← Back
Nate B. Jones June 12, 2026 19m

Codex: Your First Personal AI Agent Delegation Loop

Read full transcript 15 segments
  1. I'm obsessed with Codex right now, in I'm obsessed with Codex right now, in the way a kid is obsessed with a new the way a kid is obsessed with a new the way a kid is obsessed with a new PlayStation. I keep wanting to kind of PlayStation. I keep wanting to kind of PlayStation. I keep wanting to kind of grab people and say, "No, no, no, you grab people and say, "No, no, no, you grab people and say, "No, no, no, you have to see what this thing just did." have to see what this thing just did." have to see what this thing just did." Because Codex is not just giving me Because Codex is not just giving me Because Codex is not just giving me better AI answers, it's making my better AI answers, it's making my better AI answers, it's making my computer feel different. It's my files, computer feel different. It's my files, computer feel different. It's my files, it's my browser, it's my folders and it's my browser, it's my folders and it's my browser, it's my folders and drafts and screenshots, and they're all drafts and screenshots, and they're all drafts and screenshots, and they're all belonging to Codex now, right? It's all belonging to Codex now, right? It's all belonging to Codex now, right? It's all of my weird little systems and the stuff of my weird little systems and the stuff of my weird little systems and the stuff I usually have to manually connect all I usually have to manually connect all I usually have to manually connect all by myself. Codex moves across all of by myself. Codex moves across all of by myself. Codex moves across all of that. And that is why my token dashboard that. And that is why my token dashboard that. And that is why my token dashboard has gotten ridiculous lately. Not has gotten ridiculous lately. Not has gotten ridiculous lately. Not because I'm chatting more, but because because I'm chatting more, but because because I'm chatting more, but because I'm handing Codex bigger jobs. Before I'm handing Codex bigger jobs. Before I'm handing Codex bigger jobs. Before Codex, a lot of my AI work still ended Codex, a lot of my AI work still ended Codex, a lot of my AI work still ended up looking like chat, unless it was up looking like chat, unless it was up looking like chat, unless it was code, right? "Draft this, summarize code, right? "Draft this, summarize code, right? "Draft this, summarize this, clean this up, help me think this, clean this up, help me think this, clean this up, help me think through this." And it was really useful, through this." And it was really useful, through this." And it was really useful, but it was still basically me asking for but it was still basically me asking for but it was still basically me asking for help. And with Codex, I started doing help. And with Codex, I started doing help. And with Codex, I started doing something else. I started giving my something else. I started giving my something else. I started giving my computer jobs. Find the transcript, read computer jobs. Find the transcript, read computer jobs. Find the transcript, read the folder, compare the versions, render the folder, compare the versions, render the folder, compare the versions, render the Word file, check that it opens, open the Word file, check that it opens, open the Word file, check that it opens, open the browser, use the site, keep going the browser, use the site, keep going the browser, use the site, keep going until there's something real for me to until there's something real for me to until there's something real for me to inspect. And that is why Codex is inspect. And that is why Codex is inspect. And that is why Codex is blowing my mind. Not because it writes blowing my mind. Not because it writes blowing my mind. Not because it writes code, but because it makes the computer code, but because it makes the computer code, but because it makes the computer feel like something I can hand work to.

  2. feel like something I can hand work to. feel like something I can hand work to. My files and drafts are all now in range My files and drafts are all now in range My files and drafts are all now in range for Codex. More and more of anything I for Codex. More and more of anything I for Codex. More and more of anything I do on the computer is now work I can do on the computer is now work I can do on the computer is now work I can hand to an agent in plain English. And hand to an agent in plain English. And hand to an agent in plain English. And this is the part I want to unpack, this is the part I want to unpack, this is the part I want to unpack, because I think people are going to because I think people are going to because I think people are going to bounce off this tool for the wrong bounce off this tool for the wrong bounce off this tool for the wrong reason. This is not a take-a-side video. reason. This is not a take-a-side video. reason. This is not a take-a-side video. I am not asking you to join team OpenAI. I am not asking you to join team OpenAI. I am not asking you to join team OpenAI. This is just a deep dive into why Codex This is just a deep dive into why Codex This is just a deep dive into why Codex works for me, why I'm fired up about it, works for me, why I'm fired up about it, works for me, why I'm fired up about it, and what I've learned from using it hard and what I've learned from using it hard and what I've learned from using it hard enough that it's actually changed my enough that it's actually changed my enough that it's actually changed my day. And if you haven't used it because day. And if you haven't used it because day. And if you haven't used it because the word Codex sounds like code, that's the word Codex sounds like code, that's the word Codex sounds like code, that's exactly why you ought to stay with me exactly why you ought to stay with me exactly why you ought to stay with me here. The name is bad, honestly. It here. The name is bad, honestly. It here. The name is bad, honestly. It sounds like a developer tool. But it's sounds like a developer tool. But it's sounds like a developer tool. But it's not only a developer tool. Developers not only a developer tool. Developers not only a developer tool. Developers are seeing it first because coding has a are seeing it first because coding has a are seeing it first because coding has a really clean working environment that really clean working environment that really clean working environment that made it easy for Codex to engage. It has made it easy for Codex to engage. It has made it easy for Codex to engage. It has clean tests and files and diffs and logs clean tests and files and diffs and logs clean tests and files and diffs and logs and Codex can engage with that. But the and Codex can engage with that. But the and Codex can engage with that. But the habit Codex teaches is much bigger than habit Codex teaches is much bigger than habit Codex teaches is much bigger than code. If you write if you research, if code. If you write if you research, if code. If you write if you research, if you make documents or Excel you make documents or Excel you make documents or Excel spreadsheets, or if you run a tiny spreadsheets, or if you run a tiny spreadsheets, or if you run a tiny business, or if you organize projects, business, or if you organize projects, business, or if you organize projects, or build side projects, or manage or build side projects, or manage or build side projects, or manage content, or spend your day just content, or spend your day just content, or spend your day just switching apps, or even opening a dozen switching apps, or even opening a dozen switching apps, or even opening a dozen Chrome tabs, the important thing is not Chrome tabs, the important thing is not Chrome tabs, the important thing is not that Codex can write software. The that Codex can write software. The that Codex can write software. The important thing is that Codex can help important thing is that Codex can help important thing is that Codex can help you get all of that work done on the you get all of that work done on the you get all of that work done on the computer you already have and use. And computer you already have and use. And computer you already have and use. And yes, it's for Windows, too, now. So, I'm yes, it's for Windows, too, now. So, I'm yes, it's for Windows, too, now. So, I'm going to show you how I'm actually using going to show you how I'm actually using going to show you how I'm actually using it. I'm going to show you the Chief of it. I'm going to show you the Chief of it. I'm going to show you the Chief of Staff thread. I'm going to show you Staff thread. I'm going to show you Staff thread. I'm going to show you goals, multiple threads, computer use, goals, multiple threads, computer use, goals, multiple threads, computer use, plugins, skills, drafting several plugins, skills, drafting several plugins, skills, drafting several artifacts at once, using websites,

  3. artifacts at once, using websites, artifacts at once, using websites, checking work, and turning repeated checking work, and turning repeated checking work, and turning repeated corrections into workflows that I can corrections into workflows that I can corrections into workflows that I can reuse. And if you're already using reuse. And if you're already using reuse. And if you're already using Codex, I want I want to hear what I'm Codex, I want I want to hear what I'm Codex, I want I want to hear what I'm missing. I'm still learning this in missing. I'm still learning this in missing. I'm still learning this in public with you. If something I show you public with you. If something I show you public with you. If something I show you helps, or if you have a better way to helps, or if you have a better way to helps, or if you have a better way to run it, stick it in the comments. Let's run it, stick it in the comments. Let's run it, stick it in the comments. Let's make this a learning thread. This is make this a learning thread. This is make this a learning thread. This is early enough that the real playbook is early enough that the real playbook is early enough that the real playbook is still being written by the people who still being written by the people who still being written by the people who push the tool hard. On May 20th, my push the tool hard. On May 20th, my push the tool hard. On May 20th, my local Codex log showed 510 local Codex log showed 510 local Codex log showed 510 million tokens in one day. And I know million tokens in one day. And I know million tokens in one day. And I know that that sounds completely insane. And that that sounds completely insane. And that that sounds completely insane. And this is under This is not all of my AI this is under This is not all of my AI this is under This is not all of my AI tokens, by the way. This is just under tokens, by the way. This is just under tokens, by the way. This is just under my Codex Max account. I'm not talking my Codex Max account. I'm not talking my Codex Max account. I'm not talking about a surprise billing story here. I'm about a surprise billing story here. I'm about a surprise billing story here. I'm not paying extra for this. The point is not paying extra for this. The point is not paying extra for this. The point is that the way I'm using my computer is that the way I'm using my computer is that the way I'm using my computer is changing completely. And I think we're changing completely. And I think we're changing completely. And I think we're sleeping on it, and I want to tell you sleeping on it, and I want to tell you sleeping on it, and I want to tell you about it. More of my computer stopped about it. More of my computer stopped about it. More of my computer stopped being app-by-app manual work and started being app-by-app manual work and started being app-by-app manual work and started running through agents. It is now at the running through agents. It is now at the running through agents. It is now at the point where most of the work I do on my point where most of the work I do on my point where most of the work I do on my computer is through agents and Codex.

  4. computer is through agents and Codex. computer is through agents and Codex. It's not through apps directly. And when It's not through apps directly. And when It's not through apps directly. And when I go to apps, I feel like it's a hassle, I go to apps, I feel like it's a hassle, I go to apps, I feel like it's a hassle, right? My files, my browser sessions, my right? My files, my browser sessions, my right? My files, my browser sessions, my documents, my code, my terminal output, documents, my code, my terminal output, documents, my code, my terminal output, all of it is getting routed through all of it is getting routed through all of it is getting routed through Codex. And the number of tokens is not Codex. And the number of tokens is not Codex. And the number of tokens is not the point. Don't wake up and say, "Well, the point. Don't wake up and say, "Well, the point. Don't wake up and say, "Well, Nate said burn half a billion tokens." Nate said burn half a billion tokens." Nate said burn half a billion tokens." That would be a dumb target. The number That would be a dumb target. The number That would be a dumb target. The number matters because it shows that the matters because it shows that the matters because it shows that the computer itself is changing. We have computer itself is changing. We have computer itself is changing. We have been computing for decades using bits been computing for decades using bits been computing for decades using bits and bytes, and now we're moving to and bytes, and now we're moving to and bytes, and now we're moving to tokens. And this is the biggest shift in tokens. And this is the biggest shift in tokens. And this is the biggest shift in that, and I can prove it. I mapped my that, and I can prove it. I mapped my that, and I can prove it. I mapped my token burn back over a year. It is very token burn back over a year. It is very token burn back over a year. It is very clear, behaviorally, that the biggest clear, behaviorally, that the biggest clear, behaviorally, that the biggest shift in token burn has been over the shift in token burn has been over the shift in token burn has been over the last month or so as computer use plus last month or so as computer use plus last month or so as computer use plus 5.5 in Codex have unlocked a huge amount 5.5 in Codex have unlocked a huge amount 5.5 in Codex have unlocked a huge amount of my workflows at once. So, when I talk of my workflows at once. So, when I talk of my workflows at once. So, when I talk about the token burn, I'm not saying, about the token burn, I'm not saying, about the token burn, I'm not saying, "Look at this giant number." Half a "Look at this giant number." Half a "Look at this giant number." Half a billion tokens, 800 million tokens, billion tokens, 800 million tokens, billion tokens, 800 million tokens, whatever it is. It sounds crazy. If that whatever it is. It sounds crazy. If that whatever it is. It sounds crazy. If that only meant I was typing more prompts, it only meant I was typing more prompts, it only meant I was typing more prompts, it would be really embarrassing. But that's would be really embarrassing. But that's would be really embarrassing. But that's not what's happening here. The number not what's happening here. The number not what's happening here. The number went up because the unit of work went up because the unit of work went up because the unit of work fundamentally changed in scale. I fundamentally changed in scale. I fundamentally changed in scale. I stopped asking AI only for answers, and stopped asking AI only for answers, and stopped asking AI only for answers, and I started asking Codex to carry more of I started asking Codex to carry more of I started asking Codex to carry more of the job. Go find the source files, go the job. Go find the source files, go the job. Go find the source files, go read the transcript, go make the read the transcript, go make the read the transcript, go make the artifact, go render the document, go artifact, go render the document, go artifact, go render the document, go check the package, go inspect the check the package, go inspect the check the package, go inspect the browser, go keep working till the goal browser, go keep working till the goal browser, go keep working till the goal gets done. And so, the chart reflects gets done. And so, the chart reflects gets done. And so, the chart reflects that. So, when I say Codex has helped me that. So, when I say Codex has helped me that. So, when I say Codex has helped me 10x parts of my workflow, I don't just 10x parts of my workflow, I don't just 10x parts of my workflow, I don't just mean I became 10x smarter. I mean the mean I became 10x smarter. I mean the mean I became 10x smarter. I mean the size of the job I'm willing to hand to

  5. size of the job I'm willing to hand to size of the job I'm willing to hand to the machine changed. So, the chart isn't the machine changed. So, the chart isn't the machine changed. So, the chart isn't a scoreboard, it's not there to sort of a scoreboard, it's not there to sort of a scoreboard, it's not there to sort of make a vanity metric out of. It's just a make a vanity metric out of. It's just a make a vanity metric out of. It's just a receipt that reflects the way work has receipt that reflects the way work has receipt that reflects the way work has changed. So, the first piece here, what changed. So, the first piece here, what changed. So, the first piece here, what is the compute model? What is changing? is the compute model? What is changing? is the compute model? What is changing? For most of our lives, computers have For most of our lives, computers have For most of our lives, computers have been application-first, been application-first, been application-first, and that was considered a big deal. I and that was considered a big deal. I and that was considered a big deal. I remember back when it was DOS, and the remember back when it was DOS, and the remember back when it was DOS, and the app was a huge revolution computing, app was a huge revolution computing, app was a huge revolution computing, right? Because the app was a unit of right? Because the app was a unit of right? Because the app was a unit of work. And And I could write a document work. And And I could write a document work. And And I could write a document without writing code in the 1990s when without writing code in the 1990s when without writing code in the 1990s when documents became a thing. I I I could documents became a thing. I I I could documents became a thing. I I I could actually open a browser. I remember actually open a browser. I remember actually open a browser. I remember Netscape Navigator. I could open a Netscape Navigator. I could open a Netscape Navigator. I could open a spreadsheet and do the work and that was spreadsheet and do the work and that was spreadsheet and do the work and that was a huge productivity improvement. The a huge productivity improvement. The a huge productivity improvement. The human moved between the apps. The human human moved between the apps. The human human moved between the apps. The human remembered why each app was open. The remembered why each app was open. The remembered why each app was open. The the whole computing experience was built the whole computing experience was built the whole computing experience was built around the human first. I made a Tik Tok around the human first. I made a Tik Tok around the human first. I made a Tik Tok recently where I pointed out that my recently where I pointed out that my recently where I pointed out that my computer feels like it belongs to Codex computer feels like it belongs to Codex computer feels like it belongs to Codex as much as to me now because sometimes I as much as to me now because sometimes I as much as to me now because sometimes I can't use it because it's burning can't use it because it's burning can't use it because it's burning literally 100 million tokens an hour and literally 100 million tokens an hour and literally 100 million tokens an hour and you can hear it hissing in the you can hear it hissing in the you can hear it hissing in the background. It's burning tokens while I background. It's burning tokens while I background. It's burning tokens while I record this and I can't use it because record this and I can't use it because record this and I can't use it because it's literally at max memory capacity it's literally at max memory capacity it's literally at max memory capacity but I don't mind that because it's doing but I don't mind that because it's doing but I don't mind that because it's doing 10 things at once for me and I can't do 10 things at once for me and I can't do 10 things at once for me and I can't do 10 things at once. I just can give out 10 things at once. I just can give out 10 things at once. I just can give out assignments and then I go take a walk assignments and then I go take a walk assignments and then I go take a walk and I touch grass and I come back and and I touch grass and I come back and and I touch grass and I come back and I've got 10 things done. So we are I've got 10 things done. So we are I've got 10 things done. So we are building the computing paradigm building the computing paradigm building the computing paradigm differently now. It's the first change differently now. It's the first change differently now. It's the first change in the computing paradigm in like 40 in the computing paradigm in like 40 in the computing paradigm in like 40 years. We're moving from a world where

  6. years. We're moving from a world where years. We're moving from a world where humans were the center of the computing humans were the center of the computing humans were the center of the computing paradigm to where humans sit above the paradigm to where humans sit above the paradigm to where humans sit above the computing paradigm and we delegate to computing paradigm and we delegate to computing paradigm and we delegate to agents who run the compute for us. So agents who run the compute for us. So agents who run the compute for us. So Codex is a way into the future. I'm not Codex is a way into the future. I'm not Codex is a way into the future. I'm not saying Codex is the only answer that saying Codex is the only answer that saying Codex is the only answer that will ever get here. I just want to will ever get here. I just want to will ever get here. I just want to underline that. I am not saying underline that. I am not saying underline that. I am not saying Anthropic won't get here. I know that Anthropic won't get here. I know that Anthropic won't get here. I know that they will. Primitives like files and they will. Primitives like files and they will. Primitives like files and source notes and and templates and source notes and and templates and source notes and and templates and applications themselves, they're all applications themselves, they're all applications themselves, they're all underneath Codex. Codex can drive all of underneath Codex. Codex can drive all of underneath Codex. Codex can drive all of them with agents. You essentially have a them with agents. You essentially have a them with agents. You essentially have a state machine in Codex which is a fancy state machine in Codex which is a fancy state machine in Codex which is a fancy way of saying you have a agent in a loop way of saying you have a agent in a loop way of saying you have a agent in a loop that remembers what it's doing in Codex that remembers what it's doing in Codex that remembers what it's doing in Codex that can work the whole computer. that can work the whole computer. that can work the whole computer. Tokens are the cost of letting the agent Tokens are the cost of letting the agent Tokens are the cost of letting the agent compute for you and the more of your compute for you and the more of your compute for you and the more of your work that runs through agents, the more work that runs through agents, the more work that runs through agents, the more your computer activity becomes token your computer activity becomes token your computer activity becomes token activity. And so that is the simplest activity. And so that is the simplest activity. And so that is the simplest answer for how I get to a half a billion answer for how I get to a half a billion answer for how I get to a half a billion tokens a day. And by the way, if you're tokens a day. And by the way, if you're tokens a day. And by the way, if you're like, oh well, that was an anomaly. No, like, oh well, that was an anomaly. No, like, oh well, that was an anomaly. No, it's not an anomaly. I'm easily doing it's not an anomaly. I'm easily doing it's not an anomaly. I'm easily doing 300, 400, 500 million tokens a day these 300, 400, 500 million tokens a day these 300, 400, 500 million tokens a day these days. And I don't even try that hard.

  7. days. And I don't even try that hard. days. And I don't even try that hard. And I feel like I could do more if I And I feel like I could do more if I And I feel like I could do more if I wanted to, but the point is not to burn wanted to, but the point is not to burn wanted to, but the point is not to burn tokens. The point isn't to be wasteful. tokens. The point isn't to be wasteful. tokens. The point isn't to be wasteful. The point is to make an active layer The point is to make an active layer The point is to make an active layer between your intent and the machine, so between your intent and the machine, so between your intent and the machine, so the active layer can start to scale for the active layer can start to scale for the active layer can start to scale for you. The intelligence can scale for you. you. The intelligence can scale for you. you. The intelligence can scale for you. The first thing that made Codex click The first thing that made Codex click The first thing that made Codex click for me was this. I stopped treating for me was this. I stopped treating for me was this. I stopped treating every thread like a random chat. Most every thread like a random chat. Most every thread like a random chat. Most people use AI like a pile of separate people use AI like a pile of separate people use AI like a pile of separate conversations. One chat for a draft, one conversations. One chat for a draft, one conversations. One chat for a draft, one chat for a bug, one chat for a note, one chat for a bug, one chat for a note, one chat for a bug, one chat for a note, one chat for a random question. And the chat for a random question. And the chat for a random question. And the problem is that the human becomes the problem is that the human becomes the problem is that the human becomes the router. You have to remember where router. You have to remember where router. You have to remember where everything is. You have to remember what everything is. You have to remember what everything is. You have to remember what matters. You have to remember what the matters. You have to remember what the matters. You have to remember what the next move was. You remember what version next move was. You remember what version next move was. You remember what version was current. You remember what standard was current. You remember what standard was current. You remember what standard the work is supposed to meet. That does the work is supposed to meet. That does the work is supposed to meet. That does not scale very well, because our brains not scale very well, because our brains not scale very well, because our brains get tired. The better pattern is to get tired. The better pattern is to get tired. The better pattern is to create one thread that stays pointed at create one thread that stays pointed at create one thread that stays pointed at the work. It knows the goal. It knows the work. It knows the goal. It knows the work. It knows the goal. It knows the folders. It knows the current the folders. It knows the current the folders. It knows the current artifacts. It knows the standard. And artifacts. It knows the standard. And artifacts. It knows the standard. And then it can help you spin out smaller then it can help you spin out smaller then it can help you spin out smaller jobs without making you re-explain the jobs without making you re-explain the jobs without making you re-explain the entire project every time. And that is entire project every time. And that is entire project every time. And that is what I mean by a chief of staff thread.

  8. what I mean by a chief of staff thread. what I mean by a chief of staff thread. It's not magic memory. You still have to It's not magic memory. You still have to It's not magic memory. You still have to give it sources. You still have to give it sources. You still have to give it sources. You still have to correct it. You still have to make it correct it. You still have to make it correct it. You still have to make it show receipts. But once you start using show receipts. But once you start using show receipts. But once you start using Codex this way, it stops feeling like a Codex this way, it stops feeling like a Codex this way, it stops feeling like a chatbot and starts feeling like a home chatbot and starts feeling like a home chatbot and starts feeling like a home base for the work. The next thing that base for the work. The next thing that base for the work. The next thing that changed my usage was getting more changed my usage was getting more changed my usage was getting more serious about goals and threads. And serious about goals and threads. And serious about goals and threads. And this sounds really small until you use this sounds really small until you use this sounds really small until you use it on a real project. If I ask a normal it on a real project. If I ask a normal it on a real project. If I ask a normal chatbot for help, it will often stop chatbot for help, it will often stop chatbot for help, it will often stop when it has produced something that when it has produced something that when it has produced something that looks like an answer. Codex becomes much looks like an answer. Codex becomes much looks like an answer. Codex becomes much more useful when I give it the actual more useful when I give it the actual more useful when I give it the actual objective. Not help me with this, but objective. Not help me with this, but objective. Not help me with this, but more like read these sources, produce more like read these sources, produce more like read these sources, produce this artifact, check it against the this artifact, check it against the this artifact, check it against the standard, and do not stop at the first standard, and do not stop at the first standard, and do not stop at the first plausible draft. Keep going. That plausible draft. Keep going. That plausible draft. Keep going. That changes the relationship. Now, I am not changes the relationship. Now, I am not changes the relationship. Now, I am not asking for a response. I'm just asking for a response. I'm just asking for a response. I'm just assigning a job out. A thread is not one assigning a job out. A thread is not one assigning a job out. A thread is not one agent doing every step by itself. Codex agent doing every step by itself. Codex agent doing every step by itself. Codex can still use sub agents for smaller can still use sub agents for smaller can still use sub agents for smaller tasks, but the useful pattern looks more tasks, but the useful pattern looks more tasks, but the useful pattern looks more It looks bigger, right? A thread is the It looks bigger, right? A thread is the It looks bigger, right? A thread is the run that owns the job. And a sub agent run that owns the job. And a sub agent run that owns the job. And a sub agent is just a smaller helper inside that is just a smaller helper inside that is just a smaller helper inside that job. You use it for a narrow piece of job. You use it for a narrow piece of job. You use it for a narrow piece of work so the main thread does not get work so the main thread does not get work so the main thread does not get buried in noise. So, one thread can plan buried in noise. So, one thread can plan buried in noise. So, one thread can plan the goal and that planning thread can the goal and that planning thread can the goal and that planning thread can use sub agents for discovery and source use sub agents for discovery and source use sub agents for discovery and source checking and scouting and reading checking and scouting and reading checking and scouting and reading through messy material. And then when through messy material. And then when through messy material. And then when the goal is cleaner, I can send that the goal is cleaner, I can send that the goal is cleaner, I can send that goal to another thread to execute. The goal to another thread to execute. The goal to another thread to execute. The execution thread can own the execution thread can own the execution thread can own the deliverable, but it can still use sub deliverable, but it can still use sub deliverable, but it can still use sub agents inside the job. One sub agent agents inside the job. One sub agent agents inside the job. One sub agent might scout a site, another might check might scout a site, another might check might scout a site, another might check sources, another might inspect output, sources, another might inspect output, sources, another might inspect output, another might summarize a noisy folder.

  9. another might summarize a noisy folder. another might summarize a noisy folder. The thread owns the job as a whole. The The thread owns the job as a whole. The The thread owns the job as a whole. The sub agents just handle contained pieces sub agents just handle contained pieces sub agents just handle contained pieces of the job. Once you understand that as of the job. Once you understand that as of the job. Once you understand that as a concept, thread mode stops looking a concept, thread mode stops looking a concept, thread mode stops looking like a bunch of chats and starts looking like a bunch of chats and starts looking like a bunch of chats and starts looking like a way to separate planning and like a way to separate planning and like a way to separate planning and execution and checking the work. And the execution and checking the work. And the execution and checking the work. And the nice thing is with the Chief of Staff nice thing is with the Chief of Staff nice thing is with the Chief of Staff pattern, you can get a lot of this pattern, you can get a lot of this pattern, you can get a lot of this managed just by talking to your Chief of managed just by talking to your Chief of managed just by talking to your Chief of Staff. You don't have to assign out Staff. You don't have to assign out Staff. You don't have to assign out these work to individual agents. That's these work to individual agents. That's these work to individual agents. That's not how it works anymore. The thing that not how it works anymore. The thing that not how it works anymore. The thing that makes Codex powerful is not one magic makes Codex powerful is not one magic makes Codex powerful is not one magic prompt. It is the setup around the prompt. It is the setup around the prompt. It is the setup around the model. Computer uses literal. It can see model. Computer uses literal. It can see model. Computer uses literal. It can see a screen, it can click, it can type, it a screen, it can click, it can type, it a screen, it can click, it can type, it can use an app. Tools that it call real can use an app. Tools that it call real can use an app. Tools that it call real systems, plugins and connectors let it systems, plugins and connectors let it systems, plugins and connectors let it reach the places where your work already reach the places where your work already reach the places where your work already lives. Skills let you teach it a lives. Skills let you teach it a lives. Skills let you teach it a reusable way to do a job instead of reusable way to do a job instead of reusable way to do a job instead of explaining the same process every single explaining the same process every single explaining the same process every single time. And that last part matters so time. And that last part matters so time. And that last part matters so much. If I correct Codex once, that's much. If I correct Codex once, that's much. If I correct Codex once, that's just a chat that I had. If I turn the just a chat that I had. If I turn the just a chat that I had. If I turn the correction into a skill, into a correction into a skill, into a correction into a skill, into a checklist, into a reusable instruction, checklist, into a reusable instruction, checklist, into a reusable instruction, the work begins to compound. And this is the work begins to compound. And this is the work begins to compound. And this is where that code label becomes really where that code label becomes really where that code label becomes really misleading. Developers understand this misleading. Developers understand this misleading. Developers understand this first because they already live in a first because they already live in a first because they already live in a world where there's tools and files and world where there's tools and files and world where there's tools and files and tests and workflows. That same pattern tests and workflows. That same pattern tests and workflows. That same pattern of work applies now to documents and of work applies now to documents and of work applies now to documents and reports and research and invoices and reports and research and invoices and reports and research and invoices and dashboards and meeting prep and family dashboards and meeting prep and family dashboards and meeting prep and family logistics and customer support. All of logistics and customer support. All of logistics and customer support. All of it is using code patterns to get better it is using code patterns to get better it is using code patterns to get better with Codex. If the work lives on your with Codex. If the work lives on your with Codex. If the work lives on your computer, Codex can start to help you computer, Codex can start to help you computer, Codex can start to help you get that work done using those patterns

  10. get that work done using those patterns get that work done using those patterns it learned from code and you don't have it learned from code and you don't have it learned from code and you don't have to know code to do it. The sample Codex to know code to do it. The sample Codex to know code to do it. The sample Codex workflow that I think is big enough that workflow that I think is big enough that workflow that I think is big enough that I want to get into with you today is a I want to get into with you today is a I want to get into with you today is a workflow that essentially provides you a workflow that essentially provides you a workflow that essentially provides you a heads-up dashboard for all of your work heads-up dashboard for all of your work heads-up dashboard for all of your work day. Like imagine a world where instead day. Like imagine a world where instead day. Like imagine a world where instead of buying some SAS that, you know, has a of buying some SAS that, you know, has a of buying some SAS that, you know, has a defined amount of work that says you defined amount of work that says you defined amount of work that says you have to plug into your Slack and you have to plug into your Slack and you have to plug into your Slack and you have to plug into your email and this have to plug into your email and this have to plug into your email and this and that and it doesn't produce and that and it doesn't produce and that and it doesn't produce everything. You can make an exact everything. You can make an exact everything. You can make an exact heads-up display that gives you live heads-up display that gives you live heads-up display that gives you live alerts of what matters in your workplace alerts of what matters in your workplace alerts of what matters in your workplace that's custom-tuned to your tools. You that's custom-tuned to your tools. You that's custom-tuned to your tools. You can do it now. It's not that hard. All can do it now. It's not that hard. All can do it now. It's not that hard. All you have to do is take the time to go you have to do is take the time to go you have to do is take the time to go into Codex and tell Codex one, all about into Codex and tell Codex one, all about into Codex and tell Codex one, all about the sources that you use to do work. So, the sources that you use to do work. So, the sources that you use to do work. So, the email, the Slack, the WhatsApp the email, the Slack, the WhatsApp the email, the Slack, the WhatsApp messages, the carrier pigeon messages, messages, the carrier pigeon messages, messages, the carrier pigeon messages, whatever it is that you use to do work. whatever it is that you use to do work. whatever it is that you use to do work. And then you say, "Those are all my And then you say, "Those are all my And then you say, "Those are all my sources." sources." sources." Two, "This is what matters to me. This Two, "This is what matters to me. This Two, "This is what matters to me. This is how I move the needle in my job." And is how I move the needle in my job." And is how I move the needle in my job." And then have a really honest discussion then have a really honest discussion then have a really honest discussion with Codex about that. And talk about with Codex about that. And talk about with Codex about that. And talk about how you refer to some of the sources, how you refer to some of the sources, how you refer to some of the sources, maybe all of the sources at different maybe all of the sources at different maybe all of the sources at different points. What is salient? What matters points. What is salient? What matters points. What is salient? What matters about the information in these sources?

  11. about the information in these sources? about the information in these sources? And then, next, you say, "Okay, I want And then, next, you say, "Okay, I want And then, next, you say, "Okay, I want you to design for me a dashboard that is you to design for me a dashboard that is you to design for me a dashboard that is live-updateable based on the sources you live-updateable based on the sources you live-updateable based on the sources you can pull from via computer use or maybe can pull from via computer use or maybe can pull from via computer use or maybe via MCP server." Some of them are via via MCP server." Some of them are via via MCP server." Some of them are via MCP server. Slack has an MCP server MCP server. Slack has an MCP server MCP server. Slack has an MCP server skill. Some they'll use computer use in skill. Some they'll use computer use in skill. Some they'll use computer use in the browser, and that's fine. And say, the browser, and that's fine. And say, the browser, and that's fine. And say, "Design me a dashboard just for me that "Design me a dashboard just for me that "Design me a dashboard just for me that is my personal heads-up display for is my personal heads-up display for is my personal heads-up display for work." So, I can look at it, and I can work." So, I can look at it, and I can work." So, I can look at it, and I can say at any given point, I know what say at any given point, I know what say at any given point, I know what matters in Slack, I know what matters in matters in Slack, I know what matters in matters in Slack, I know what matters in email, I know what I have to do, I know email, I know what I have to do, I know email, I know what I have to do, I know what my prioritized list is, and I can what my prioritized list is, and I can what my prioritized list is, and I can go and get it. And it's not something go and get it. And it's not something go and get it. And it's not something that someone built with a seed round and that someone built with a seed round and that someone built with a seed round and a bunch of VC money. You built it just a bunch of VC money. You built it just a bunch of VC money. You built it just for you for you for you in a way that works for you with your in a way that works for you with your in a way that works for you with your data. And Codex can do that today. And data. And Codex can do that today. And data. And Codex can do that today. And yes, I have the complete readout on that yes, I have the complete readout on that yes, I have the complete readout on that on Substack. You can actually see on Substack. You can actually see on Substack. You can actually see examples of that over my shoulder here examples of that over my shoulder here examples of that over my shoulder here as I'm talking because we went through as I'm talking because we went through as I'm talking because we went through and we built it. It's really fun. and we built it. It's really fun. and we built it. It's really fun. It helps you to understand what a big It helps you to understand what a big It helps you to understand what a big loop can be. It helps you to understand loop can be. It helps you to understand loop can be. It helps you to understand automations because you can actually automations because you can actually automations because you can actually start to build an automation that start to build an automation that start to build an automation that updates this every 15 minutes, every updates this every 15 minutes, every updates this every 15 minutes, every half hour, it's kind of up to you. It half hour, it's kind of up to you. It half hour, it's kind of up to you. It will check through all those data will check through all those data will check through all those data sources. It will run the saliency sources. It will run the saliency sources. It will run the saliency analysis to see what really matters. It analysis to see what really matters. It analysis to see what really matters. It will come back and say, "This is what I will come back and say, "This is what I will come back and say, "This is what I think matters. This is how I rejig the think matters. This is how I rejig the think matters. This is how I rejig the priority, and this is what I want to priority, and this is what I want to priority, and this is what I want to emphasize as really important for work."

  12. emphasize as really important for work." emphasize as really important for work." It becomes your headquarters for work It becomes your headquarters for work It becomes your headquarters for work every day, and you custom built it. every day, and you custom built it. every day, and you custom built it. Isn't that cool? I think that's really Isn't that cool? I think that's really Isn't that cool? I think that's really cool. That's an example of an open loop cool. That's an example of an open loop cool. That's an example of an open loop you can build. That has never been you can build. That has never been you can build. That has never been something that we could make before. something that we could make before. something that we could make before. That wasn't something we could make even That wasn't something we could make even That wasn't something we could make even two or three months ago because as cool two or three months ago because as cool two or three months ago because as cool as the models were and as much as we're as the models were and as much as we're as the models were and as much as we're into the long-running agentic into the long-running agentic into the long-running agentic revolution, we didn't have the computer revolution, we didn't have the computer revolution, we didn't have the computer availability, and we did not have the availability, and we did not have the availability, and we did not have the computer use availability to get that computer use availability to get that computer use availability to get that unlocked. And so, I picked this because unlocked. And so, I picked this because unlocked. And so, I picked this because it shows something that only Codex could it shows something that only Codex could it shows something that only Codex could do today. I'm sure other models will do today. I'm sure other models will do today. I'm sure other models will come along and do it soon. And Codex come along and do it soon. And Codex come along and do it soon. And Codex will go and do that work, especially if will go and do that work, especially if will go and do that work, especially if you use the set of gold feature. The set you use the set of gold feature. The set you use the set of gold feature. The set of gold feature is really handy because of gold feature is really handy because of gold feature is really handy because it basically zeros in Codex on the gold it basically zeros in Codex on the gold it basically zeros in Codex on the gold you define, and it will just run through you define, and it will just run through you define, and it will just run through walls until it gets to that gets to that walls until it gets to that gets to that walls until it gets to that gets to that done state. And I love that because I done state. And I love that because I done state. And I love that because I want to have agents that don't stop want to have agents that don't stop want to have agents that don't stop early. Remember when we talked about the early. Remember when we talked about the early. Remember when we talked about the Ralph Wiggum loop and it was like Ralph Wiggum loop and it was like Ralph Wiggum loop and it was like January and February and we were all January and February and we were all January and February and we were all excited because Claude was stopping on excited because Claude was stopping on excited because Claude was stopping on agent loops, but Ralph made Claude keep agent loops, but Ralph made Claude keep agent loops, but Ralph made Claude keep going. You don't need to do that with going. You don't need to do that with going. You don't need to do that with Codex. You set a goal and it just keeps Codex. You set a goal and it just keeps Codex. You set a goal and it just keeps going. It's great. If you're new to going. It's great. If you're new to going. It's great. If you're new to Codex, do not begin by trying to Codex, do not begin by trying to Codex, do not begin by trying to automate your whole life. Just pick one automate your whole life. Just pick one automate your whole life. Just pick one loop that is annoying and valuable.

  13. loop that is annoying and valuable. loop that is annoying and valuable. Something like turn this transcript into Something like turn this transcript into Something like turn this transcript into a brief, organize this source folder, a brief, organize this source folder, a brief, organize this source folder, build me a simple dashboard to track my build me a simple dashboard to track my build me a simple dashboard to track my inbound email subscriptions, whatever it inbound email subscriptions, whatever it inbound email subscriptions, whatever it is. Prepare my day from calendar, email, is. Prepare my day from calendar, email, is. Prepare my day from calendar, email, and Slack. Draft three versions of this and Slack. Draft three versions of this and Slack. Draft three versions of this document and explain the difference. document and explain the difference. document and explain the difference. Check this package, tell me what's Check this package, tell me what's Check this package, tell me what's missing. I can give you a bunch more, missing. I can give you a bunch more, missing. I can give you a bunch more, right? Then give Codex five things. Give right? Then give Codex five things. Give right? Then give Codex five things. Give it a goal, give it sources, give it a it a goal, give it sources, give it a it a goal, give it sources, give it a standard, give it a permission boundary, standard, give it a permission boundary, standard, give it a permission boundary, and give it the proof that it's done. and give it the proof that it's done. and give it the proof that it's done. That's the most basic way to set up a That's the most basic way to set up a That's the most basic way to set up a loop. It's not a fancy prompt. It's not loop. It's not a fancy prompt. It's not loop. It's not a fancy prompt. It's not a hack. You're just setting a loop up. A a hack. You're just setting a loop up. A a hack. You're just setting a loop up. A real assignment with real sources and a real assignment with real sources and a real assignment with real sources and a way to check the results. And if you're way to check the results. And if you're way to check the results. And if you're already using Codex, this is the level already using Codex, this is the level already using Codex, this is the level you go to next. Look for the loops you you go to next. Look for the loops you you go to next. Look for the loops you keep repeating. Every time you find keep repeating. Every time you find keep repeating. Every time you find yourself giving the same correction or yourself giving the same correction or yourself giving the same correction or writing the same setup note or asking writing the same setup note or asking writing the same setup note or asking for the same kind of review or checking for the same kind of review or checking for the same kind of review or checking the same kind of output, then ask the same kind of output, then ask the same kind of output, then ask whether that should become a skill. Ask whether that should become a skill. Ask whether that should become a skill. Ask whether it should become a standing whether it should become a standing whether it should become a standing workflow, an automation. Ask whether it workflow, an automation. Ask whether it workflow, an automation. Ask whether it should become a memory for Codex. And should become a memory for Codex. And should become a memory for Codex. And that is when it stops being one-off help that is when it stops being one-off help that is when it stops being one-off help and starts becoming something where and starts becoming something where and starts becoming something where Codex is evolving with you to accomplish Codex is evolving with you to accomplish Codex is evolving with you to accomplish the work you want done through a series the work you want done through a series the work you want done through a series of automated loops. When I say Codex is of automated loops. When I say Codex is of automated loops. When I say Codex is blowing my mind, I do not mean I want blowing my mind, I do not mean I want blowing my mind, I do not mean I want agents running around my life without agents running around my life without agents running around my life without rules. I mean the opposite. The more rules. I mean the opposite. The more rules. I mean the opposite. The more powerful the tool gets, the more powerful the tool gets, the more powerful the tool gets, the more important the boundaries get. Don't important the boundaries get. Don't important the boundaries get. Don't paste API keys or passwords into the paste API keys or passwords into the paste API keys or passwords into the chat, right? Learn to use a .env file.

  14. chat, right? Learn to use a .env file. chat, right? Learn to use a .env file. It's not hard and it keeps secrets out It's not hard and it keeps secrets out It's not hard and it keeps secrets out of the prompt. That's just one example, of the prompt. That's just one example, of the prompt. That's just one example, right? Or don't give it right access right? Or don't give it right access right? Or don't give it right access just because read access would be just because read access would be just because read access would be useful. Don't let it send and publish useful. Don't let it send and publish useful. Don't let it send and publish and delete or spend money unless you and delete or spend money unless you and delete or spend money unless you really understand the workflow. And when really understand the workflow. And when really understand the workflow. And when it produces something important, make it it produces something important, make it it produces something important, make it show the receipts. This is why Codex is show the receipts. This is why Codex is show the receipts. This is why Codex is interesting to me. It's not just that interesting to me. It's not just that interesting to me. It's not just that it's powerful, it's that it's very easy it's powerful, it's that it's very easy it's powerful, it's that it's very easy to inspect the work. It will show you to inspect the work. It will show you to inspect the work. It will show you the files and the logs and the tests and the files and the logs and the tests and the files and the logs and the tests and the renders and the command output and the renders and the command output and the renders and the command output and you can build a habit of getting proof you can build a habit of getting proof you can build a habit of getting proof from your agent around it. And that's from your agent around it. And that's from your agent around it. And that's what keeps this from turning into a what keeps this from turning into a what keeps this from turning into a bunch of hype and wishful thinking. The bunch of hype and wishful thinking. The bunch of hype and wishful thinking. The tool matters because it lets you hand tool matters because it lets you hand tool matters because it lets you hand off more work responsibly. And the skill off more work responsibly. And the skill off more work responsibly. And the skill is learning to do that without getting is learning to do that without getting is learning to do that without getting sloppy. sloppy. sloppy. The reason I wanted to make this video The reason I wanted to make this video The reason I wanted to make this video is simple. Codex is changing how I work is simple. Codex is changing how I work is simple. Codex is changing how I work and I don't think the story is only for and I don't think the story is only for and I don't think the story is only for developers. Look, I'm not asking you to developers. Look, I'm not asking you to developers. Look, I'm not asking you to pick a side in a platform fight between pick a side in a platform fight between pick a side in a platform fight between OpenAI and Anthropic. I'm saying just OpenAI and Anthropic. I'm saying just OpenAI and Anthropic. I'm saying just pay attention to what Codex lets you pay attention to what Codex lets you pay attention to what Codex lets you practice and see if it's useful. If you practice and see if it's useful. If you practice and see if it's useful. If you do knowledge work, if you write, if you do knowledge work, if you write, if you do knowledge work, if you write, if you research, if you manage projects, if you research, if you manage projects, if you research, if you manage projects, if you build documents, if you run support, build documents, if you run support, build documents, if you run support, when you plan your life, or when you when you plan your life, or when you when you plan your life, or when you spend your day moving between apps, this spend your day moving between apps, this spend your day moving between apps, this app matters to you. This app will make a app matters to you. This app will make a app matters to you. This app will make a difference for you. Codex is one of the difference for you. Codex is one of the difference for you. Codex is one of the first tools that lets you practice a new first tools that lets you practice a new first tools that lets you practice a new kind of computer literacy, the computer kind of computer literacy, the computer kind of computer literacy, the computer literacy of the future. Not typing, not literacy of the future. Not typing, not literacy of the future. Not typing, not prompting, but handing work to agents prompting, but handing work to agents prompting, but handing work to agents that can truly use the computer and then that can truly use the computer and then that can truly use the computer and then learning how to check what came back.

  15. learning how to check what came back. learning how to check what came back. That's why I built the token dashboard. That's why I built the token dashboard. That's why I built the token dashboard. That's why I'm using this thing so much. That's why I'm using this thing so much. That's why I'm using this thing so much. That's why I wanted this to be a real That's why I wanted this to be a real That's why I wanted this to be a real deep dive instead of a quick reaction. deep dive instead of a quick reaction. deep dive instead of a quick reaction. If you want the checklist and the If you want the checklist and the If you want the checklist and the examples and the setup notes, I put the examples and the setup notes, I put the examples and the setup notes, I put the practical version of all of this to get practical version of all of this to get practical version of all of this to get started on the Substack. And there's an started on the Substack. And there's an started on the Substack. And there's an active community there that's already active community there that's already active community there that's already building with Codex that you can check building with Codex that you can check building with Codex that you can check into. We have a whole Slack, it's into. We have a whole Slack, it's into. We have a whole Slack, it's amazing. But I also want the comment amazing. But I also want the comment amazing. But I also want the comment section to be useful here. If you're section to be useful here. If you're section to be useful here. If you're using Codex, tell me how. If you have a using Codex, tell me how. If you have a using Codex, tell me how. If you have a better workflow, I want to see it. If better workflow, I want to see it. If better workflow, I want to see it. If one of these tricks helps, tell me which one of these tricks helps, tell me which one of these tricks helps, tell me which one. This is still early enough that one. This is still early enough that one. This is still early enough that people who use the tool hard are people who use the tool hard are people who use the tool hard are learning from each other in public, and learning from each other in public, and learning from each other in public, and I want you guys to be the cool kids. I want you guys to be the cool kids. I want you guys to be the cool kids. Show me you're the cool kids, and show Show me you're the cool kids, and show Show me you're the cool kids, and show me what you're building. This is why it me what you're building. This is why it me what you're building. This is why it feels exciting. This is This is a moment feels exciting. This is This is a moment feels exciting. This is This is a moment when computing is changing, and Codex is when computing is changing, and Codex is when computing is changing, and Codex is at the at the forefront of that. Codex at the at the forefront of that. Codex at the at the forefront of that. Codex is the tip of the spear on that. So, is the tip of the spear on that. So, is the tip of the spear on that. So, show me what you're building in the show me what you're building in the show me what you're building in the comments. I'll see you next time. I'm so comments. I'll see you next time. I'm so comments. I'll see you next time. I'm so excited to see what you're building with excited to see what you're building with excited to see what you're building with Codex.

Summary

The main theme is the revolutionary potential of Codex as an AI agent that can interact with and manage a user's digital environment. Key subjects include AI, large language models, and the integration of AI into personal computing workflows, extending beyond just coding. The practical takeaway is that Codex enables users to hand complex tasks and workflows to an AI agent using plain English, fundamentally changing how we interact with our computers.

View original episode ↗