete with AI labs by going deep and using a portfolio of models. For example, coding startups like Devin and Factory are doing well because their harnesses route across multiple models to help customers save on cost without giving up performance. They’re also focused on a few specific use cases instead of trying to be everything to everyone.

16. Always-on cloud agents will be accessible from any device. Running agents with your laptop half-open will feel silly soon. Instead, many builders are already launching cloud agents using Cursor, Devin, and others. Codex and Claude Code are no doubt working on the same experience, and this will be the default soon.

17. Collaboration between agents and teams has yet to be figured out. The default agent harness with a list of threads on the left is still very much a single-player experience. The multiplayer experience is still being defined — whether that’s Claude Tag in Slack, agents in Linear, or something else.

18. “The future isn’t 20 terminal tabs. It’s better loops.” I watched Peter Steinberger share this in his keynote at yesterday’s AI Engineer conference. He no longer watches the agents code. Instead, he defines the requirements, and let agents plan, execute, and validate by themselves. I’m a bit wary of loops since they can lead to AI slop, but I’m sure better planning and models will make them more mainstream.

The AI market is about to get a lot more interesting

Here are my 18 takes summarized in four bullets:

1. The frontier-only AI stack is collapsing. Companies will use a portfolio of models to save costs, with everyday tasks defaulting to low-cost open models from China.

2. The AI super app era is here. Codex, Claude, Cursor, and others are competing to disrupt knowledge work by using agents for everything you can do on a computer.

3. Traditional software risks becoming a dumb pipe. Agents will become the default user. They’ll use APIs and browser use to access your website and app without humans ever seeing them.

4. Cloud agents and collaboration are the next wave. The future is agents living in the cloud, accessible from any device, and collaborating closely with both you and your team. This will happen very soon.

Let me know what you think about these takes in the comments!

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

Today I’m excited to launch my beginner-friendly Hermes course with 17 opinionated lessons to set up my favorite AI chief of staff in a single afternoon.

This course covers everything from installation to integrations (e.g., email, calendar, Google Workspace) to cron jobs (e.g., morning briefing, health check).

Watch my free 45-minute walkthrough on YouTube. If you want the written version with all 17 lessons and copy-paste skills, consider upgrading to paid at behindthecraft.com.

What the course covers:

• (00:00) Why Hermes is the best 24/7 AI chief of staff

• (01:16) Where and how to install Hermes safely

• (02:55) The best AI model to pick for Hermes

• (05:04) Connect to Telegram for mobile chats

• (11:08) How Hermes uses tools, memory, and skills

• (12:39) How to personalize Hermes by editing its user and soul files

• (15:49) Two best ways to troubleshoot Hermes

• (18:15) Set up Hermes to respond via voice

• (22:47) Connect Gmail, Calendar, Docs, Drive, and Sheets step by step

• (38:25) Create routines like morning briefing, health check, and more

Why Hermes and what’s inside the course?

Hermes is, in my opinion, the best AI chief of staff available today. It’s reliable, free to use (you just need a $20 ChatGPT subscription), and very powerful.

That’s why I spent 20+ hours writing 17 opinionated lessons covering three tracks:

1. Quickstart: Get Hermes running in less than 30 minutes.

2. Integrations: Let Hermes work in your favorite apps (e.g., email, calendar, docs).

3. Cron jobs: Set up morning briefings, health checks, business reports, and more.

Upgrade to Get My Full Hermes Course

Here’s what each track covers.

Quickstart: Get Hermes running in less than 30 minutes

Learn how to install Hermes safely, connect it to your phone via Telegram, and personalize it to be yours by editing its user and soul files.

This track covers:

1. Where to install: Set up Hermes on your laptop, Mac Mini, or virtual server.

2. Install Hermes: Download the desktop app and pick your AI model.

3. Connect Telegram: Create your bot and chat with Hermes from your phone.

4. How Hermes works: A beginner-friendly guide to memory, tools, and more.

5. Personalize Hermes: Edit its user and soul files to make it genuinely useful.

6. Troubleshooting: My two favorite ways to fix Hermes if you get stuck.

Integrations: Connect the apps you already use

Integrations are what make Hermes more useful than a chatbot. Start with voice replies and Google Workspace, which I think are must-haves. Then consider linking Granola for meetings, GitHub for backups, YouTube for research, and more.

This track covers:

7. Voice replies: Talk to Hermes while on the go.

8. Google Workspace: Connect Gmail, Calendar, Docs, Sheets, and Drive.

9. WhatsApp: Use Hermes from WhatsApp with a second phone number.

10. Slack: Add Hermes to Slack for threaded discussions.

11. Granola: Let Hermes analyze your meeting notes.

12. GitHub: Back up Hermes and let it work with your repos.

13. YouTube: Let Hermes summarize videos and research for you.

Cron jobs: make Hermes proactive

Last but not least, cron jobs (or scheduled routines) let Hermes do work for you proactively. I cover how to set up my favorite cron jobs including:

14. Weekend planner: Find fun, time-sensitive family activities for the weekend.

15. Morning briefing: A daily check of your email, calendar, and more.

16. Business review: A weekly insights email with your financials and more.

17. Health check: A weekly review with your weight, workouts, and more.

My goal is to create the most practical AI membership online

With today’s update, paid subscribers can now access all of the following on the Behind the Craft membership portal:

1. 12+ skills and 20+ prompts handcrafted for personal, product, and creator work.

2. 17 lessons on setting up your AI chief of staff with Hermes.

3. Full Codex and Claude Code courses coming later this year.

We’ve also started hosting monthly expert-led live AI workshops in our AI Slack community, starting with my walkthrough of my Codex setup last Friday.

Again, I’ve made the full 45-minute walkthrough free on YouTube to make it easy for you to set up Hermes. If you’d like the written course, my AI skills, live workshops, and upcoming Codex and Claude Code courses, consider upgrading to paid.

Thanks!
Peter

Get instant access

Here’s the recording and key takeaways from our recent live workshop. Paid subscribers can find all workshop recordings here.

How to decide what to automate

Read more

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

Bin and Jake built HyperFrames, a free open-source tool that turns HTML into product launch videos that used to cost thousands of dollars ot make. In this episode, they showed me how to one-shot a video from any website. Jake also revealed his full 5-step video workflow to make polished videos with Codex or Claude Code.

Watch now on YouTube, Apple, and Spotify.

We talked about:

• (00:00) From HTML to professional launch videos with AI

• (02:16) Getting started: Install HyperFrames for free

• (03:50) /website-to-video: Turn any URL into a launch video

• (08:28) Jake’s 5-step playbook to generate better videos

• (10:03) Step 1: Gather assets and create a frame.md

• (11:46) Step 2: Create a storyboard.md with the scenes

• (12:45) Step 3: Pull animations from HyperFrames launches

• (15:43) Step 4: Generate and review static frames

• (17:20) Step 5: Build the video and polish in Studio

I’m proud to partner with Wispr Flow

When I’m building with Codex or 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

Getting started with Hyperframes

1. Install HyperFrames for free to make videos from HTML. Hyperframes is a free and open source repository for making videos. To install it, just type “npx skills add heygen-com/hyperframes” in terminal or point Codex or Claude Code at the repo.

2. After HyperFrames is installed, try the website-to-video skill first. In Codex or Claude Code, prompt “Use /website-to-video to turn [paste URL] into a 30s promo video.” Paste a website you like, and HyperFrames will make the launch video in one shot by pulling the site’s screenshots, assets, copy, and brand look.

Jake’s 5-step playbook to generate better videos

While Hyperframes makes it easy to generate basic videos, it still takes a bit of work to generate professional animated videos like the above. Jake shared his 5-step playbook with me to do just that:

Here’s a detailed walkthrough of each step:

Read more

Today, I want to show you how to build an AI advisor that helps you think through important life and career decisions.

This is my favorite AI skill because it knows my goals, gives me useful feedback, and gets better the more I talk to it.

Watch my tutorial now to see how my /advisor skill works and how you can build your own in 13 minutes.

Timestamps:

• (00:00) Why I built a personal AI advisor

• (02:09) skill.md: How to define the advisor’s behavior

• (03:31) plan.md: The context file with goals, principles, energy, and life details

• (07:54) learnings.md: How the advisor remembers patterns over time

• (09:22) eval.md: What AI checks before giving me advice

• (10:15) Demo: Using Anthropic's Fable for deeper advice

• (11:31) How to build your own advisor skill now

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

How my AI advisor helps me make decisions

I recently made a video sharing why I decided to leave my job to bet on myself.

What I didn’t share is that I talked to my AI advisor for over 3 months leading up to that decision. It gave me advice like:

“Your decision is psychological and about letting go of the person you spent a decade becoming.”

“Your kids are eight and four and will grow up fast. Your goal isn’t to maximize income, it’s to make enough so you can spend more time with them.”

My /advisor skill has been so useful because it has context about my goals, family, work, financials, and energy to help me think more clearly.

The whole setup is basically a folder with a few text files:

Let’s walk through each file and how you can build your own version.

1. Skill: How you want the AI to give you advice

Your skill.md should not contain a bunch of personal information about yourself.

Instead, it should tell AI what role to play, what context to read, how to advise you, and what to remember over time. Here’s the full skill.md for my AI advisor:

This file defines the advisor’s behavior. The next file gives it your personal context.

2. Plan: Important context about your work and life

Paid subscribers can keep reading for the full /advisor setup, including my plan.md structure, learnings.md examples, eval.md checklist, and more.

Read more

Today, I want to share a new episode with Matt Van Horn.

Matt doesn’t have a CS degree, know how to code, or even read the plans that AI writes. Despite this, he’s built an incredible open source track record with projects like last30days (#1 trending on GitHub with 44K+ stars) and Printing Press (a tool that lets agents use any website or app). Matt has been a huge inspiration for my AI builder journey, and I think you’ll feel the same after watching our conversation.

Watch now on YouTube, Apple, and Spotify.

Matt and I talked about:

• (00:00) "I don't read code and the plans are for AI"

• (01:19) Compound Engineering: Matt’s go-to agentic loop

• (07:07) How Matt builds without a CS degree or reading code

• (11:18) Printing Press: Turning any website into an agent CLI

• (15:38) How Printing Press finds hidden APIs and GitHub projects

• (22:44) Why CLI + skill beats MCP for agent workflows

• (32:49) How Matt contributes to Python, Go, and other top repos

• (44:28) Why Matt is still afraid to launch finished projects

I’m proud to partner with Riverside

I’ve used Riverside for years because it records each person locally in up to 4K, so my podcast audio and video stay clean even when a guest’s wifi gets shaky. Now it also helps me edit from the transcript, clean up audio, generate captioned clips, and publish everywhere from one place. Use code PeterYang at checkout for 1 month free.

Try Riverside for Free

Top 10 takeaways I learned from this episode

1. Use Printing Press to give your AI access to almost any website or app. Matt open sourced Printing Press to let anyone generate a CLI (command line interface) for any website or app. It works by researching docs, finding niche GitHub repos, and sniffing hidden API requests, so agents can use sites like Google Flights, Suno, OpenArt, and more.

2. If you’re non-technical, use Compound Engineering skills to build. Compound Engineering is a set of AI coding skills that lets anyone build with AI in a more structured way. Matt’s go-to skills include:

   1. /ce-plan to research the codebase, edge cases, and implementation path.

   2. /ce-work to execute the plan while following the project’s patterns.

   3. /ce-brainstorm to think through the feature and produce a requirements doc.

   4. /lfg to run the full loop from planning to implementation to PR.

To install it, point your favorite coding agent (e.g., Codex / Claude Code) at this link:

Read more

Last year, I made seven figures at my product job. Last week, I left that job to bet on myself.

This wasn’t an easy choice to make. After over a decade in product, walking away from a great job felt like giving up a core part of my identity.

What finally helped me decide were 5 principles I wrote down after a lot of reflection.

Watch my video now to hear how I made this decision and perhaps it can help you think through your next career move too.

Timestamps:

• (0:00) Why I quit my high-paying product job

• (0:23) Go where work feels like play

• (3:44) Give yourself permission to build

• (5:35) At some point, trading time for wealth just isn't worth it

• (8:33) Surround yourself with people who share your curiosity

• (10:11) The people you love won't be there forever

• (13:57) What I'm doing next (and a promise)

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.

Try Riverside for Free

1. Go where work feels like play

I became a PM over a decade ago because I wanted to ship great products. I loved the loop of understanding problems, identifying solutions, and executing to craft something great.

This loop is exactly what I got to do at Roblox. I have a lot of fond memories from shipping products like thumbnail personalization, configs & experiments, and AI analytics with my talented team of engineers, designers, and PMs. Most of all, I loved watching Roblox creators light up as we put these products in their hands.

But there’s another side of product management that I didn’t love, and it exists in some form at all the great companies that I’ve worked at. I call it product management theater, and it’s when the focus shifts to:

1. Polishing internal docs over the actual user-facing product.

2. Getting stakeholder alignment over doing what’s right for customers.

3. Climbing the career ladder over shipping products you’re proud of.

For example, early in my career, I spent 4 hours in a meeting with other PMs aligning on quarterly OKRs. That was one of the longest days in my PM career. Being stuck in that room is what pushed me to write my very first newsletter post. I desperately needed to ship something, even if it was just a blog post. That post became this newsletter, which now has almost 150K subscribers.

There’s a framework I come back to whenever I’m making a big career decision called the Zone of Genius. I use it to sort my work into 4 zones:

• Zone of genius is what you’re great at and love doing.

• Zone of curiosity is what you suck at but still love learning about.

• Zone of excellence is what you’re great at but hate doing.

• Zone of incompetence is what you suck at and have no desire to improve.

My zone of genius is building products with customers and sharing what I learn with you all. My zone of curiosity is getting better at building with AI agents. But all that PM theater I just described falls squarely into the other two zones.

I realized that I don’t want to spend my day in back-to-back meetings, no matter how much money or prestige comes with those jobs. I also realized that I was waking up at 6 AM every day to write this newsletter, even though I didn’t make any money from it for years.

Of course, I also loved crafting products and sharing memes with my team, and honestly I miss that already. But life is about trade-offs, and I wanted to spend more of my day in my zones of genius and curiosity.

So I encourage you to map out your own zones and be honest about what you actually enjoy, even if you’re not making money from it right now.

For me, I love building and get antsy if I can’t ship anything in a week, which brings me to the second principle.

2. Give yourself permission to build

The career ladder pushes everyone to be a leader, but I just want to be a builder.

The reality is that a lot of product leaders have calendars that look like this:

Because of this calendar, the only time that I really had to build was on nights and weekends.

Now don’t get me wrong, I enjoy helping people grow and think I’m good at it. But I never want to give up the craft of making great products. I love being hands-on and obsessing over every little detail, from the copy to the UX to the marketing, because that’s what it takes to make a product great.

I also loved being able to check in code myself as a PM with AI’s help. Here’s the tongue-in-cheek GitHub profile that I used at work:

Yet, as you climb the ladder at most companies, you’re expected to step away from building and fill your time with product reviews, cross-functional alignment, managing up, and performance calibrations.

The good news is that this is finally changing. Companies are rewarding builders and ICs more than ever, and even managers are increasingly expected to do IC work too.

But becoming a good builder takes reps, and it’s just hard to put in those reps when you’re in back-to-back meetings all day.

So if you’re a builder at heart, embrace it. You don’t have to give up what you’re good at to be a “leader.”

It doesn’t matter if you’re an engineer, PM, marketer, or designer. Learn how to build.

3. At some point, trading time for wealth just isn’t worth it

Most people in tech are obsessed with total compensation and getting that next title.

If you’ve spent any time on Blind, you know what I’m talking about. Everyone is comparing how much they make, what their title is, and whether they work at OpenAI, Anthropic, or FAANG.

Look, I get it. Put in a few years at one of these companies and you can make generational wealth. But the people who hit all of these goals often have the least control over their time.

If you’re a VP, for example, chances are you’re in back-to-back meetings from morning to night. Kudos to anyone who can do that job well, but it’s just not the life I want. Instead, here’s what I figured out after the highest-earning year of my career:

Past a certain point, more money is not worth giving up agency over your time.

Real agency inside a company is rare. You might pour yourself into a promising product that gets canceled. You might have a great manager who gets re-orged out. So much of it is out of your hands.

And while I have a lot of respect for VC-backed founders, that life also sounds very stressful. You’ll have investors, a board, and payroll to satisfy every month whether you like it or not. With a VC-backed company, you have to go big or go home. You can’t just hit profitability and call it a day. Your investors will push you to 10x or 100x the business.

The path I want to try is being a bootstrapped founder of a small business. As long as I can pay the bills, I’m willing to trade off hundreds of thousands of dollars to be able to decide who I work with, what I work on, and how hard I work. It’s only been a week, but I love waking up to a calendar with no meetings before the afternoon and enough time to chase my curiosity and share what I learn with you all.

The funny thing is, growing up, I didn’t even know this was a real path. I chased prestigious schools and brand-name companies and thought there were only two options: climb the ladder in big tech, or raise money and build a unicorn.

But I think bootstrapping makes a lot of sense now for many people. It’s cheaper than ever to start a business, and a single person with AI tools and agents can get a lot done.

To wrap up this section, there’s this image from Wait But Why that brings into perspective just how little time we all have:

I’m in my early 40s so almost half of my time is already over. If you’re in my shoes, realize that:

The hedonistic treadmill of chasing money and prestige can become a trap. Time and agency are the most valuable assets we have.

4. Surround yourself with people who share your curiosity

One of the best ways to spend your time is with people who share your values and goals.

These days, I mostly make new friends through my kids’ playdates or online. X can be toxic if you’re just doom scrolling, but I’ve made some good friends there who gave me the courage to make this bet. I think everyone should have a few group chats with people who are on the same journey as them.

Two group chats that I rely on are:

1. A YouTube learning group started by my friend Steve Huynh, who spent 14 years as a principal engineer at Amazon before building his own business. I joke that Steve’s group is bad for the economy, because everyone in it eventually walks away from their high-paying tech job to build their own thing.

2. A PM creator group started by Ben Erez, with folks you might know like Lenny, Elena, and others. Everyone in it is a PM or product leader who’s also teaching, creating, and building.

My point is that it’s important to find people who share your values and goals. People who are honest, encouraging, and open, who won’t put up a front, and who’ll give you the courage to make decisions like this.

Courage is contagious. Hang out with people who’ve done some version of what you want to do and who are honest about the parts that are great and the parts that suck.

5. The people you love won’t be there forever

I think about my parents a lot these days. They sacrificed a lot to move to Canada and give me a good education. Now, they’re retired and honestly living the good life, going on cruises all the time.

The thing is, once you’re retired, nobody cares what your title was, how much money you made, or which company logos are on your LinkedIn.

And the reality is that at most companies I’ve worked at, there are only a handful of coworkers I still keep in touch with. Almost everyone else moves on the moment your employment ends.

So if work isn’t the relationship that lasts, then it has to be the people we too often put second: our family and close friends.

Being a PM and a creator at the same time made me feel productive, and the dual income was great, but I hadn’t had breakfast with my kids in months. I was just working all the time.

Over the past week, I’ve been walking my 8-year-old daughter to school. It’s twenty minutes each way, twenty minutes that I used to spend stuck in traffic or on Slack. Now I spend it with her, and she tells me about her friends, her dreams, and the things she’s worried about. This walk is now the highlight of my day.

Before I quit, I promised my wife I’d spend more time being present with my kids. Parenting is hard and I’m far from perfect. Sometimes I just want to shut myself in a room and play video games. But I now have a lot more time to try to keep that promise.

Nobody wants to put on their tombstone that they got divorced and neglected their family, but at least they made VP at Meta.

The people you love won’t be there forever, so spend more time with them while you can.

The 5 principles that helped me make my decision

Here are the five principles again that led to my decision to leave a high-paying job to bet on myself:

1. Go where work feels like play. Map out your zone of genius and be honest with yourself about what you actually enjoy doing.

2. Give yourself permission to build. If you're a builder at heart, embrace it, because you don't have to give up what you're good at to become a "leader."

3. At some point, trading time for wealth just isn’t worth it. Real wealth is having agency over who you work with, what you work on, and how hard you work.

4. Surround yourself with people who share your curiosity. Courage is contagious, so find people who are on a similar journey as you.

5. The people you love won’t be there forever. Make time for your family and close friends while you still can.

One more piece of practical advice if you’re feeling the same itch to bootstrap:

Don’t take a blind leap. It took me three years to get here, and I didn’t make the jump until I was making around the same from my business as my product salary. Start by tinkering and building things on the side while showing up fully at your day job. I took pride in my work at Roblox until my last day.

Here’s what I’m doing next

For now, my focus is on delivering the most practical AI tutorials and interviews available online. That means:

1. Making this channel and my newsletter the best place to learn AI online without the hype.

2. Building behindthecraft.com into a valuable membership where you can get my personal AI operating system, AI tools, and community access.

3. Building products with AI myself and sharing all the wins and the mistakes along the way.

One more thing — it’s so easy to pump out AI slop these days, but I think trust is the only currency that matters for creators and builders. I’ll use AI to save time, but I promise that everything I publish will be reviewed by my own eyes and AI slop free.

And if I ever get too cringe, you should hold me accountable.

Watch my video and I’m happy to answer any questions in the comments.

Today, I want to share a new episode with Kun Chen.

Kun is an ex-L8 principal engineer at Meta who now ships up to 40 PRs a day while rarely reviewing code. In our episode, he walked through the free tools he built to make that possible: Lavish for visual planning in HTML, Treehouse for parallel agents, and No Mistakes for catching AI’s errors before they make it to production.

Watch now on YouTube, Apple, and Spotify.

Kun and I talked about:

• (00:00) Why he doesn't review code anymore

• (01:04) Agentic engineering: Plan, code, validate

• (06:22) Demo: Fixing an AI tutor screen with agents

• (08:40) Demo: Why HTML is better than markdown for planning

• (19:53) How to turn a rough idea into an AI-ready spec

• (23:21) How Kun runs 20-30 agents in parallel

• (32:04) No Mistakes: Kun's free AI code review tool

• (45:19) What Kun checks before merging AI-written code

• (50:18) How to get better at agentic engineering

I’m proud to partner with Linear

As teams ship faster with AI agents, the bottleneck shifts from building to deciding what to build.

Linear’s new Agent understands your full workspace context: roadmap, issues, customer requests, and code. Ask it to surface patterns across feedback, scope out a spec, or catch you up on team progress.

Try Linear for Free

Top 10 takeaways I learned from this episode

1. Code faster with a team of AI agents. Kun sees himself as the manager of an always-on engineering team. His job is to create plans, validate work, and improve the overall system. Specifically, he runs the same three phases each time:

   1. Plan: Building clear plans is now the most important phase.

   2. Implement: Coding is now handled almost entirely by agents.

   3. Validate: Agents check the work first and only escalate to Kun if needed.

Plan: Spend most of your time here

2. Plan quality determines how long agents run on their own. A one-line prompt might get the agent to work for a few minutes while a detailed plan can keep it working for hours. To delegate more work to agents, move up these three planning levels:

Read more