The real skill isn’t taste anymore

You collect references. Dribbble shots, Awwwards sites, that one landing page everyone shares. You feed them to the model with detailed instructions. The output is close but off. Wrong spacing. Clunky animations. Not quite the vibe.

You think you need better prompts.

You don’t. You need different models.

I spent weeks trying to replicate Phantom.com’s interface. Gorgeous bento cards, smooth interactions, the kind of design that makes you want to screenshot and study. I fed every detail to Claude. Refined prompts. Adjusted parameters. Fought the model to execute my exact vision.

Then Gemini 3.0 launched. I gave it a loose brief ”build a landing page, make it clean” and it shipped something usable in three hours. Not a pixel-perfect clone. A working interface people actually praised.

The kicker? I was solving the wrong problem. The risk wasn’t shipping something imperfect. The cost was the month I spent forcing one model to do what another model handles in an afternoon.

Let me be precise about the cost.

I started this project in spring. It’s now November. I wanted to ship in a month. Instead I burned eight weeks across multiple attempts. Quit twice. Came back. Quit again.

The bento cards kept breaking. The animations looked janky. The layout consistency fell apart. Next would work on V3 tailwind, break on V4. Color rules I set would get ignored. Integration with the old Angular and Node.js Express codebase kept failing. Even auth tests broke.

I tried elaborate prompts. Ones that worked perfectly for Gemini. Fed them to Claude. Claude ignored them. Turned out I’d written “follow the Prometheus protocol” thinking it would enforce structure. Claude’s internal instructions rejected it.

The worst part? Every failure felt like my fault. The prompt wasn’t detailed enough. I wasn’t describing the shadows correctly. I needed better reference images. So I’d spend another day refining the instructions, adding more specificity, trying different approaches.

I even tried copying prompts that worked for other models. Gemini would ship a clean layout from a loose instruction. I’d take that same prompt to Claude. Nothing. Claude would interpret it differently, prioritize different elements, ignore half my specifications. I kept thinking: if I just find the right words, the right structure, the right protocol, it’ll work.

It never did.

Then everything changed in one week. Not because Gemini 3.0 fixed everything. Because Gemini 3.0, Codex, and Claude’s new frontend skills all dropped at once. The combination unlocked what no single model could deliver.

The paradigm broke

You’re not working with a tool anymore. You’re working with a roster.

Gemini 3.0 cranks out frontend layouts but handles state management differently than Claude. Claude 4.5 with frontend context ships cleaner component structure than Claude 4.5 without it. Cursor nails certain interactions that Gemini can’t touch. Each tool has a natural range.

The old game: Pick your aesthetic. Force every model to replicate it. Measure success by fidelity to the reference.

The new game: Understand what each model does without friction. Route work accordingly. Measure success by speed to working prototype.

This isn’t about lowering standards. It’s about moving faster by swimming downstream instead of fighting the current.

The taxonomy

Every model has two zones:

Native territory: Tasks it ships fast and clean on the first try. Minimal prompt refinement. Output is 80–90% done immediately.

Forced territory: Tasks where you fight for incremental improvements. Lots of prompt iteration. Output never quite lands.

Your job: Map each model’s native territory through experimentation, then route ruthlessly.

When Gemini ships a layout in one shot that would take Claude six rounds, use Gemini. When Claude structures logic that Gemini fumbles, use Claude. When Cursor nails an interaction pattern the others miss, use Cursor.

Stop trying to make every model do everything. You’re burning time in forced territory.

The hidden truth

Three months from now, a new model drops that handles the thing you’re struggling with today in two clicks. The capabilities shift every quarter.

The skill that compounds isn’t taste. It’s not prompt engineering. It’s not even knowing the current capabilities.

The skill is rapid model experimentation. Testing what works. Noting where each model ships clean. Cutting losses when you’re in forced territory. Adapting as the landscape shifts.

The designers who win aren’t the ones with the best aesthetic vision. They’re the ones who route work fastest to the model that ships it clean, then move to the next task while everyone else is still refining prompts.

That’s the first unlock. Here’s the second.

Subscribe now

Run them in parallel

You think routing tasks sequentially is the win. It’s not. The real velocity comes from running multiple models simultaneously, each in their native territory, complementing each other’s gaps.

My current setup:

Two Codex agents building backend architecture and setting up pipelines. Two Claude agents (one with frontend skill, one without) handling different parts of the stack. One Gemini polishing UI where Claude’s output needs refinement.

All running at once. In Warp. Three tabs. Color-coded so I know which model is handling what.

Here’s the actual workflow that shipped in one week what took eight weeks to fail:

I open all five agents at once. Claude with frontend skill starts documenting all user scenarios and building Storybook screens—no backend, just mockups and contracts. While that runs, Codex starts integrating with the old Angular and Node.js codebase, writing the docs on how to interface with legacy API endpoints.

Simultaneously, the other Claude agent starts covering edge cases I missed in the product use case documentation. All three running. When Storybook finishes, I know the component contracts. I feed those to Codex. It starts implementing the backend API to match.

ESLint errors pop up. Claude ignores them. Codex doesn’t. It sets up Guards, Lint rules, color detection, the full QA pipeline. Keeps Claude honest. When Codex moves slow on quick fixes, Claude takes over. When Claude ships janky animations, Gemini polishes.

Five windows. Five specialists. Each doing what it does cleanly. No fighting. No forcing.

I hit rate limits on all five agents in five hours. Wait for refresh. Come back. Hit them again. Work that used to take a month now takes a day.

Not because I got better at prompting. Because I stopped trying to make one model do everything and started orchestrating five specialists doing what they do cleanly.

Here’s what hitting rate limits actually means in practice:

By 10 AM, Claude with frontend skill has shipped three Storybook scenarios. Gemini has polished two UI flows. Codex has set up the integration layer with the old codebase and written the Guards. The other Claude agent has documented edge cases and fixed three bugs that would’ve shipped to production.

By lunch, all five hit rate limits. I’ve shipped more than I used to ship in a week. I wait for the refresh. Come back at 2 PM. Route the next set of tasks. Hit limits again by 4 PM. The velocity isn’t incremental. It’s exponential.

The old approach: spend Monday perfecting one Claude prompt. Tuesday debugging why it broke. Wednesday trying a different angle. Thursday still fighting. Friday shipping something half-done.

The new approach: Monday morning, all five agents ship their pieces. Monday afternoon, second round after rate limits refresh. Tuesday, you’re integrating and testing. Wednesday, you’re shipping.

The real edge

Prompting still matters. Knowing each model’s capabilities matters. But the compound skill is this:

Understanding how to adapt tasks to each model’s constraints, then running them in parallel so they fill each other’s gaps.

The prompt you write for Claude is different from the one you write for Gemini. The tasks Codex handles differ from what Claude ships. The way you structure work for parallel execution differs from sequential routing.

You’re not a prompt engineer anymore. You’re a conductor. Five instruments. Each plays their part. Together they ship what one model fighting itself could never produce.

Open five interfaces. Route your stuck tasks to native territories. Let them run simultaneously. Color-code the tabs. Watch them complement each other.

Hit your rate limits by lunch.

You’ve been living in rehearsal mode. Maybe for years. You’re building the perfect plan, the 10-step strategy, the contingency for the contingency. The spreadsheet comparing 47 cities. The probability distribution for whether this relationship will work. You think you’re being smart, strategic, rational. But here’s the truth: the show already started. The curtain is up. You’re already on stage. And while you’re backstage perfecting your lines, people with half your intelligence are out there performing. They’re making irreversible moves. Marrying the “wrong” person who becomes right. Moving to the “wrong” city that transforms them. Starting the “wrong” business that sets them free. And you? You’re watching from the wings with your perfect script that never gets performed.

I know this because I was you. I spent two years analyzing cities (and more years for more serious things). I had a Notion database with weighted scoring systems: cost of living, quality of healthcare, walkability index. I was going to find the objectively perfect place to live. Then I randomly went to Bangkok for two weeks. No plan, no analysis, just curiosity. It became my favorite city on earth. Better than Barcelona, better than every European city I’d “scientifically” evaluated. Not because Bangkok scored higher on my rubric, but because I stopped judging and started living. I walked through what I thought was a “test run” a two-way door I could easily exit. It became a one-way door. It changed me forever.

And here’s what I realized when I looked back: I don’t regret a single irreversible decision I actually made. Not one. You know what I regret? The years I spent preparing for the “perfect moment” that never came. The relationships I didn’t pursue because I was calculating divorce probability. The cities I didn’t move to because they didn’t score 100% on my matrix. The businesses I didn’t start because I was “still researching.” Every day I spent optimizing was a day that died forever. That’s the real irreversibility I couldn’t see.

Your brain is running a simulation that will never end

“You could leave life right now. Let that determine what you do and say and think.” - Marcus Aurelius, Meditations 2.11

Let me guess your process. You treat life like a software release. You think every major decision can be “rolled back” if it fails, so you spend months trying to code the perfect algorithm for your life. You calculate probability distributions for marriage success. You build comparison matrices for cities with 30+ variables. You analyze market conditions for business ideas until the market has already moved on. You think this makes you smart. But here’s the bug in your operating system: you think the risk is making the wrong irreversible choice. The real risk is the irreversible passage of time while you’re deciding.

I see this constantly. Someone spends six months “researching” where to live. They build a 47-tab spreadsheet, join social groups, and watch YouTube videos. Six months later, they’re still in the same apartment. Meanwhile, their less-analytical friend moved to Bali on a whim, and now their life looks like they discovered the meaning of existence itself. What’s the difference? One person thought they were avoiding risk by gathering more data. The other person understood that the decisions that transform your life never feel like transformations when you make them. They feel like small experiments, reversible tests, two-week trips. But you can’t run the experiment if you’re still reading the manual.

Here’s what actually happens with “irreversible” decisions: you don’t get to know if a door is one-way until you walk through it. That relationship you’re afraid to commit to might be the one that teaches you how to love, even if it ends. That city you’re afraid to move to might reveal parts of yourself you didn’t know existed. That business you’re afraid to start might fail, but the person you become in the process might be exactly who you needed to be. The transformation isn’t the outcome. The transformation is you, becoming someone who can make irreversible choices.

I spent about five years trying to make it as an indie hacker. From 2019 to 2025, with breaks and pauses. Building a restaurant SaaS that caused me more stress than revenue. Watching my MRR hit $3,000 while I spent $5,000 a month keeping the machine running. I was afraid of “wasting time” on the wrong path. But you know what I learned? The only time I actually wasted was the time I spent being afraid. When I finally quit, I wasn’t mourning a failed business. I was mourning the fact that I’d spent years in a casino, believing the algorithm that showed me only the lottery winners. But even that “failure” wasn’t a waste. It taught me to distinguish between two types of decisions. And once I understood this, everything changed.

Subscribe now

How to stop running simulations and start building your life

Every decision in your life falls into one of two categories: two-way doors and one-way doors. Two-way doors are decisions you can reverse with minimal cost. One-way doors are decisions that fundamentally change who you are. Most people treat all decisions like they’re one-way doors. That’s why they’re paralyzed.

Two-way doors are everywhere. A two-week trip, a coffee meeting with a potential cofounder, a side project, a first date, testing a new framework, posting a controversial tweet. These are experiments, not commitments. But your brain treats them like marriage vows. You spend three weeks debating whether to message that potential cofounder on Twitter. It’s a two-way door. Worst case: they don’t respond and you lost five minutes. Best case: you find your business partner. The rule is simple: if you can reverse it in less than a week with minimal cost, decide in 48 hours and execute. Think of two-way doors like A/B tests in product development - you don’t spend six months debating which button color to use, you test both and let the data decide. Your life works the same way.

That trip you’re “considering” for six months? Book it this week. It’s two weeks of your life. If you hate it, you leave. If you love it, you just discovered something about yourself you couldn’t have known from research. When you start treating reversible decisions as experiments instead of commitments, you 10x your learning speed. You get real data instead of hypothetical projections. You become the person who moves fast, not the person who thinks fast and moves never.

Now let’s talk about real one-way doors. These are rare, way rarer than your anxiety tells you. Real one-way doors fundamentally change your identity: marriage, children, a decade-long commitment to build a specific company, moving to another country for citizenship. These decisions create a new version of you that can’t be undone. Here’s the distinction two-way doors are like rearranging Lego blocks that you can take apart and rebuild. One-way doors are like baking a cake - you can’t un-bake it.

And here’s where most people get it wrong. They think the risk of a one-way door is “what if this relationship fails?” The real question is: “Am I willing to become the person who loved deeply, even if it ends?” That’s the irreversible part - not the outcome, but who you become. When I started my restaurant SaaS, I thought I was making a reversible bet. “I’ll try this for a year, and if it doesn’t work, I’ll get a job.” It became a one-way door, not because I couldn’t quit (I eventually did), but because building that business changed me. It taught me how to sell, how to handle pressure, how to keep a system running when real businesses depended on my code. I can’t un-learn those things. I can’t go back to the person I was before. And you know what? I don’t regret it. Even though it “failed” by Silicon Valley standards, I won, because I became someone different. That’s what one-way doors do - they don’t determine your outcomes, they determine who you become.

Here’s the paradox that will change your life: everything worth having requires you to close doors behind you. Deep love, mastery of a craft, a business that changes lives, children who carry your legacy - all of these require irreversible commitment. You can’t become world-class at anything while keeping all your options open. You can’t build a meaningful relationship while calculating your exit strategy. You can’t create something that matters while treating it like a “side project you might quit.” Sovereignty isn’t about keeping options open, it’s about choosing one path and going all-in. Think of it like this: a river that splits into a thousand streams has no power, but a river that commits to one channel carves canyons. Your life is the same.

When you’re 45, you won’t regret the relationship that didn’t work out. You’ll regret the years you spent afraid to commit to anyone. You won’t regret the business that failed. You’ll regret the ideas you never launched because you were “still researching.” I look back at my five years of indie hacking now, and I don’t wish I’d never started. I wish I’d started sooner. Because the person I am now, the person writing this to you, only exists because I walked through that one-way door.

Here’s the tool that will save you years of wasted time. Ask yourself: “Am I preparing for the show, or am I using preparation as an excuse to avoid the show?” If you’ve been “preparing” for more than three months, you’re avoiding. Professional actors rehearse for weeks, not years. At some point, rehearsal becomes procrastination disguised as professionalism. You’ve been “learning to code” for 18 months, but haven’t shipped a single product? That’s not preparation, that’s rehearsal. You’ve been “working on yourself” for two years, but won’t let anyone close? That’s not healing, that’s hiding. You’ve been “researching business ideas” for a year but haven’t made a single sale? That’s not strategy, that’s fear. The show is already happening. The curtain is up. You’re the only one who doesn’t realize you’re already on stage.

So here’s your assignment. Pick one one-way door you’ve been standing in front of for months. Walk through it this week. Not when you’re ready, not when you have the perfect plan. Now. Because the only way to know if a door leads to your best life is to walk through it. What’s your Bangkok? What’s the thing you’ve been over-analyzing that you need to just try? Book the ticket. Send the message. Start the company. Commit to the person. Do it before your brain builds another 10-step contingency plan.

Because here’s what I know for certain: you don’t regret the things you did that didn’t work out. You regret the things you never tried because you were afraid they might not work out. The irreversible decisions you’re avoiding are the ones that will define your life. The only question is: will you make them while you still have time, or will you keep rehearsing until the theater closes?

“Life should not be a journey to the grave with the intention of arriving safely in a pretty and well preserved body, but rather to skid in broadside in a cloud of smoke, thoroughly used up, totally worn out, and loudly proclaiming ‘Wow! What a Ride!’”

Hunter S. Thompson, The proud highway: saga of a desperate southern gentleman.

Imagine your Twitter feed only showed lottery winners.

Every day, you see people posting screenshots of their jackpot. “I’m profitable!” “Just quit my job!” “Hit $10k MRR!”

Within weeks, you’d start to think winning is normal. You’d start to believe you’re just one ticket away.

This was my reality for two years.

It started with a spark. Three months before I was laid off, I was already building a complex B2B SaaS for restaurant chains. I couldn’t stop myself. I coded at night, after my day job. It was my secret project, my escape plan.

Then the layoff call came. And standing at that crossroads, with a head full of success stories from Y Combinator and YouTube, I made the call. I wasn’t going back to a job. I was going all-in.

About a month later, I got my first taste. A payment for a hundred bucks or so. It was the first money I’d ever earned from code I’d written myself. That small win felt like a jackpot. It was the algorithm whispering in my ear: «See? It’s working. You just need to learn how to play better.»

So I played harder.

I joined the community of full-time lottery players. Every small win was amplified. “You’re on the right path, bro! Keep going!”

What they didn’t see was the reality behind the curtain. This wasn’t a simple app. It was a mission-critical system for restaurant chains. If my code failed, real businesses lost thousands of dollars in real orders, right now. The pressure was crushing.

My life became a frantic cycle: sell a feature to a client, then lock myself in a room and code frantically to build what I just promised. Each new sale wasn’t a win; it was just another layer on a teetering tower of obligations.

I pushed the MRR to $3,000. On Twitter, that number made me a winner. In reality, I was spending $5,000 a month to keep the machine running. I was in a cult, and the price of membership was my health, my sanity, and a growing mountain of debt.

The years went by. I still saw the daily stream of winners on my feed. But I was still losing. And I started wondering.

Why am I not winning? Is there something wrong with me? Am I stupid?

There was nothing wrong with me. I just made the mistake of believing the algorithm. I woke up to the fact that “indie hacking” isn’t a career path. It’s a casino disguised as a movement.

And in that moment, I felt liberated.

What if the goal isn’t to become the next levels.io? What if the real prize isn’t the MRR, but the skills you build along the way?

What if you, a developer, build a small project not to get rich, but to become a killer salesperson? What if you use it as a testing ground to land a Product Manager role? The project’s “failure” to hit $10k MRR would still be a massive personal success.

This is the game I’m playing now. This is Prometheus Protocols.

This is not another newsletter selling lottery tickets. This is my public log of building a new system. A system where the goal isn’t the jackpot, but building antifragile skills and small, resilient assets.

We will not go all-in. We will make small, smart bets. We will use leverage, like AI, to build in 4 hours what used to take 40. We will design projects that make us win, even if they never make a dollar.

If you’re tired of playing a rigged game, then welcome. You’re not a loser who gave up. You’re one of the few who woke up.

Let’s build our own game.

Subscribe now