Most agent demos end at the moment the agent says it succeeded. That’s where my work starts.
\nLast year, Helix was a few machines at home and one rule: if a routine task needs me to log in, it isn’t finished. I’ve spent the time since finding out how much of what passes for autonomy falls apart once you ask for proof.
\nI’m a registered polysomnographic technologist, which is probably why I got suspicious early. Much of that work is watching signals and deciding which ones are real. A patient rolling over can look alarming on the screen, while a real problem can look quiet. Sleep medicine has also had software scoring studies for years, and a person still reviews the result, because everyone in the field knows the software can be confidently wrong. The AI industry is learning that lesson in public and acting surprised.
\nEarly on, I measured progress by how much the agents could do, and they could do a lot. They also got in each other’s way. Two agents working in the same tree cost me a review gate in August and a file in September.
\nNothing about that was an intelligence failure. Two writers shared one resource with no coordination, a bug older than most of the people now selling multi-agent frameworks. A better prompt wouldn’t have touched it, and I’ve come to think an instruction in a prompt is only a request. A rule is something the agent can’t get around.
\nSo I wrote a boring one: code reaches the main server by one route, behind tests, and it rolls back if they fail. That route grew into a loop that runs on a schedule, finds failures that keep recurring, proposes fixes, tests them and ships them. A new check has to fail against the broken code before it can vouch for a fix, because I don’t trust a test I’ve never seen fail. Every change gets a versioned release note, and there have been 650 of those since version 1.0 went out on September 5.
\nThe failures that taught me the most had nothing to do with how smart the models were.
\nIn September, two servers went down. An outside watcher I’d built saw it and said nothing for six hours. I had shipped it muted so it wouldn’t nag me while it proved itself, and four separate settings kept it quiet. That one was entirely my fault, and I’d now call a muted monitor worse than none, since having it let me believe someone was watching. It ships armed now, and a muted watcher gets reported like any other problem.
\nA few days later, the account paying for one of our models hit zero, and every job that depended on it failed for days. Everything watching the fleet was checking whether machines and services were alive, and none of it could see a wallet. I’ve never seen a wallet on an agent architecture diagram, and I’d bet yours doesn’t have one either. I added a watcher for the balance.
\nThen there was the tool reporting “Logged in” on machines whose logins were dead. We stopped asking it, and now we find out who can do the work by having them try. I treat an agent’s “done” the same way. It’s a claim, and it’s worth about as much as that login status until something outside the agent confirms it.
\nAlerts are where people fool themselves most. Everyone adds them and almost nobody measures them. I tested mine against 1,924 real outputs. Tightening the rules took them from about 20 a day to about 6, and on a labelled test set they still caught all 49 cases they had to catch. If you can’t give me those numbers for your own alerts, you don’t know what they do.
\nFull autonomy is the wrong thing to aim for, and I say that as someone whose rule is that the system shouldn’t need me. What I want is for it to need my attention rarely and my authority always.
\nI use agents for most of the routine work, more of it than ever, with more checks around them. “Done” has to mean a test passed or a real run happened, and the result gets written down. A model from a different vendor reviews what matters, since models share blind spots with themselves, and asking one to check its own work is mostly theater. Agreements with an agent go in a log so they survive the conversation. A small set of systems can’t be changed without my recorded approval, and the most serious approvals carry my signature.
\nI’d take a mediocre model inside that structure over the best model in the world without it. Most of the engineering is in that layer: deciding what an agent may do alone and what needs a person, and being able to tell afterward what really happened. It’s less fun to post about than a new model release, and it’s the only part of this that has kept paying off.
\nThis site came out of the same process. I rebuilt its publishing desk with agents, and a review of the work caught a real security bug before anything went public. I don’t find that embarrassing. Agents write bugs and so do I, and what I care about is whether something was set up to catch them.
\nThings still break, and I still find gaps I hadn’t thought to check. When something goes wrong now, I can usually tell you what knew about it, when it knew, and why it said what it said, which I couldn’t have done a year ago. I’d ask that of anyone telling you their agents run themselves. The tagline here still says “supposed to,” and I’m keeping it.
\n","content_text":"Most agent demos end at the moment the agent says it succeeded. That’s where my work starts.\nLast year, Helix was a few machines at home and one rule: if a routine task needs me to log in, it isn’t finished. I’ve spent the time since finding out how much of what passes for autonomy falls apart once you ask for proof.\nI’m a registered polysomnographic technologist, which is probably why I got suspicious early. Much of that work is watching signals and deciding which ones are real. A patient rolling over can look alarming on the screen, while a real problem can look quiet. Sleep medicine has also had software scoring studies for years, and a person still reviews the result, because everyone in the field knows the software can be confidently wrong. The AI industry is learning that lesson in public and acting surprised.\nMulti-agent is a concurrency problem\nEarly on, I measured progress by how much the agents could do, and they could do a lot. They also got in each other’s way. Two agents working in the same tree cost me a review gate in August and a file in September.\nNothing about that was an intelligence failure. Two writers shared one resource with no coordination, a bug older than most of the people now selling multi-agent frameworks. A better prompt wouldn’t have touched it, and I’ve come to think an instruction in a prompt is only a request. A rule is something the agent can’t get around.\nSo I wrote a boring one: code reaches the main server by one route, behind tests, and it rolls back if they fail. That route grew into a loop that runs on a schedule, finds failures that keep recurring, proposes fixes, tests them and ships them. A new check has to fail against the broken code before it can vouch for a fix, because I don’t trust a test I’ve never seen fail. Every change gets a versioned release note, and there have been 650 of those since version 1.0 went out on September 5.\nYour dashboard is lying to you\nThe failures that taught me the most had nothing to do with how smart the models were.\nIn September, two servers went down. An outside watcher I’d built saw it and said nothing for six hours. I had shipped it muted so it wouldn’t nag me while it proved itself, and four separate settings kept it quiet. That one was entirely my fault, and I’d now call a muted monitor worse than none, since having it let me believe someone was watching. It ships armed now, and a muted watcher gets reported like any other problem.\nA few days later, the account paying for one of our models hit zero, and every job that depended on it failed for days. Everything watching the fleet was checking whether machines and services were alive, and none of it could see a wallet. I’ve never seen a wallet on an agent architecture diagram, and I’d bet yours doesn’t have one either. I added a watcher for the balance.\nThen there was the tool reporting “Logged in” on machines whose logins were dead. We stopped asking it, and now we find out who can do the work by having them try. I treat an agent’s “done” the same way. It’s a claim, and it’s worth about as much as that login status until something outside the agent confirms it.\nAlerts are where people fool themselves most. Everyone adds them and almost nobody measures them. I tested mine against 1,924 real outputs. Tightening the rules took them from about 20 a day to about 6, and on a labelled test set they still caught all 49 cases they had to catch. If you can’t give me those numbers for your own alerts, you don’t know what they do.\nI want less of my attention spent, and all of my authority kept\nFull autonomy is the wrong thing to aim for, and I say that as someone whose rule is that the system shouldn’t need me. What I want is for it to need my attention rarely and my authority always.\nI use agents for most of the routine work, more of it than ever, with more checks around them. “Done” has to mean a test passed or a real run happened, and the result gets written down. A model from a different vendor reviews what matters, since models share blind spots with themselves, and asking one to check its own work is mostly theater. Agreements with an agent go in a log so they survive the conversation. A small set of systems can’t be changed without my recorded approval, and the most serious approvals carry my signature.\nI’d take a mediocre model inside that structure over the best model in the world without it. Most of the engineering is in that layer: deciding what an agent may do alone and what needs a person, and being able to tell afterward what really happened. It’s less fun to post about than a new model release, and it’s the only part of this that has kept paying off.\nThis site came out of the same process. I rebuilt its publishing desk with agents, and a review of the work caught a real security bug before anything went public. I don’t find that embarrassing. Agents write bugs and so do I, and what I care about is whether something was set up to catch them.\nThings still break, and I still find gaps I hadn’t thought to check. When something goes wrong now, I can usually tell you what knew about it, when it knew, and why it said what it said, which I couldn’t have done a year ago. I’d ask that of anyone telling you their agents run themselves. The tagline here still says “supposed to,” and I’m keeping it.","date_published":"2026-11-02T00:00:00-05:00","date_modified":"2026-11-02T00:00:00-05:00","tags":["Agents","Automation","Infrastructure"],"_kind":"note"},{"id":"https://waltspence.com/thoughts/w2611a2","url":"https://waltspence.com/thoughts/w2611a2","content_html":"Autonomy and authority aren’t the same thing. Agents can do the work. Restarting the system should still take my signature.
\n","content_text":"Autonomy and authority aren’t the same thing. Agents can do the work. Restarting the system should still take my signature.","date_published":"2026-11-01T12:00:00-05:00","tags":["Agents","Automation"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2611a5","url":"https://waltspence.com/thoughts/w2611a5","content_html":"Match the model to the stakes. A small coding model is fine for light work and the wrong call for anything critical.
\n","content_text":"Match the model to the stakes. A small coding model is fine for light work and the wrong call for anything critical.","date_published":"2026-10-26T12:00:00-04:00","tags":["Agents"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2611b2","url":"https://waltspence.com/thoughts/w2611b2","content_html":"Don’t let the main menu turn into a junk drawer. Anything that keeps piling up gets its own menu.
\n","content_text":"Don’t let the main menu turn into a junk drawer. Anything that keeps piling up gets its own menu.","date_published":"2026-10-23T15:00:00-04:00","tags":["macOS"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2611b1","url":"https://waltspence.com/thoughts/w2611b1","content_html":"A good test for any app: what would make it a no-question $25 one-time purchase?
\n","content_text":"A good test for any app: what would make it a no-question $25 one-time purchase?","date_published":"2026-10-23T14:00:00-04:00","tags":["macOS"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2611a7","url":"https://waltspence.com/thoughts/w2611a7","content_html":"Ask what standard practice is. Then ask what the gold standard is, and build toward that one.
\n","content_text":"Ask what standard practice is. Then ask what the gold standard is, and build toward that one.","date_published":"2026-10-23T13:00:00-04:00","tags":["Automation"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2611a6","url":"https://waltspence.com/thoughts/w2611a6","content_html":"When a model swings from “this is nothing” to “build everything around this” in one reply, call it out and get a second opinion.
\n","content_text":"When a model swings from “this is nothing” to “build everything around this” in one reply, call it out and get a second opinion.","date_published":"2026-10-23T12:00:00-04:00","tags":["Agents"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2611b3","url":"https://waltspence.com/thoughts/w2611b3","content_html":"Name things so they don’t collide with words people already know. “Package” already means something on Linux.
\n","content_text":"Name things so they don’t collide with words people already know. “Package” already means something on Linux.","date_published":"2026-10-22T12:00:00-04:00","tags":["Infrastructure"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2611a3","url":"https://waltspence.com/thoughts/w2611a3","content_html":"If an agent answers with a list of things for me to do, it has the roles backwards. I’m not the worker here. It is.
\n","content_text":"If an agent answers with a list of things for me to do, it has the roles backwards. I’m not the worker here. It is.","date_published":"2026-10-20T12:00:00-04:00","tags":["Agents"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2611a1","url":"https://waltspence.com/thoughts/w2611a1","content_html":"Separate the agents that decide policy from the agents that carry it out. Church and state.
\n","content_text":"Separate the agents that decide policy from the agents that carry it out. Church and state.","date_published":"2026-10-18T12:00:00-04:00","tags":["Agents"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2611a8","url":"https://waltspence.com/thoughts/w2611a8","content_html":"If the text already exists, read it. Don’t record the microphone to transcribe what the closed captions are already saying.
\n","content_text":"If the text already exists, read it. Don’t record the microphone to transcribe what the closed captions are already saying.","date_published":"2026-10-17T12:00:00-04:00","tags":["Automation","macOS"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2611a9","url":"https://waltspence.com/thoughts/w2611a9","content_html":"Let the user pick light or dark. Player controls that change color with whatever is on screen are just annoying.
\n","content_text":"Let the user pick light or dark. Player controls that change color with whatever is on screen are just annoying.","date_published":"2026-10-16T12:00:00-04:00","tags":["macOS"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2611a4","url":"https://waltspence.com/thoughts/w2611a4","content_html":"Not every decision needs a frontier model. Let a cheap model judge whether the request needs an expensive one.
\n","content_text":"Not every decision needs a frontier model. Let a cheap model judge whether the request needs an expensive one.","date_published":"2026-10-13T12:00:00-04:00","tags":["Agents"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2025a2","url":"https://waltspence.com/thoughts/w2025a2","content_html":"If your agent’s only memory is the chat window, it doesn’t have a memory.
\n","content_text":"If your agent’s only memory is the chat window, it doesn’t have a memory.","date_published":"2025-06-24T22:10:00-04:00","tags":["Agents"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2025a1","url":"https://waltspence.com/thoughts/w2025a1","content_html":"I don’t want an AI that does everything. I want one that tells me exactly what it did.
\n","content_text":"I don’t want an AI that does everything. I want one that tells me exactly what it did.","date_published":"2025-02-11T21:50:00-05:00","tags":["Agents","Automation"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2024a2","url":"https://waltspence.com/thoughts/w2024a2","content_html":"A small model that knows its job beats a big model guessing at yours.
\n","content_text":"A small model that knows its job beats a big model guessing at yours.","date_published":"2024-08-20T06:45:00-04:00","tags":["Agents"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2024a1","url":"https://waltspence.com/thoughts/w2024a1","content_html":"Run a model on your own machine once and you’ll understand what you’ve been trading for convenience.
\n","content_text":"Run a model on your own machine once and you’ll understand what you’ve been trading for convenience.","date_published":"2024-03-12T22:30:00-04:00","tags":["Agents"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2023a2","url":"https://waltspence.com/thoughts/w2023a2","content_html":"The AI demo ends when the model says it worked. The product starts there.
\n","content_text":"The AI demo ends when the model says it worked. The product starts there.","date_published":"2023-10-03T21:20:00-04:00","tags":["Agents"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2023a1","url":"https://waltspence.com/thoughts/w2023a1","content_html":"Prompt engineering is a job title for a problem that should be solved in code.
\n","content_text":"Prompt engineering is a job title for a problem that should be solved in code.","date_published":"2023-05-16T22:40:00-04:00","tags":["Agents"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2022a2","url":"https://waltspence.com/thoughts/w2022a2","content_html":"Everyone’s asking what ChatGPT knows. The better question is what it will do when nobody’s checking.
\n","content_text":"Everyone’s asking what ChatGPT knows. The better question is what it will do when nobody’s checking.","date_published":"2022-12-06T23:15:00-05:00","tags":["Agents"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2022a1","url":"https://waltspence.com/thoughts/w2022a1","content_html":"Pediatric studies are the hardest work in sleep medicine and the most rewarding. Kids don’t fake sleep, and they don’t fake being uncomfortable either.
\n","content_text":"Pediatric studies are the hardest work in sleep medicine and the most rewarding. Kids don’t fake sleep, and they don’t fake being uncomfortable either.","date_published":"2022-04-26T06:30:00-04:00","tags":["Sleep Medicine"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2021a2","url":"https://waltspence.com/thoughts/w2021a2","content_html":"The patient trusts the device, and the device maker never meets the patient. When something goes wrong, the technologist is the one in the room explaining it.
\n","content_text":"The patient trusts the device, and the device maker never meets the patient. When something goes wrong, the technologist is the one in the room explaining it.","date_published":"2021-07-08T06:55:00-04:00","tags":["Sleep Medicine"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2021a1","url":"https://waltspence.com/thoughts/w2021a1","content_html":"NFTs are the new box of samples. Same pitch, new chain.
\n","content_text":"NFTs are the new box of samples. Same pitch, new chain.","date_published":"2021-03-18T22:05:00-04:00","tags":["Commentary"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2020a2","url":"https://waltspence.com/thoughts/w2020a2","content_html":"Home sleep tests will keep growing, and they should. But a home test can’t watch the patient. Some studies still need a technologist in the room.
\n","content_text":"Home sleep tests will keep growing, and they should. But a home test can’t watch the patient. Some studies still need a technologist in the room.","date_published":"2020-09-22T07:40:00-04:00","tags":["Sleep Medicine"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/w2020a1","url":"https://waltspence.com/thoughts/w2020a1","content_html":"Remote work isn’t new. We ran EnLab as a distributed team in 2015. What’s new is that managers can’t hide behind the office anymore.
\n","content_text":"Remote work isn’t new. We ran EnLab as a distributed team in 2015. What’s new is that managers can’t hide behind the office anymore.","date_published":"2020-04-14T21:10:00-04:00","tags":["Entrepreneurship"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/s000002","url":"https://waltspence.com/thoughts/s000002","external_url":"/notes/embrace-the-rain","content_html":"I always take time to learn from my circumstances. Life has seasons. I’ve learned to embrace the rain.
\n","content_text":"I always take time to learn from my circumstances. Life has seasons. I’ve learned to embrace the rain.","date_published":"2018-08-24T07:35:00-04:00","tags":["Writing"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/s000003","url":"https://waltspence.com/thoughts/s000003","external_url":"/notes/embrace-the-rain","content_html":"Take a whole day and make a good inventory of what’s positive in your life and what’s negative.
\n","content_text":"Take a whole day and make a good inventory of what’s positive in your life and what’s negative.","date_published":"2018-08-24T07:31:00-04:00","tags":["Writing","Entrepreneurship"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/s000004","url":"https://waltspence.com/thoughts/s000004","external_url":"/notes/embrace-the-rain","content_html":"You have to understand who you are. That’s critical to finding happiness.
\n","content_text":"You have to understand who you are. That’s critical to finding happiness.","date_published":"2018-08-24T07:21:00-04:00","tags":["Writing"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/thoughts/s000005","url":"https://waltspence.com/thoughts/s000005","external_url":"/notes/embrace-the-rain","content_html":"While you shouldn’t always concern yourself with what others think of you, you should always aim to present the best possible version of yourself.
\n","content_text":"While you shouldn’t always concern yourself with what others think of you, you should always aim to present the best possible version of yourself.","date_published":"2018-08-24T07:11:00-04:00","tags":["Writing"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/notes/embrace-the-rain","url":"https://waltspence.com/notes/embrace-the-rain","title":"Embrace the Rain: Ten Years of Lessons","summary":"Ten years of lessons, written down just before I turned 36.","content_html":"Lately I’ve been feeling listless and reflective. I blame the rain as much as anything, but I can trace it back a while. It started with the death of someone who shaped how I see the world, Anthony Bourdain. Not long after, we lost my uncle. There were other problems during that time and there have been since.
\nIt doesn’t keep me from getting things done, but my brain has to process things. I always take time to learn from my circumstances. Life has seasons. I’ve learned to embrace the rain.
\nWriting helps me work through things, and I like sharing what I’ve learned. I’m about to turn 36, so I decided to write down some of the lessons from the last 10 years, because I don’t think I’ve grown more in any other stretch of my life. I’m not an expert, far from it. I’m a work in progress. I’m sharing these because a lot of people have given me good advice.
\nMost of these topics could be a book on their own, but I’ve tried to respect your time.
\nYour beliefs will probably change. One day you’ll wake up and start questioning what you thought was true, whether that’s religion, relationships, or almost anything else. Don’t despair. That’s part of growing. Your beliefs might change, or you might circle back to what you believed in the first place. I question my beliefs often. It’s the only way I stay grounded in them.
\nYou might not find your passion, so learn to find it in what you’re doing. You’ve heard “find your passion” so much that this probably sounds like terrible advice. I thought so too when I first heard it. With time it has proven true. I’ve watched friends end up unfulfilled following that advice. Some even became depressed, or worse. Either they couldn’t find their passion, or they found it and it couldn’t pay the bills. Find meaning in what you’re doing and go from there. Sometimes your passion is better as a hobby.
\nAt some point you’ll look back and not recognize who you used to be. That’s a good sign. It means you’ve grown. You should be more worried if this hasn’t happened. It’s easy to check. Ask yourself: “If I spent time with myself from five to ten years ago, could I relate to this person? Could I stand their company?” If the answer is yes, take a closer look. It could mean nothing, but it could be a sign.
\nYou can’t grow while you’re angry or cynical. You can’t grow emotionally if you hold a grudge. You can’t grow professionally or personally if you romanticize the past and are cynical about the present. Times change. Things aren’t better or worse, just different. Adapt.
\nBe patient. If you’re impatient you’re going to struggle at everything. This is one of my own struggles. Over time I’ve learned to enjoy the process and to enjoy getting even the smallest thing done, as long as it keeps me headed towards my goals.
\nTake responsibility, be accountable, and give credit. That’s what leaders do. If you’re ever in charge of people, understand that everything is your fault and that you work for them, not the other way around. If you run a business, be grateful that someone is willing to work for you.
\nListen to your critical self. Think of yourself as two people: your critical self, who knows what you should do, and your experiential self, who just wants to have a good time. People keep drinking because they think they’ll quit tomorrow. They never imagine that tomorrow they’ll be anything short of their perfect self. The trouble is we’re creatures of habit. If you live for today today, you’ll probably do it tomorrow, then most days, then all the time.
\nSave time. Go with your gut more often than not. It can save you time and a lot of pain. In my experience my gut nearly always knows which way to go. When I listen, things go well. When I ignore it and use logic alone, it backfires. It’s fine to weigh the pros and cons, that’s being responsible, but try not to ignore your intuition.
\nGet out of toxic relationships quickly. It doesn’t matter if it’s business, family, or friends. They hold you back and take a toll, and often all you learn from them is that they were toxic. I’ve been there several times in business and in my personal life. It’s a hard decision at the time, but you’ll thank yourself. Just make sure you’re in a good frame of mind when you make it.
\nBuild bridges and leave the matches at home. That may seem to contradict the last point, but this was one of the hardest lessons I’ve had to learn. Sometimes things don’t work out and you have to write someone off. But we also do this when we’re unhappy, without realizing it. We take things out on the wrong people and only hurt ourselves. If you’re not in a good frame of mind, good relationships can look toxic. So think carefully about how you approach every relationship. If you’ve burned the wrong bridge, work out where you went wrong, then reach out and try to make it right, expecting nothing.
\nThey’re about more than you and your issues. In a serious relationship you have to put aside some of your own issues. Not all of the time, but most of the time. All relationships, and especially romantic ones, are really about listening.
\nDon’t worry about how other people are doing. No keeping up with the Joneses. You’ll do it anyway. It’s human nature. We all compare our progress with somebody else’s. That’s ok, just limit it. Be genuinely happy for your friends when they’re doing well. But it shouldn’t change how you feel about your own life. The more you worry about other people’s lives, the less time you have for your own.
\nWhat does success mean to you? Everyone wants to be a millionaire. Few want to put in the effort to learn how, much less the hours to get there. If being a millionaire were easy, there wouldn’t be millionaires. Define what success means to you, and don’t base it on what other people think it is.
\nFind your passion. Don’t make it a career…necessarily. I’m going to get some heat for this, but “If you do what you love you’ll never work a day in your life” is bad, irresponsible advice. Your first job is meeting your responsibilities. If you want your own business, work on it on your own time. Something you’re passionate about may not be a good job. It might not pay enough to live on, or you might start hating it once you do it for a living. I’ve known people who went through both.
\nYou may find your purpose later in life. Don’t stress over finding what you love. Sometimes it comes much later, which is why it’s important to try everything.
\nLife will have light rain and the occasional hurricane. I hope some of this helps. Whatever happens, it’s your life.
\n","content_text":"A bit of a preamble\nLately I’ve been feeling listless and reflective. I blame the rain as much as anything, but I can trace it back a while. It started with the death of someone who shaped how I see the world, Anthony Bourdain. Not long after, we lost my uncle. There were other problems during that time and there have been since.\nIt doesn’t keep me from getting things done, but my brain has to process things. I always take time to learn from my circumstances. Life has seasons. I’ve learned to embrace the rain.\nWriting helps me work through things, and I like sharing what I’ve learned. I’m about to turn 36, so I decided to write down some of the lessons from the last 10 years, because I don’t think I’ve grown more in any other stretch of my life. I’m not an expert, far from it. I’m a work in progress. I’m sharing these because a lot of people have given me good advice.\nMost of these topics could be a book on their own, but I’ve tried to respect your time.\nYourself\nYour beliefs will probably change. One day you’ll wake up and start questioning what you thought was true, whether that’s religion, relationships, or almost anything else. Don’t despair. That’s part of growing. Your beliefs might change, or you might circle back to what you believed in the first place. I question my beliefs often. It’s the only way I stay grounded in them.\nYou might not find your passion, so learn to find it in what you’re doing. You’ve heard “find your passion” so much that this probably sounds like terrible advice. I thought so too when I first heard it. With time it has proven true. I’ve watched friends end up unfulfilled following that advice. Some even became depressed, or worse. Either they couldn’t find their passion, or they found it and it couldn’t pay the bills. Find meaning in what you’re doing and go from there. Sometimes your passion is better as a hobby.\nAt some point you’ll look back and not recognize who you used to be. That’s a good sign. It means you’ve grown. You should be more worried if this hasn’t happened. It’s easy to check. Ask yourself: “If I spent time with myself from five to ten years ago, could I relate to this person? Could I stand their company?” If the answer is yes, take a closer look. It could mean nothing, but it could be a sign.\nYou can’t grow while you’re angry or cynical. You can’t grow emotionally if you hold a grudge. You can’t grow professionally or personally if you romanticize the past and are cynical about the present. Times change. Things aren’t better or worse, just different. Adapt.\nBe patient. If you’re impatient you’re going to struggle at everything. This is one of my own struggles. Over time I’ve learned to enjoy the process and to enjoy getting even the smallest thing done, as long as it keeps me headed towards my goals.\nTake responsibility, be accountable, and give credit. That’s what leaders do. If you’re ever in charge of people, understand that everything is your fault and that you work for them, not the other way around. If you run a business, be grateful that someone is willing to work for you.\nListen to your critical self. Think of yourself as two people: your critical self, who knows what you should do, and your experiential self, who just wants to have a good time. People keep drinking because they think they’ll quit tomorrow. They never imagine that tomorrow they’ll be anything short of their perfect self. The trouble is we’re creatures of habit. If you live for today today, you’ll probably do it tomorrow, then most days, then all the time.\nSave time. Go with your gut more often than not. It can save you time and a lot of pain. In my experience my gut nearly always knows which way to go. When I listen, things go well. When I ignore it and use logic alone, it backfires. It’s fine to weigh the pros and cons, that’s being responsible, but try not to ignore your intuition.\nOther people\nGet out of toxic relationships quickly. It doesn’t matter if it’s business, family, or friends. They hold you back and take a toll, and often all you learn from them is that they were toxic. I’ve been there several times in business and in my personal life. It’s a hard decision at the time, but you’ll thank yourself. Just make sure you’re in a good frame of mind when you make it.\nBuild bridges and leave the matches at home. That may seem to contradict the last point, but this was one of the hardest lessons I’ve had to learn. Sometimes things don’t work out and you have to write someone off. But we also do this when we’re unhappy, without realizing it. We take things out on the wrong people and only hurt ourselves. If you’re not in a good frame of mind, good relationships can look toxic. So think carefully about how you approach every relationship. If you’ve burned the wrong bridge, work out where you went wrong, then reach out and try to make it right, expecting nothing.\nThey’re about more than you and your issues. In a serious relationship you have to put aside some of your own issues. Not all of the time, but most of the time. All relationships, and especially romantic ones, are really about listening.\nDon’t worry about how other people are doing. No keeping up with the Joneses. You’ll do it anyway. It’s human nature. We all compare our progress with somebody else’s. That’s ok, just limit it. Be genuinely happy for your friends when they’re doing well. But it shouldn’t change how you feel about your own life. The more you worry about other people’s lives, the less time you have for your own.\nWork and purpose\nWhat does success mean to you? Everyone wants to be a millionaire. Few want to put in the effort to learn how, much less the hours to get there. If being a millionaire were easy, there wouldn’t be millionaires. Define what success means to you, and don’t base it on what other people think it is.\nFind your passion. Don’t make it a career…necessarily. I’m going to get some heat for this, but “If you do what you love you’ll never work a day in your life” is bad, irresponsible advice. Your first job is meeting your responsibilities. If you want your own business, work on it on your own time. Something you’re passionate about may not be a good job. It might not pay enough to live on, or you might start hating it once you do it for a living. I’ve known people who went through both.\nYou may find your purpose later in life. Don’t stress over finding what you love. Sometimes it comes much later, which is why it’s important to try everything.\nLife will have light rain and the occasional hurricane. I hope some of this helps. Whatever happens, it’s your life.","date_published":"2018-08-24T07:00:00-04:00","date_modified":"2026-11-02T12:00:00-05:00","tags":["Open Web","Writing"],"_kind":"note"},{"id":"https://waltspence.com/notes/what-enlab-is-not","url":"https://waltspence.com/notes/what-enlab-is-not","title":"What EnLab is Not","summary":"Why EnLab refused to be called a startup, a SaaS company, an app studio or a web shop.","content_html":"On December 9, 2012, the business entity known as EnLab was born as an LLC. Our beginnings were as inauspicious as any other startup or small business. I began this business without much of a clue about what I actually wanted to do, other than knowing that I didn’t want to work for anyone else any more.
\nWith that in mind, I began with web development and consulting as a “solo-preneur.” As fate would have it, I ended up going down a long path that led me here, and I outlined that path in my previous post, Song of an Entrepreneur’s Soul.
\nRather than explaining that path, I want to flash forward to today. Our company has grown to just under ten people, three of whom are founders. The three of us are very proud to have made it this far, and it is all due to the vision we have for the future.
\nThat said, I find it difficult to share that vision when someone asks, “What is EnLab and what do you do?” The question is direct, but it also generalizes. Everyone who asks follows my answer with “Oh, I get it, you’re like X company or Z Inc.” My response is always “yeah, but no,” and I leave it at that.
\nI’ve had enough of it, though, because people then make assumptions based on that association.
\nSo here is my line in the sand. We won’t be put in a box.
\nWith all of this going back and forth, I decided it was better to just say who we are by our name. It’s more ambiguous, but it keeps us out of these boxes. You may be wondering now, though.
\nWe are a distributed development lab. We have people all around the world working on products together. We are also a holding company for future startups and products, and a place for aspiring entrepreneurs to see their ideas through, using our development talent in exchange for a little equity.
\nWe believe great ideas come from everywhere and should be brought to light to change the world. Since this is our direction, we also won’t be put in a box on our model. We reserve the right to experiment and try new things. Our name is EnLab because I believe life is about learning, assessing new data and acting on it. One could say life is spent in the lab, or EnLab.
\n\n\nPeople can keep their unicorns. This economy is driven by tiny empires.
\n
A footnote: I’ve been hearing a lot more talk about hustle culture lately, and you can read my take on it here. Thanks again to the folks at Basecamp for being a voice of reason in the crazy and seemingly unsustainable world of startups.
\n","content_text":"On December 9, 2012, the business entity known as EnLab was born as an LLC. Our beginnings were as inauspicious as any other startup or small business. I began this business without much of a clue about what I actually wanted to do, other than knowing that I didn’t want to work for anyone else any more.\nWith that in mind, I began with web development and consulting as a “solo-preneur.” As fate would have it, I ended up going down a long path that led me here, and I outlined that path in my previous post, Song of an Entrepreneur’s Soul.\nRather than explaining that path, I want to flash forward to today. Our company has grown to just under ten people, three of whom are founders. The three of us are very proud to have made it this far, and it is all due to the vision we have for the future.\nThat said, I find it difficult to share that vision when someone asks, “What is EnLab and what do you do?” The question is direct, but it also generalizes. Everyone who asks follows my answer with “Oh, I get it, you’re like X company or Z Inc.” My response is always “yeah, but no,” and I leave it at that.\nI’ve had enough of it, though, because people then make assumptions based on that association.\nSo here is my line in the sand. We won’t be put in a box.\nWhat EnLab is not\n\nA startup. Sure, in a general sense we are. But we are more in the mold of Jason Fried and DHH’s Basecamp. We share their vision of building a stable company. EnLab is a holding company in which to place many small bets and to seek investment in the companies we spin off from it.\nA SaaS company. Our first product, due out soon, is web based and a service, but we will not be put in this box. We won’t be put in any box unless it’s a TARDIS, because that would be cool. We will be building for many platforms. SaaS is traditionally thought of as web services, so I refuse to be labeled that way.\nAn app studio. I have often described EnLab this way because it makes our model easier to understand. But we aren’t backed by someone with a lot of money. We are bootstrapped and hungry. Recently I’ve tried to “fork” the term into development studio, and while that fits perfectly, it leads to the last box.\nA web development studio. This is the last box we’ve been put in, because of that switch to “development studio.” It’s understandable that someone would think this, but my reaction was always, in my head, “that’s what this used to be.”\n\nWith all of this going back and forth, I decided it was better to just say who we are by our name. It’s more ambiguous, but it keeps us out of these boxes. You may be wondering now, though.\nWhat is EnLab?\nWe are a distributed development lab. We have people all around the world working on products together. We are also a holding company for future startups and products, and a place for aspiring entrepreneurs to see their ideas through, using our development talent in exchange for a little equity.\nWe believe great ideas come from everywhere and should be brought to light to change the world. Since this is our direction, we also won’t be put in a box on our model. We reserve the right to experiment and try new things. Our name is EnLab because I believe life is about learning, assessing new data and acting on it. One could say life is spent in the lab, or EnLab.\n\nPeople can keep their unicorns. This economy is driven by tiny empires.\n\nA footnote: I’ve been hearing a lot more talk about hustle culture lately, and you can read my take on it here. Thanks again to the folks at Basecamp for being a voice of reason in the crazy and seemingly unsustainable world of startups.","date_published":"2015-12-21T17:32:00-05:00","date_modified":"2026-11-02T12:00:00-05:00","tags":["Writing","Entrepreneurship"],"_kind":"note"},{"id":"https://waltspence.com/thoughts/s000008","url":"https://waltspence.com/thoughts/s000008","external_url":"/notes/song-of-an-entrepreneurs-soul","content_html":"There are way too many articles selling a lifestyle that doesn’t exist for everyone in this startup community.
\n","content_text":"There are way too many articles selling a lifestyle that doesn’t exist for everyone in this startup community.","date_published":"2015-08-31T09:05:00-04:00","tags":["Entrepreneurship"],"_kind":"thought","_source":"native"},{"id":"https://waltspence.com/notes/song-of-an-entrepreneurs-soul","url":"https://waltspence.com/notes/song-of-an-entrepreneurs-soul","title":"What Bootstrapping Actually Looked Like","summary":"On hustle culture, the gap between the lifestyle being sold and the life being lived, and what it actually looked like for me.","content_html":"I want to vent about the entrepreneurship community on the web. I’ve bitten my tongue for too long, watching talking heads glamorize “hustle culture” when there is little to no glamor in it.
\nMany of you will think this sounds bitter. Fair enough.
\nI’d rather share something that means something to me. There are way too many articles selling a lifestyle that doesn’t exist for everyone in this startup community.
\nSo here’s my own story. Many people will dismiss it and say I just need to “get out” and get another job. That’s fine.
\nFall of 2007. I was working as a polysomnographic technician, which paid well enough for the nicest apartment in the nicest part of Richmond, Virginia.
\nI also did web development as a hobby, as I have since ’96 or ’97 (way before it was called “coding”). Since it wasn’t my main job I was a little behind on the latest techniques, but I thought I was very good.
\nThen the economic downturn came, and I was laid off from a job I had no intention of ever leaving. After several failed attempts to join another practice, I decided to use the skills I’d picked up over the years and do what the people I read and listened to kept saying to do.
\nI was going into business for myself. I had $1,500 in the bank and felt confident in my ability to sell and in my skills. I knew I would be ok. I was finally going to stop making money for someone else.
\nAfter chasing clients and mostly coming up short, I learned what I didn’t know. I was young and comfortable and I hadn’t done any research.
\nWeb development in Richmond had grown a lot while I wasn’t looking. There were plenty of freelancers thanks to technical schools and online courses.
\nThat was my first clue that I wasn’t the businessman I thought I was.
\nThat first attempt was a total failure. I didn’t understand the market and I overestimated my value. I felt crushed. I didn’t have the money to keep the business going, so I started looking for jobs in my field so I could feed myself and pay bills again.
\nI went back to the first clinic where I’d been a technician and realized it was close to going out of business because of poor management and changes in Medicare reimbursement. I saw the signs and jumped at a job at a hospital an hour away, for the stability.
\nFor a while I was completely satisfied, but after a few months I saw that even hospitals were feeling the Medicare changes. The politics there were also way too much for me.
\nAfter too many long days and nights of worrying about the future, I went back to the video that first got me thinking about working for myself: Steve Jobs’ commencement speech at Stanford.
\nWatching it again, I knew it was time to start planning another go. This time I had saved a little more cash and had been educating myself for a while before making the jump.
\nI had gone through everything I could find on small business, startups and management: books, documentaries, TV shows, radio shows, podcasts. I felt ready.
\nI decided to try a different kind of business, so I could keep up with web development and learn more about commerce with a partner I trusted.
\nSo I went into business with my brother. We took over a consignment retail store in Waynesboro, VA. We had very little traction, but within the first few months we turned that around.
\nWe were breaking sales records by listening to our customers, getting involved in the community, creating an online store and working as hard as we could.
\nThat still wasn’t enough for our goals, so we changed the model from full consignment to about 50/50 new and used inventory. That made all the difference, and I learned a lot about markets, supply, and demand.
\nI also learned about sacrifice, and that I still wasn’t as good with money as I hoped. I hadn’t saved enough. We reinvested in the store and didn’t pay anyone, including ourselves, for the first 2–3 months. When my money started running out, we agreed to pay me a little to help with the car payment, but that still wasn’t enough to feed myself.
\nSo I worked late nights on the weekend putting out signs for a local real estate company, for months, in all kinds of weather, including over a foot of snow, just to stay afloat.
\nThere was no glamor in any of it, whatever some talking heads would have you believe. Sacrifice was a hard lesson, but as important as any business lesson so far.
\nWith those lessons, and many late nights learning more web and app development, I started missing my old business and my family home in Richmond. I went home to try again on my own. I wanted to show myself I could do it.
\nThis time I did rather well on client work, but money was still tight.
\nI’ve grown tired of chasing clients, so I’m changing direction again, back towards what I actually care about.
\nI believe in good ideas and smart people, so I started recruiting people who wanted the same thing. I have a clear idea of where EnLab is going over the next 5 years. That has led to a team I could only have dreamed of a couple of years ago, and conversations with investors about seed rounds. Even so, I still work part time at night on weekends doing what I used to do.
\nI look forward to seeing what a partly client services, partly app studio model does for the company, the team and the community.
\nWhatever happens to EnLab from here, this has been a long and difficult road. I wouldn’t wish some of the lows on anyone, and the highs sometimes feel few and far between.
\nI have gone months without maintenance on my vehicles, and I haven’t been to a doctor in at least 3 years because I haven’t had health insurance. It’s not glamorous. We don’t all come up with an idea and suddenly have a fancy office in San Francisco or New York.
\nEven so, I think this is the best path. I’ve grown, the business has grown organically, and I wouldn’t trade what I’ve learned. I’m still learning, right now the difference between small business and fundraising for startups (converts, Y Combinator’s simple agreements for future equity, how long a seed round should keep a company running, etc).
\nWe all wish we could build a killer app and have that be the end of the story. For most of us it’s slow and hard. If you’re bootstrapping, patience isn’t optional.
\nIt’s a long game.
\n","content_text":"I want to vent about the entrepreneurship community on the web. I’ve bitten my tongue for too long, watching talking heads glamorize “hustle culture” when there is little to no glamor in it.\nMany of you will think this sounds bitter. Fair enough.\nI’d rather share something that means something to me. There are way too many articles selling a lifestyle that doesn’t exist for everyone in this startup community.\nSo here’s my own story. Many people will dismiss it and say I just need to “get out” and get another job. That’s fine.\nFall of 2007. I was working as a polysomnographic technician, which paid well enough for the nicest apartment in the nicest part of Richmond, Virginia.\nI also did web development as a hobby, as I have since ’96 or ’97 (way before it was called “coding”). Since it wasn’t my main job I was a little behind on the latest techniques, but I thought I was very good.\nThen the economic downturn came, and I was laid off from a job I had no intention of ever leaving. After several failed attempts to join another practice, I decided to use the skills I’d picked up over the years and do what the people I read and listened to kept saying to do.\nI was going into business for myself. I had $1,500 in the bank and felt confident in my ability to sell and in my skills. I knew I would be ok. I was finally going to stop making money for someone else.\nAfter chasing clients and mostly coming up short, I learned what I didn’t know. I was young and comfortable and I hadn’t done any research.\nWeb development in Richmond had grown a lot while I wasn’t looking. There were plenty of freelancers thanks to technical schools and online courses.\nThat was my first clue that I wasn’t the businessman I thought I was.\nThat first attempt was a total failure. I didn’t understand the market and I overestimated my value. I felt crushed. I didn’t have the money to keep the business going, so I started looking for jobs in my field so I could feed myself and pay bills again.\nI went back to the first clinic where I’d been a technician and realized it was close to going out of business because of poor management and changes in Medicare reimbursement. I saw the signs and jumped at a job at a hospital an hour away, for the stability.\nFor a while I was completely satisfied, but after a few months I saw that even hospitals were feeling the Medicare changes. The politics there were also way too much for me.\nAfter too many long days and nights of worrying about the future, I went back to the video that first got me thinking about working for myself: Steve Jobs’ commencement speech at Stanford.\nWatching it again, I knew it was time to start planning another go. This time I had saved a little more cash and had been educating myself for a while before making the jump.\nI had gone through everything I could find on small business, startups and management: books, documentaries, TV shows, radio shows, podcasts. I felt ready.\nI decided to try a different kind of business, so I could keep up with web development and learn more about commerce with a partner I trusted.\nSo I went into business with my brother. We took over a consignment retail store in Waynesboro, VA. We had very little traction, but within the first few months we turned that around.\nWe were breaking sales records by listening to our customers, getting involved in the community, creating an online store and working as hard as we could.\nThat still wasn’t enough for our goals, so we changed the model from full consignment to about 50/50 new and used inventory. That made all the difference, and I learned a lot about markets, supply, and demand.\nI also learned about sacrifice, and that I still wasn’t as good with money as I hoped. I hadn’t saved enough. We reinvested in the store and didn’t pay anyone, including ourselves, for the first 2–3 months. When my money started running out, we agreed to pay me a little to help with the car payment, but that still wasn’t enough to feed myself.\nSo I worked late nights on the weekend putting out signs for a local real estate company, for months, in all kinds of weather, including over a foot of snow, just to stay afloat.\nThere was no glamor in any of it, whatever some talking heads would have you believe. Sacrifice was a hard lesson, but as important as any business lesson so far.\nWith those lessons, and many late nights learning more web and app development, I started missing my old business and my family home in Richmond. I went home to try again on my own. I wanted to show myself I could do it.\nThis time I did rather well on client work, but money was still tight.\nI’ve grown tired of chasing clients, so I’m changing direction again, back towards what I actually care about.\nI believe in good ideas and smart people, so I started recruiting people who wanted the same thing. I have a clear idea of where EnLab is going over the next 5 years. That has led to a team I could only have dreamed of a couple of years ago, and conversations with investors about seed rounds. Even so, I still work part time at night on weekends doing what I used to do.\nI look forward to seeing what a partly client services, partly app studio model does for the company, the team and the community.\nWhatever happens to EnLab from here, this has been a long and difficult road. I wouldn’t wish some of the lows on anyone, and the highs sometimes feel few and far between.\nI have gone months without maintenance on my vehicles, and I haven’t been to a doctor in at least 3 years because I haven’t had health insurance. It’s not glamorous. We don’t all come up with an idea and suddenly have a fancy office in San Francisco or New York.\nEven so, I think this is the best path. I’ve grown, the business has grown organically, and I wouldn’t trade what I’ve learned. I’m still learning, right now the difference between small business and fundraising for startups (converts, Y Combinator’s simple agreements for future equity, how long a seed round should keep a company running, etc).\nWe all wish we could build a killer app and have that be the end of the story. For most of us it’s slow and hard. If you’re bootstrapping, patience isn’t optional.\nIt’s a long game.","date_published":"2015-08-31T09:00:00-04:00","date_modified":"2026-11-02T12:00:00-05:00","tags":["Writing","Entrepreneurship","Sleep Medicine"],"_kind":"note"}]}