The argument in one line.
Claude Code isn't the bottleneck on your output — your attention habits, planning discipline, and judgment about when to use AI at all are, and six concrete fixes close that gap.
Read if. Skip if.
READ IF YOU ARE…
- Someone using Claude Code daily for real work who feels like their output isn't scaling with all the AI hype.
- A solo builder or small team lead trying to build a repeatable plan-execute-verify workflow instead of ad hoc prompting.
- Anyone building Claude skills or automations who wants a gut-check for when automation is premature versus proven.
SKIP IF…
- You're looking for prompt syntax, model comparisons, or a specific coding tutorial — this is entirely about operator habits, not the tool itself.
- You already run a disciplined plan-execute-verify loop with explicit CLAUDE.md verification language and wired-up MCP servers.
The full version, fast.
This video argues that Claude was never the bottleneck — the operator's habits are. It walks through six fixes: matching task difficulty to your energy instead of treating every hour the same, protecting brand quality now that production is nearly free, replacing ad hoc prompting with a plan-execute-verify loop (the single lever Anthropic says moves Claude's output quality most), running a 5-step filter — question, delete, simplify, augment, automate — before reaching for AI on any process, grounding new AI concepts in one real example instead of staying abstract, and shipping the good 80% instead of chasing a perfect 100% that rarely arrives.
Free for members
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Create a free account →Where the time goes.
00:00 – 00:18
01 · Cold open — the real bottleneck
Frames the entire video: hundreds of Claude tutorials miss that the person using the tool, not the model, is the actual constraint on output.
00:18 – 01:56
02 · Fix 1: Embrace your attention limitations
AI capability has outpaced human attention span. Splits tasks into an AI-fresh morning slot for complex work and a low-effort PM slot, consolidates every automation's output into one Slack hub, and pushes toward mobile/voice-first tools like Claude's dispatch, Whisperflow, and Hex.
01:56 – 05:37
03 · Fix 2: Quality over quantity
Because AI made producing content free, brand equity — not volume — is the scarce resource. Introduces an 'ask the board' skill cloning 4-5 industry thought leaders, an 'internal focus group' skill for customer-facing work, and a 'clone your manager' skill for feedback before submission. Includes a mid-roll Nexos.ai sponsor segment.
05:37 – 07:58
04 · Fix 3: Stop prompting, start planning and verifying
Contrasts 'sculptors' (hands-on, prompt-by-prompt) with 'gardeners' (plan, execute, verify). Cites Anthropic's internal claim that verification is the single highest-leverage lever on output quality, and gives three ways to build it in: explicit CLAUDE.md verification language, wiring up MCP servers, and expert-review skills for non-technical work.
07:58 – 10:48
05 · Fix 4: Stop treating everything like a nail
Introduces a 5-step AI Enhancement Framework inspired by Elon Musk's productivity algorithm — question every requirement, delete what isn't needed, simplify what remains, augment with AI only once a process is proven manually, then automate — arguing most 'AI problems' should first be questioned or deleted, not automated.
10:48 – 12:08
06 · Fix 5: Bridge abstract to concrete
New AI concepts (skills, loops, MCP) only stick once grounded in a real, personal example. Demonstrates by prompting Claude to scan his own session history for a task that would benefit from a scheduled loop rather than a one-shot skill.
12:08 – 14:05
07 · Fix 6: Ship good, not perfect
AI reliably gets output to about 80% quality but shows diminishing (asymptotic) returns past that point, so the priority is shipping the good 80% fast and reserving the expensive last 20% of effort for what actually needs to be great. Closes noting most shipped projects fail, so speed to ship matters more than polish.
Lines worth screenshotting.
- AI capability has gone nuclear over the last three years while human attention spans have only gotten worse, and that widening gap — not the model — is the real bottleneck.
- Splitting tasks into an AI-fresh morning slot for intellectually complex work and a low-effort PM slot beats treating every hour of the day the same.
- Routing every automation's output back through a single hub like Slack cuts context-switching more than adding another point tool ever will.
- Once production is nearly free, quality becomes the only scarce resource — three months of AI slop can undo years of built-up brand equity.
- An 'ask the board' skill that clones 4-5 industry thought leaders can give high-stakes work simulated feedback before it's ever submitted, not after.
- A 'clone your manager' skill trained on someone's blog posts, Slack messages, and emails can simulate their feedback before you hand off real work to them.
- 'Sculptors' hand-craft output prompt by prompt; 'gardeners' plan, execute, and verify — and it's the shift from sculptor to gardener that actually 10x's output.
- Anthropic has reportedly said verification is the single highest-leverage lever on Claude's internal output quality — above model choice or prompt wording.
- A one-line addition to CLAUDE.md — 'before returning any work, verify that it works and the task is complete' — forces a self-check before every handoff.
- Before reaching for AI on any inefficiency, run a 5-step filter: question the requirement, delete it if possible, simplify what's left, then augment, then automate.
- Automating a process you haven't first run manually with AI as your assistant just locks in a mistake faster instead of removing it.
- AI reliably gets you roughly 80% of the way to a good result almost for free, but pushing from 80% to 100% by re-prompting can produce diminishing — or even negative — returns.
- Only 4 of a well-known indie hacker's 70+ shipped projects ever made real money, a reminder that shipping something good beats perfecting something nobody's asked for yet.
Your habits, not Claude, cap your output.
HABITS OVER TOOLS
The gap between people who 10x their Claude output and people who don't comes down to six checkable habits, not model access or prompt tricks.
02Fix 1: Embrace your attention limitations
- Match task difficulty to your energy: do intellectually demanding work in your freshest hours and save repetitive tasks for when your attention is already spent.
- Route every tool's output through one central hub, like a Slack channel, instead of getting pinged from five different apps — fewer interruptions means more usable attention.
03Fix 2: Quality over quantity
- Once producing content or code is nearly free, the volume you ship stops being the differentiator — the quality bar you hold it to becomes the entire game.
- Get feedback on high-stakes work before you submit it, not after, by having AI simulate reviewers — a board of experts, a focus group, even your actual manager — ahead of time.
04Fix 3: Stop prompting, start planning and verifying
- Treat AI like a gardener, not a sculptor: set the goal and the pass/fail criteria up front, then let execution happen, instead of hand-crafting every response in real time.
- Write an explicit verification instruction into your project's standing instructions file so AI checks its own work before handing it back, instead of assuming the first pass is done.
- Connect AI directly to the real tools and systems you use, not just what you paste into chat, so it can verify against real state instead of guessing.
05Fix 4: Stop treating everything like a nail
- Before automating any inefficiency, first ask whether the step should exist at all — most process bloat survives only because nobody was willing to cut it.
- Only automate a process after you've run it manually with AI's help and confirmed it actually works — automating something unproven just locks in a mistake faster.
06Fix 5: Bridge abstract to concrete
- New AI capabilities stay abstract and unused until you ground them in one real example from your own work — build the first instance yourself instead of just reading about the concept.
07Fix 6: Ship good, not perfect
- AI reliably gets you to roughly 80% quality fast, but pushing further by re-prompting shows diminishing returns and can even make results worse — spend your own effort on that last stretch instead.
- Most shipped projects fail anyway, so the priority is getting a good version in front of reality fast, then improving what actually gets traction, not polishing something unproven.
Terms worth knowing.
- MCP (Model Context Protocol)
- A protocol that lets Claude connect directly to external tools and live data — Slack, project trackers, databases — instead of only working with whatever text you paste into the chat.
- Claude skill
- A saved, reusable instruction set you invoke by name so Claude repeats a specific multi-step task the same way every time, instead of you re-explaining it from scratch each session.
- CLAUDE.md
- A project-level instructions file that Claude Code reads automatically at the start of every session, used to set standing rules like required verification steps.
- Sculptor vs. gardener
- Two ways of working with AI: a sculptor hand-crafts the output prompt by prompt, while a gardener sets the plan and verification criteria up front and lets execution happen on its own.
- Asymptotic improvement
- A pattern where each additional round of AI refinement yields a smaller gain than the last, so chasing the final stretch of quality by re-prompting produces diminishing, or even negative, returns.
Things they pointed at.
01:36toolClaude dispatch
Lines you could clip.
00:00
“There are hundreds of Claude code tutorials out there, but all of them are ignoring the most important factor.”
07:00
“Verification has had the most measurable impact on Claude's output quality internally. It's their highest single quality lever in their entire system.”
07:40
“If you hand someone a hammer, everything starts looking like a nail. If you hand someone Claude, everything starts looking like an AI problem.”
13:45
“Claude is not the bottleneck. It's you.”
Word for word.
Read-along
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
metaphoranalogystory
00:00There are hundreds of Claude code tutorials out there, but all of them are ignoring the most important factor. The reality is if you, the person watching this, doesn't use the tool properly, then nothing else matters. So today, I'm bringing down these six fixes you need to make to 10 x your output.
00:13Each fix comes from problems that I've identified after working with hundreds of business owners and their employees. So fix number one is embrace your attention limitations. In the past three years, the ability for AI tools to create productive output has gone nuclear.
00:25Yet, people's attention span has only gotten worse. So this divergence is the problem. Simon Wilson put it perfectly on Lenny's podcast.
00:31Sort of personal skill that we have to learn, which is finding our new limits. Like, what is what is a responsible way for us to you to to not burn out? So how do you embrace your own limitation and set yourself up for success?
00:42First, you need to understand where AI excels and where you excel. AI is great at fast, continuous execution, pattern matching at scale. Whereas, you're great at judgment, taste, and knowing when something's actually finished.
00:53With this in mind, put your task into high and low effort, where you wanna put the intellectually complex stuff in your freshest hours. Then put the simpler repetitive stuff at the end of the day. My system for this is dead simple.
01:03Everyday I have an AM slot for complex tasks, and PM slot for chill stuff that I can do while watching Netflix. The second is that you wanna consolidate your notifications. Different tools ping you in every direction will quickly draw down your attention.
01:15So I set up my workspace so that Slack is the central hub for my entire business. Every cloud automation and loop that I run reports back through Slack, reducing my context switch. I found that the easiest way to do this is using Slack webhooks and having specific channels for specific automations.
01:30The third is that you wanna have Claude meet you with where you're at. Use Claude's dispatch to access your computer's file system from your phone. There's no need for you to sit at your all day.
01:38You can just do these things remotely. Also, key factor here is use voice first tools like WhisperFlow or Hex so you don't have to type text in. Voice keeps it so that you're not typing all day, which will just burn you out.
01:49So attention reclaim is fix number one, but the next fix is an issue that ninety nine percent of people run into. Fix number two is quality over quantity. Since AI started taking off, producing things has become essentially free.
02:00So just getting things done in a world of abundance is worthless. But what is still valuable? Quality.
02:05Let's think about Nike for a second. They've spent decades building their brand. And every piece of content that they publish either improves the brand or it hurts it.
02:13There's really no neutral. So if they just had three months of AI slop, then the brand would be cooked. And the same can be said for you.
02:18Yes. You can produce millions of things and hope that one sticks, but your personal brand equity will suffer in the process.
02:25And I'm not just talking about content creation. This matters even if you've never created a piece of content in your life. People notice when you send them AI emails.
02:32They notice the AI generated reports that aren't thought through. That's that quantity that you're just producing things and it doesn't provide value. So how can we leverage AI to increase quality instead of focusing on increasing quantity?
02:44We want to . And we do this by building a system that gives you feedback before the finalized version is ever submitted.
02:51This makes it so that you can take that feedback, improve it, and then the final version is that much better. For any high level strategic task, you wanna create a skill called ask the board. Find four or five thought leaders in your vertical with publicly available content.
03:03That's gonna be your board of directors. For example, let's say Alex Ramosy, Mark Cuban, Andrea Carpathi. You would use this prompt to then scrape their public content and create their clones.
03:12Now, if that sounds like a lot to you, you can use my plug in buildpartner.ai and run this, which is already trained on the exact people I mentioned. Now, for anything that's customer facing, you wanna create an internal focus group skill.
03:22Have Claude interview to create a clone of the end user of whatever you're working on. Here's a prompt to help extract this information. And this applies really to anyone.
03:29Right? A person marketing a $10 product on YouTube, to a person presenting a financial report to investors. Trust me, this stuff really makes a difference.
03:37I used something similar at my last startup which raised over $20,000,000. And the third way is for any day to day work task, create a skill called clone your manager. Amol, who runs growth at Anthropic, cloned his manager from her blog posts, her Slack messages, and her emails.
03:50Now he can get feedback from her before actually submitting anything to her. So as AI makes quantity of production go parabolic, quality is at more of a premium, not less. Now before we get to the next fix, which is universally agreed upon, you may find that a lot of what we're covering feels a bit technical, which brings us to today's video sponsor, nexus dot ai.
04:08Nexus dot ai is an AI platform which is a category of tools that I love. The reason being is that it removes all the technical skills that are normally needed to set up an AI agent system, and it can save you hundreds of dollars a month because you don't have to pay for five different AI tools. Now, are three specific features that I love.
04:23The first is that every flagship model is under a single Nexus login. So ChatGPT, Claw, Gemini Grok, and 200 others can all be accessed at once. And this is important because there's really no single best AI model.
04:34Different ones are better at different things, and Nexus will automatically route the specific prompt you're using to the model that's best suited. The second is that it's all combined under one price. Instead of having to go out and pay for each tool separately, it stacks them all together and can save you up to $200 a month.
04:49And if you're watching this, you'll actually get 50% off NexSys, which is pretty dope. The third is their no code AI agent builder. If you can use the Internet, you can use NexSys to build an AI agent.
04:58You just describe what you want and NexSys will build the agent for you. And whether that's for one time jobs like I need to do deep research on this specific topic or repetitive tasks like turning your notes into a weekly report automatically, Nexus will handle this for you. For me, I have a lot of products in my ecosystem for my YouTube, my newsletter, build partners, so it's hard to keep track of.
05:15I can create a weekly report that it analyze my entire marketing funnel, connects to my Slack, and then sends an update message so my whole team can be on the same page. This is a task that I normally would never do just because I don't have time to do it. So to check out Nexus, click the first link in the description where you'll get a discount of 75% off annual plans.
05:31And to be honest, I'm not entirely sure how long this discount will last because I had to really push for it. So go check that out. Fix number three is stop prompting, start planning, and empowering verification.
05:41Generally, I bucket people into two groups, . The sculptor's hands on, crafting the final product step by step. They prompt, they wait for their response, they adjust it, they prompt again, they grind until that final product is ready.
05:53The gardener on the other hand position plants to grow, it waits, then it harvests the fruit at the end. So they create a plan, they establish goals, and they make it clear how AI can verify the output. To build 10 times faster, you need to move from sculptor to a gardener.
06:06I have videos on my channel where I dive deep into this, but the short version to become a gardener is we want to first plan, then have AI execute for us, and then use AI to verify the output. This general framework will allow AI to complete tasks efficiently. So to plan anything, the simplest way to do this is slash plan.
06:22I want to build task. Interview me to identify any gaps in my knowledge. And if you want a more robust skill, once the plan's created, you have AI execute it and then verify.
06:30If you get the plan right, execution is pretty straight forward. The differentiator is verification. Simply put, if you can have AI verify that the final product is correct, it'll know when it's incorrect and it'll keep going until it's correct.
06:40Anthropy actually said this directly. Verification has had the most measurable impact on Claude's output quality internally. It's their highest single quality lever in their entire system.
06:49There are three ways to integrate verification into your work. The first is update your Claude MD with explicit verification language. Just add one sentence.
06:57Before returning any work, verify that it works and the task is complete. If you can't verify it, fix it and rerun. That single line will force Claude to check its own output before handing it back to you.
07:06The second is you need to wire up MCP servers for the external systems you actually work with. So for whatever systems you're using, they likely have an MCP or an API connection that Claude can connect directly to. By establishing this connection, you make it so that Claude can get real world data, not just the data it's seeing on its computer.
07:23If you type slash MCP into Claude code, you'll see what's already connected. Then you could use this prompt to audit what's missing and what connections you can make to help improve your verification. The third for non technical work, you can use some of the skills that we made earlier in this video, the ask the board, the internal focus group, or you can use buildpartner.ai, the slash expert advice, which has experts to get feedback on whatever you're working So let's say you were creating a sales email, you could see what Alex or Mozy would think about it and if it approved or does not approve it.
07:50In 2026, you need to become a gardener, not a sculptor. And the difference is whether the system catches its own mistakes before you have to. Fix number four is that you have to stop treating everything like a nail.
08:00And this is inspired by Elon's five step productivity framework. If you . If you hand someone clawed, everything starts looking like an AI problem.
08:09But the reality is that most things you want to fix with clawed can be solved more effectively with a different lens. Before reaching for AI on any inefficiency run into, run my five step AI enhancement framework. First, you need to question every requirement.
08:23Is this step in the process even necessary? Half of business processes exist because someone was too polite to delete them or you just never told someone it's not needed. Step two is delete the part or process.
08:33If you can kill it, kill it. Elon puts it bluntly. The most common error of a smart engineer is to optimize the thing that should not exist.
08:41If you aren't deleting so many process that you have to add back 10% of them, that means you're not deleting enough. And trust me, this applies to both business owners and employees. I've been on both sides of it.
08:51When I was at JPMorgan, I deleted so much bull just wasn't needed. Step three, simplify or optimize. If something is absolutely needed, now you wanna try and simplify the process.
09:01Remove steps, reduce friction, combine tasks. Step four is skill driven AI augmentation. Tackle a task with AI as your assistant.
09:08And if the process repeats, create a clawed skill based on what you just did and then reuse that every time you run this process. Then each time you use a skill, work on enhancing it so that every iteration it gets better. Step five is skill driven AI automation.
09:21In step four, you create a skill that you know works because you actively used it. Only after you've done that is it time to actually automate something. If you're automating something that you haven't already systematized manually, then you're just wasting your time.
09:32Personally, I don't trust myself to run this check-in my head. So I actually have an automation verification skill. If I'm debating building out a robust automation, this skill has to sign off on this decision based on everything it knows.
09:43Here's a prompt that you can use to build out a skill that you can just use as a sanity check whenever you're thinking about building out a crazy automation. If you just step right to four and five, you're gonna be stuck working on things that you probably should have deleted or just replaced entirely. We've created a framework so that we can be a gardener, not a sculptor, and we understand not to use AI for everything.
10:01But once it's actually time to use AI, one problem people run into is that they feel overwhelmed with all the new AI advancements. And before we get to what fixes this, which is something no other creator will talk about, if this is your first video of mine, welcome to the channel.
10:14If it's your second or more, here's our anti slap agreement. The visuals, the testing, all of the things that are going on on screen, this is built entirely for humans, not for AI scrapers. So, I ask as part of this agreement is that you subscribe to this channel so that it can reach more people.
10:28Also, every video I give away a Claude Max subscription and this week's winner is Maygrab nine nine nine. They're building a script to automate an old game. Honestly, hopefully, that's RuneScape.
10:37Shout out my old character, Devils Are Back. And to enter the next giveaway, comment below with what you're building or a recent feature you built. And every new video you comment on will be an additional entry to this giveaway.
10:47So let's go to fix number five, which is about bridging the abstract to concrete. Every new AI feature is new to everyone. So no matter what, it's going to start off feeling very abstract.
10:57But each new feature or tool can be bridged to a concrete example for whatever you're working on. So if you wanna learn about Claude skills, build a skill you can use. If you wanna learn about Claude loops, build a loop you can use.
11:08The faster you go from abstract to concrete, the faster you'll build. And so how do do this in practice? Well, first, you wanna do proof based learning.
11:15Seeing results yourself is believing. So concepts only stick when you've actually built something with them. So you need a way to ground it to your work immediately for new concepts to stick.
11:25For example, when I wanted to learn about loops, I used this prompt. Look at my past sessions history and find tasks I've done multiple times where I'd benefit from a loop. Tell me how I could use this and why it's different than just calling skills.
11:36So when I ran this on the project I was working on, you can see the response on screen. And at the bottom of it, it says, so the loop does not replace a skill. It removes you as the trigger.
11:44Your three funnel digestion sessions across eight days are exactly the symptom, a recurring obligation you carry in your head. The skill answers, what work happens? The loop slash schedule answers, when and who remembers?
11:55This positions this new concept into the context of my project. And as a result, I'm able to understand how it applies to what I'm working on in minutes, not hours. The faster that you can bridge the abstract to the concrete, the faster you'll be able to build.
12:08Fix number six, ship good, not perfect. One of my favorite quotes is from a French philosopher. Perfect is the enemy of good.
12:15The truth is you can always make something better, but for most things, good is good enough. And any time you spent making it perfect is wasted. And I know what you're thinking.
12:23Doesn't this contradict what I said earlier about quality over quantity? The answer is no for two reasons. The first is that the best builders know what needs to be good versus perfect.
12:32And they choose to build the minimum viable standard, which saves them time and money. The second, when using AI, there's a concept of asymptotic improvements. What this means is that AI is getting really good at getting you 80% of the way there.
12:45But no matter how many times you prompt it, it won't get you to that final 20%. So if you try and go from the 80%, the good, to the great, the a 100%, you may never actually get there by prompting AI. And there's a chance that you might actually see slight regression trying to make it perfect.
12:59So I'm not saying deliver AI slop. Good is not slop. What I am saying is follow the eighty twenty rule.
13:0480% of your task should take 20% of the time. Lean on AI to get most of the way to that asymptote. 20% of your task should take the 80% of the time.
13:12That's where you wanna focus your energy to bring good to great. And I can't stress this enough for people watching who run their own business or wanna run their own business. Peter Levels, a famous indie hacker who launched his products, said that only four out of 70 plus projects that he's launched ever made money and grew.
13:27So about 95% of everything that he's done has failed. And this means in some cases, it's important to build things that are good and worry about making them perfect later.
13:37The reality is with all of this is that Claude is not the bottleneck. It's you. But if you apply these six fixes, you'll start building faster and more efficiently.
13:45Because reality is no matter what improvements come from AI, these bottlenecks will hold you back until you fix them. Now, if you like this video, you'll love this video where I walk through exactly what you can paste into Claude to start building 10 times faster. The fixes I cover here paired with the tactical advice on that video puts you in the top 1% of all AI builders.
14:03I'll see you over there. Peace.
The Hook
The bait, then the rug-pull.
The title's accusation is the whole pitch: after watching hundreds of Claude tutorials fail to move the needle, this creator argues the tool was never the constraint — attention habits, quality standards, and premature automation are. What follows are six specific, checkable fixes, not more prompting tips.
Named ideas worth stealing.
09:03list
5-Step AI Enhancement Framework
- Question every requirement
- Delete the part or process
- Simplify or optimize
- Skill-driven AI augmentation
- Skill-driven AI automation
A filter to run before reaching for AI on any inefficiency — most 'AI problems' should be questioned or deleted before they're ever automated.
Steal forany internal process audit before building an automation
03:10concept
Ask the Board (skill)
A Claude skill that clones 4-5 public thought leaders in your vertical so high-stakes strategic work gets simulated feedback before it's finalized.
Steal forvetting big decisions or content before shipping
05:41model
Sculptor vs. Gardener
A working-style framework: sculptors hand-craft output prompt by prompt; gardeners plan, execute, and verify. The shift from sculptor to gardener is what actually 10x's output.
Steal fordiagnosing why your AI workflow feels slow despite constant AI use
How they asked for the click.
VERBAL ASK
13:59next-video
“if you like this video, you'll love this video where I walk through exactly what you can paste into Claude to start building 10 times faster”
Soft next-video CTA at the very end paired with an on-screen subscribe card — no hard sales pitch here since the paid offers were already covered in the mid-roll sponsor read.
MENTIONED ON CAMERA
FROM THE DESCRIPTION
PRIMARY CTAWhere the creator wants you to go next.
OTHER LINKSAlso linked in the description.
- Get in the top 1% of AI builders ↗
- Claude Code loops to build 10x faster ↗
- How Anthropic engineers use Claude Code ↗
- Free 5-day AI playbook (what I used to build a $25M+ startup) ↗
- Use BuildPartner to build 10x faster with Claude Code (try free) ↗
- Want to build a SaaS product without hiring a CTO? ↗
- Whisperflow (voice dictation) ↗
- Hex (voice dictation) ↗
- Instagram ↗
- Youtube ↗
Visual structure at a glance.
