The Orchestrator's High

About half a year ago, AI took a real jump in usefulness for deep knowledge work. Claude Code had been around for a while, but it was around then that people inside the bubble started realising it was good for much more than writing code — research, planning, decision support, knowledge work of every kind. I got in, started learning, and within a few weeks I’d figured out how to get it to actually carry context from one session to the next. Self-learning systems, context engineering — the kind of thing that turns a stateless assistant into something that remembers what it learned yesterday.

The first weekend I really pushed the new setup, I was logged into Claude Code with two accounts at the same time. Private projects in the browser, work projects in the desktop app, both accounts grinding against their session limits, my OpenClaw agent humming away on a third window. Five or six sessions in flight, another fifteen queued up for follow-up, spread across four virtual desktops on a wide screen so I could flip between them with the keyboard. I’d missed dinner. I hadn’t been outside since lunch. It was past midnight and my brain was loud.

Every day a new wave was coming in. A new model release, a new agent harness, new MCPs, ten new “best practices” people were posting about, twenty new use cases I hadn’t tried. I was getting hooked, and I knew I was getting hooked, and I was getting hooked anyway.

This guide is about what happens next. About the shift from using AI to running a small team of yourself. The superpower side is real — I’ll get to it. So is the cost. And so is the bubble of other people sprinting alongside you, making sure you don’t slow down.

What “orchestrating” actually looks like

The mental shift is the part most guides skip. With chatbot-style AI you ask a question and read an answer. With agentic AI you launch a session, the agent works autonomously for ten to fifteen minutes, and then you read the result and decide what’s next.

Ten to fifteen minutes is the magic number. Long enough that you can’t just sit and watch — you’d be wasting the whole point. Short enough that you can plausibly fit two or three rounds of feedback to other sessions into the same wait. So you start running things in parallel. You launch session B while session A is working. You give session C its next instruction while you’re reviewing session A’s result. You’re not coding anymore. You’re conducting.

My setup is unspectacular. Four virtual desktops on a wide monitor, one window left and one right per desktop, so I can flip between eight things by keyboard. A Stream Deck on the desk — twenty-four programmable buttons — is mostly mapped to switching desktops and pulling specific apps to the foreground, plus a push-to-talk button I use to dictate instead of typing when my hands or my patience have run out. Five or six sessions running at any given peak, maybe fifteen more queued waiting for the next nudge. Rookie numbers, frankly — Steve Yegge has been writing about running thirty in parallel through a custom orchestrator he calls Gas Town, and a Cloudflare engineer rebuilt 94% of Next.js’s public API in about a week by running 800-plus sessions over a long weekend. People are running far more extreme versions of this than I am.

But the structure is the same at every scale: you’ve stopped being the person doing the work. You’ve become the person managing several copies of someone else doing the work. The bottleneck moves from your hands to your attention.

What this actually unlocks

The case for celebrating it is genuine, and I don’t want to wave it away.

A few weeks ago I redesigned the user onboarding flow for our mobile app at Carewell. Not a tweak — a re-think. What the new user sees, what we ask them, what we don’t ask them, how we sequence the trust we need to build with someone before they hand over information that matters.

Old timeline: weeks. Schedule a workshop with the product team. Brief a designer. Wait for a draft. Talk to engineering about feasibility. Get compliance to weigh in. Wait. Wait. Every round of feedback gated by other humans being free at the same time as me.

New timeline: a weekend. Roughly ten interview rounds with the AI playing the role of different expert advisors, where I made something like thirty product decisions out loud and had each one stress-tested before I committed to it. By Sunday night I had a working high-fidelity prototype — not clickable mockups, real frontend code with realistic test data, runnable on a phone, walking through all the actual paths a new user could take.

The part that sped up most wasn’t the building. It was the decision-making. When I work with human experts I’m typically waiting two days between question and answer, only during their office hours, and I have to bring each of them up to speed first. With AI playing the same role, the feedback cycle is two minutes, it’s three in the morning if I want, and it has the context already.

And it isn’t one advisor on call — it’s all of them. In a single session I can have a senior UX designer reviewing a flow, a behavioural economist pointing out which cognitive bias is going to bite us, a first-principles thinker asking why we’re solving this problem at all, and an engineering lead telling me which version is realistic to ship by when. Then the same system turns into a developer who actually builds what the conversation has just decided. Immediate advice and feedback on every topic where I lack expertise, and a builder standing by to implement whatever the room lands on.

Multiply that by every decision a product or a strategy needs and you start to see what the noise online is about. It’s not that AI writes better code than a senior engineer. It’s that an experienced generalist with the right system around them can compress a cross-functional team’s whole feedback loop into a single afternoon. That’s the part that’s genuinely different.

What it costs you

The other side is just as real.

The first thing I noticed was exhaustion. Not foggy or distracted — properly tired. After a few hours of context-switching every couple of minutes, the part of my brain that does the hard work just clocked out. Sitting with a question, holding three constraints in my head, working through a non-obvious chain of reasoning — none of it would happen. I’d end up running easier tasks for an hour to let my head recover before it would handle anything heavy again.

There’s a subtler version of the same problem that snuck up on me later. I’ll catch myself thinking I could do this better with AI in moments where the right move is to just sit and think for ten minutes. The instinct to reach for the tool has overgrown the muscle to use my own brain. That muscle, like any muscle, weakens when you stop using it — and once you’ve felt that, you start guarding the time when you’re supposed to be the one doing the work.

Gloria Mark, the UC Irvine researcher who’s spent two decades measuring attention, has found that it takes about 23 minutes to fully recover from an interruption. Average sustained focus on a single screen has gone from 2.5 minutes in 2004 to 47 seconds in her latest data. The orchestrator workflow is interruption every ten minutes by design. It isn’t that you might lose focus. The setup makes deep focus mechanically impossible.

The second thing was the racing brain at night. I’d close the laptop at midnight and lie down and immediately my head would start the next session. What if I tried this. What if that other thing actually worked. I should have launched one more before bed. Quentin Rousseau, the CTO at Rootly, eventually got a doctor to prescribe him orexin-receptor blockers because he couldn’t sleep — months of agent loops had left him, in his words, “stuck in agentic dopamine loops” he couldn’t switch off. I’m nowhere near that. But the mechanism he describes is the one I felt.

The third thing was just the absence of the rest of life. Meals delayed. Walks skipped. Bathroom breaks postponed an hour because three sessions were about to come back. A weekend where I worked from waking until midnight every day and barely registered that the weather was good.

The work was real. The output was real. But by the end of those stretches I was not a person I’d want to be in a room with.

The bubble that won’t let you stop

The thing that keeps you in the loop isn’t the work itself. It’s the bubble around the work.

I follow other builders, makers, founders. I have an entrepreneurial mind, and I look at what’s happening right now and I see it clearly: the window of what a single competent person can build has widened by an order of magnitude in a year. Small agile companies that understand AI can match much bigger, much better-funded ones that haven’t figured out what to do with it yet. People are launching businesses solo, in a fraction of the time it used to take, with credible revenue appearing faster than anyone thought possible.

Entrepreneurship is arbitrage. Right now there’s a generational arbitrage open, and most of the world is asleep on it. That’s not hype. I genuinely believe it. The opportunity is real.

And that belief is the engine that makes the laptop hard to close. Every hour you’re not pushing is an hour someone else is. The dopamine of finished sessions plus the fear of falling behind is the exact combination that produces the all-nighter.

I’m not the only one feeling it. Andrej Karpathy admitted on a podcast last month that he’s “in a state of psychosis trying to figure out what’s possible… I need to be at the forefront, or I feel extremely nervous.” Garry Tan, the CEO of Y Combinator, said at SXSW that he sleeps four hours a night and has “cyber psychosis, but I think a third of the CEOs I know have it too.” Peter Steinberger built a viral product in ten days, said it almost broke his sleep, called himself a “Claudoholic” and texted other founders at four in the morning about a club of people walking around with black eyes.

None of these are people on the edges. These are people who have already won, and they cannot stop.

The slot machine inside your head

I noticed the pattern in myself before I had a name for it. Every finished session produced a small kick of excitement — sometimes the result was great, sometimes it was a mess that needed three more rounds to clean up, and either way I wanted to launch the next one immediately. Reading other people’s accounts, the same thing kept coming up: a jittery just one more prompt feeling, regardless of whether the prompt was paying off.

Then I ran into Steve Yegge’s Brute Squad essay, and it had the label: variable-ratio reinforcement. Every time the agent succeeds, you get a dopamine hit. Every time it fails spectacularly, you get adrenaline. Both are reinforcing. It’s the same mechanism that makes slot machines the most addictive form of gambling — and Anthropic engineers reportedly told power users early on to “treat it like a slot machine.”

That isn’t a metaphor. The reward system in your brain is responding to exactly the same pattern: unpredictable results, mostly positive, occasionally astonishing, with the next attempt one button press away. Tao Bojlén described his Claude sessions producing “this jittery craving for more” the moment one finished — and compared it directly to TikTok scrolling. Armin Ronacher, watching the same scene from the outside, wrote:

“When I watch someone at 3am, running their tenth parallel agent session, telling me they’ve never been more productive — in that moment I don’t see productivity. I see someone who might need to step away from the machine for a bit.”

And here’s the part I think about most. The METR study from mid-2025 had experienced developers do real-world tasks both with and without AI tools. The developers using AI took 19% longer on average. They also believed they were 20% faster. Variable-ratio reinforcement doesn’t just keep you pulling the lever. It distorts your perception of whether the lever is actually paying out.

I don’t think this means the work isn’t real. Mine is, the Cloudflare rebuild is, plenty of people are shipping things that would have been impossible a year ago. But it does mean you can’t trust the in-the-moment feeling that you’re being maximally productive. That feeling is exactly what the reinforcement loop is designed to produce, whether or not it happens to be true today.

What I’ve actually started doing

I’d love to tell you I have this figured out. I don’t. The feeling that I have to move faster, learn more, achieve more — I expect that to linger for a long time. The arbitrage really is generational, and pretending it isn’t just to feel calm would be its own kind of dishonesty.

What I have, instead, are the same anchors I learned during my first startup, applied to a new shape of the same problem.

Real time with the people who matter to me. Not interrupted, not half-attended-to while a session is running in the next room. A meal with my wife where the laptop is in another room and the phone is face down. A call with a friend that takes as long as it takes. The work cannot be the only thing.

Outside, often enough to count. A walk between sessions, not after the day is over. Sunlight on a weekday afternoon. A weekend with no agenda. The body doesn’t run on dopamine alone, and the brain making the next round of decisions is the same one that needs movement and light.

Hard physical exercise. The cleanest available reset. Twenty minutes of something that makes you breathe hard does more for the racing-brain problem than an hour of trying to wind down. I treat workouts like meetings now — scheduled, attended, not optional.

Plan the session before you start. Walking up to the screen with no plan and just “seeing what I can ship today” is the most efficient way to lose four hours and end up tired. I now write down — even one sentence — what the session is for, before I launch anything. It sounds trivial. It changes the day.

Work with my rhythm, not against it. I’m a night owl. After putting my daughter to bed, I have a stretch of quiet hours that are genuinely productive — those aren’t the ones I’m trying to cut. What I’ve changed is the first half of the day. Mornings now are usually no-AI: own reading, own writing, own thinking, and a written list of what the rest of the day is for. By the time I open the laptop in the evening, I already know what I want done, and the orchestrator hours feel different — directed, not desperate. The rule isn’t “stop earlier.” It’s “decide first, launch second.”

None of this is dramatic. It’s the boring stuff anyone who’s been around a creative or entrepreneurial life knows. The point is just that the boring stuff still applies, and the new tools don’t somehow exempt you from the equation that broke people in every previous bubble.

If you’re about to step into this

A few honest things if you’re picking up Claude Code or a similar agent for the first time and you can already feel the gravitational pull.

The early phase is the most dangerous one. Not because the work is bad — the work is great. Because every new release, every new MCP, every “look what I built in a weekend” post is going to land on a brain that’s already getting hits from the loop. Pace yourself early. Take days off in the first few weeks specifically. You don’t need to be at the frontier on day three.

Trust the boring measures. When you find yourself an hour into something and you can’t remember why you started, that’s the signal. Stand up, drink water, go outside for ten minutes. The session will wait. It always waits.

Watch the people around you for ground truth. I trust my wife to tell me when I’ve gone off the deep end before I notice myself. The bubble around the work is full of people doing the same thing as you, who will not be the ones to flag that you’ve been weird at dinner all week. The people who’ll flag it are the ones outside the bubble. Listen to them.

Don’t trust the in-the-moment “I’m so productive” feeling. It might be true. It might be the slot machine. The way to tell is whether you’re shipping work you’re proud of two weeks later, not whether you ended the day pulse-pounding.

The arbitrage will still be there next week. This is the one I keep telling myself. The window is wide. It will not slam shut on Thursday. The people who go the furthest with this technology over the next five years won’t be the ones who burned hottest in the first quarter — they’ll be the ones who can still think clearly in year three. That’s a craft of its own.

---

For the mechanics of how I actually run Claude Code day to day, see Claude Code: When AI Stops Talking and Starts Doing. For the system around the model that lets it work as a partner rather than a tool, Working With AI, Not Through It covers the rules-of-engagement piece. And if you’re still in the “is this even worth it” phase, How to Actually Get Good at AI is the better starting point.