Making opinionated AI tooling decisions with Nimbalyst's Greg Hinkle

Yeah, I I've had some moments of Yeah, I I've had some moments of absolute pure delight in the sort of absolute pure delight in the sort of absolute pure delight in the sort of interactive voice. interactive voice. interactive voice. You know, it's it's still in testing, You know, it's it's still in testing, You know, it's it's still in testing, but but but it I basically have a voice agent that it I basically have a voice agent that it I basically have a voice agent that can control a coding agent. Um I can can control a coding agent. Um I can can control a coding agent. Um I can control the whole set of coding agents control the whole set of coding agents control the whole set of coding agents and it's I'm talking to it and it's and it's I'm talking to it and it's and it's I'm talking to it and it's firing off prompts and it's just a much firing off prompts and it's just a much firing off prompts and it's just a much higher rate of speed and it can wake up higher rate of speed and it can wake up higher rate of speed and it can wake up and and notify me and I can be walking and and notify me and I can be walking and and notify me and I can be walking around, you know, the yard having a around, you know, the yard having a around, you know, the yard having a conversation controlling multiple agents conversation controlling multiple agents conversation controlling multiple agents all through my my headphones. It's all through my my headphones. It's all through my my headphones. It's pretty It's pretty cool. Yeah, it is pretty It's pretty cool. Yeah, it is pretty It's pretty cool. Yeah, it is cool. And I think also it's worth noting cool. And I think also it's worth noting cool. And I think also it's worth noting that people oversimplify and they think that people oversimplify and they think that people oversimplify and they think it's I talk to it, it talks to me. But it's I talk to it, it talks to me. But it's I talk to it, it talks to me. But the trick is you can talk faster than the trick is you can talk faster than the trick is you can talk faster than you can type and you can read faster you can type and you can read faster you can type and you can read faster than it can talk. than it can talk. than it can talk. That's right. Hey friends, I'm Scott That's right. Hey friends, I'm Scott That's right. Hey friends, I'm Scott Hanselman and this is another episode of Hanselman and this is another episode of Hanselman and this is another episode of Hanselminutes. Today I'm chatting with Hanselminutes. Today I'm chatting with Hanselminutes. Today I'm chatting with Greg Hinkle. He's a chief technology Greg Hinkle. He's a chief technology Greg Hinkle. He's a chief technology officer and co-founder at Nimble list. officer and co-founder at Nimble list. officer and co-founder at Nimble list. He was previously at Salesforce and was He was previously at Salesforce and was He was previously at Salesforce and was a manager of engineering at Red Hat. So a manager of engineering at Red Hat. So a manager of engineering at Red Hat. So you've been doing this for a minute, you've been doing this for a minute, you've been doing this for a minute, sir. How are you? I'm doing well. sir. How are you? I'm doing well. sir. How are you? I'm doing well. Thanks, Scott. How are you? I'm okay. Thanks, Scott. How are you? I'm okay. Thanks, Scott. How are you? I'm okay. You know, there's so much AI going on You know, there's so much AI going on You know, there's so much AI going on right now. People keep saying like why right now. People keep saying like why right now. People keep saying like why are you talking about it? And I realize are you talking about it? And I realize are you talking about it? And I realize that it's not about AI for me, it's that it's not about AI for me, it's that it's not about AI for me, it's about software engineering.

about software engineering. about software engineering. Of which AI is the tool that is kind of Of which AI is the tool that is kind of Of which AI is the tool that is kind of like blowing up software engineering. like blowing up software engineering. like blowing up software engineering. And if it was And if it was And if it was 20 years ago, I'd be talking about, you 20 years ago, I'd be talking about, you 20 years ago, I'd be talking about, you know, build servers and continuous know, build servers and continuous know, build servers and continuous integration and you know, Agile and TDD integration and you know, Agile and TDD integration and you know, Agile and TDD and things like that. But trying to, you and things like that. But trying to, you and things like that. But trying to, you know, figure out this moment that we're know, figure out this moment that we're know, figure out this moment that we're in and how to build software in and how to build software in and how to build software correctly and still value the craft is correctly and still value the craft is correctly and still value the craft is something that I'm really interested in. something that I'm really interested in. something that I'm really interested in. So that's why I wanted to talk about So that's why I wanted to talk about So that's why I wanted to talk about about Nimble list because it feels like about Nimble list because it feels like about Nimble list because it feels like you're trying to navigate this you're trying to navigate this you're trying to navigate this this space of multitasking. Multitasking this space of multitasking. Multitasking this space of multitasking. Multitasking seems to be seems to be seems to be the the skill the the skill the the skill and then expressing your taste, you and then expressing your taste, you and then expressing your taste, you know, expressing your your judgment when know, expressing your your judgment when know, expressing your your judgment when the AI generated pull requests and diffs the AI generated pull requests and diffs the AI generated pull requests and diffs and stuff comes in and Nimble list takes and stuff comes in and Nimble list takes and stuff comes in and Nimble list takes a very opinionated approach. a very opinionated approach. a very opinionated approach. Yes. Yeah, we're we're trying to Yes. Yeah, we're we're trying to Yes. Yeah, we're we're trying to you know, thread that needle of changing you know, thread that needle of changing you know, thread that needle of changing the way the experience is is is the way the experience is is is the way the experience is is is happening for a user happening for a user happening for a user by just giving them a different by just giving them a different by just giving them a different interface. Focusing on what the user interface. Focusing on what the user interface. Focusing on what the user needs to see as they're managing many needs to see as they're managing many needs to see as they're managing many agents doing many jobs. Uh so it's agents doing many jobs. Uh so it's agents doing many jobs. Uh so it's really about, you know, increasing the really about, you know, increasing the really about, you know, increasing the bandwidth for the user so that they can bandwidth for the user so that they can bandwidth for the user so that they can keep control of the chaos. Mhm. Yeah, keep control of the chaos. Mhm. Yeah, keep control of the chaos. Mhm. Yeah, the chaos is true. Like I was talking the chaos is true. Like I was talking the chaos is true. Like I was talking with Mark Russinovich, my buddy at work, with Mark Russinovich, my buddy at work, with Mark Russinovich, my buddy at work, about what's the right number of agents about what's the right number of agents about what's the right number of agents that I can manage comfortably. And he that I can manage comfortably. And he that I can manage comfortably. And he and I feel for us it's three to five.

and I feel for us it's three to five. and I feel for us it's three to five. But then I've got guys at work and gals But then I've got guys at work and gals But then I've got guys at work and gals at work that are doing 10, 20 things and at work that are doing 10, 20 things and at work that are doing 10, 20 things and they have squads of squads of agents and they have squads of squads of agents and they have squads of squads of agents and things like that. And I'm finding that things like that. And I'm finding that things like that. And I'm finding that the context switching is just too much, the context switching is just too much, the context switching is just too much, the cognitive load for me running all the cognitive load for me running all the cognitive load for me running all these basically terminal tabs. That's as these basically terminal tabs. That's as these basically terminal tabs. That's as far as I've gone is terminal tabs and far as I've gone is terminal tabs and far as I've gone is terminal tabs and it's hitting the wall pretty quickly. it's hitting the wall pretty quickly. it's hitting the wall pretty quickly. Yeah, that's exactly right. And we we Yeah, that's exactly right. And we we Yeah, that's exactly right. And we we have this opinion that have this opinion that have this opinion that keeping track of everything goes beyond keeping track of everything goes beyond keeping track of everything goes beyond just having tabs. Um tabs are just too just having tabs. Um tabs are just too just having tabs. Um tabs are just too short-lived and a lot of short-lived and a lot of short-lived and a lot of you know, it's funny it's sort of like a you know, it's funny it's sort of like a you know, it's funny it's sort of like a hurry up and wait where you come up with hurry up and wait where you come up with hurry up and wait where you come up with this great idea, but then you have to this great idea, but then you have to this great idea, but then you have to wait for the agent to go do the work or wait for the agent to go do the work or wait for the agent to go do the work or go do the research. And so you're not go do the research. And so you're not go do the research. And so you're not getting the best bandwidth if you're not getting the best bandwidth if you're not getting the best bandwidth if you're not multitasking. But you it really multitasking. But you it really multitasking. But you it really you have to carefully multitask. You you have to carefully multitask. You you have to carefully multitask. You have to do prep work, have the agents go have to do prep work, have the agents go have to do prep work, have the agents go and do research and then stop so that and do research and then stop so that and do research and then stop so that you can come back when you have time to you can come back when you have time to you can come back when you have time to work on that particular task. Uh and work on that particular task. Uh and work on that particular task. Uh and that's what I find is the best way to that's what I find is the best way to that's what I find is the best way to improve the bandwidth.

improve the bandwidth. improve the bandwidth. Yeah, that's a great point. Increase the Yeah, that's a great point. Increase the Yeah, that's a great point. Increase the parallelization. Yeah, the throughput. parallelization. Yeah, the throughput. parallelization. Yeah, the throughput. The throughput for sure. It feels like, The throughput for sure. It feels like, The throughput for sure. It feels like, you know, like I've again I'm waxing you know, like I've again I'm waxing you know, like I've again I'm waxing philosophic back 20 years ago like it philosophic back 20 years ago like it philosophic back 20 years ago like it was waiting for the build. was waiting for the build. was waiting for the build. And now it's waiting for the agent to And now it's waiting for the agent to And now it's waiting for the agent to turn. So some people just kind of like turn. So some people just kind of like turn. So some people just kind of like sit there and cross your arms and wait sit there and cross your arms and wait sit there and cross your arms and wait for the thing to turn. But at the same for the thing to turn. But at the same for the thing to turn. But at the same time I don't want to multitask all the time I don't want to multitask all the time I don't want to multitask all the way to a drastically different thing. I way to a drastically different thing. I way to a drastically different thing. I want to get in the flow. And Mark and I want to get in the flow. And Mark and I want to get in the flow. And Mark and I were trying to figure out were trying to figure out were trying to figure out do we have we lost the flow and what do we have we lost the flow and what do we have we lost the flow and what have we done to our tooling that is have we done to our tooling that is have we done to our tooling that is preventing us from getting into that preventing us from getting into that preventing us from getting into that that that flow state, that hyperfocus that that flow state, that hyperfocus that that flow state, that hyperfocus state. And I wonder state. And I wonder state. And I wonder how much you've been thinking about how much you've been thinking about how much you've been thinking about you want to multitask, but it shouldn't you want to multitask, but it shouldn't you want to multitask, but it shouldn't feel like multitasking, if that makes feel like multitasking, if that makes feel like multitasking, if that makes sense. It shouldn't feel like you're sense. It shouldn't feel like you're sense. It shouldn't feel like you're ripped out of one task and thrown into ripped out of one task and thrown into ripped out of one task and thrown into another. another. another. Exactly. It's the context switching Exactly. It's the context switching Exactly. It's the context switching that's the pain. that's the pain. that's the pain. Uh so Uh so Uh so what you're really doing is trying to do what you're really doing is trying to do what you're really doing is trying to do all the prep work so that when you do all the prep work so that when you do all the prep work so that when you do context switch into a particular task, context switch into a particular task, context switch into a particular task, you can really focus and spend, you you can really focus and spend, you you can really focus and spend, you know, that 20, 30 minutes doing nothing know, that 20, 30 minutes doing nothing know, that 20, 30 minutes doing nothing but thinking about, you know, what did but thinking about, you know, what did but thinking about, you know, what did the agent come up with? Is it the right the agent come up with? Is it the right the agent come up with? Is it the right thing? Testing it, using it, thing? Testing it, using it, thing? Testing it, using it, looking at the code, having another looking at the code, having another looking at the code, having another agent review the code and really talking agent review the code and really talking agent review the code and really talking it over with that agent. Uh that's what it over with that agent. Uh that's what it over with that agent. Uh that's what I find the best, you know, results come I find the best, you know, results come I find the best, you know, results come from being able to focus while still from being able to focus while still from being able to focus while still multitasking. Yeah, indeed. The other multitasking. Yeah, indeed. The other multitasking. Yeah, indeed. The other thing that I think it does well, Nimble thing that I think it does well, Nimble thing that I think it does well, Nimble list does well, is you're bringing some list does well, is you're bringing some list does well, is you're bringing some some skills and some work along that is

some skills and some work along that is some skills and some work along that is already in our lives like Excalidraw and already in our lives like Excalidraw and already in our lives like Excalidraw and different mock-ups and tools like that different mock-ups and tools like that different mock-ups and tools like that and you're you're bringing them out of and you're you're bringing them out of and you're you're bringing them out of the box because I usually end up telling the box because I usually end up telling the box because I usually end up telling the agent, "Oh, make make me some ASCII the agent, "Oh, make make me some ASCII the agent, "Oh, make make me some ASCII art mock-up." And I get kind of a weak art mock-up." And I get kind of a weak art mock-up." And I get kind of a weak sauce sauce sauce ASCII art with a non-aligned right ASCII art with a non-aligned right ASCII art with a non-aligned right margin and everything like that. But margin and everything like that. But margin and everything like that. But you've got skills and commands built in you've got skills and commands built in you've got skills and commands built in for for stuff like that. You're actually for for stuff like that. You're actually for for stuff like that. You're actually acknowledging that these tools exist and acknowledging that these tools exist and acknowledging that these tools exist and then baking them into the flow directly. then baking them into the flow directly. then baking them into the flow directly. That's right. We think if you have a That's right. We think if you have a That's right. We think if you have a single, single, single, you know, pane of glass that is all of you know, pane of glass that is all of you know, pane of glass that is all of the tools that an agent that you need to the tools that an agent that you need to the tools that an agent that you need to work with an agent to be able to, you work with an agent to be able to, you work with an agent to be able to, you know, build know, build know, build to build product, to build technology. to build product, to build technology. to build product, to build technology. Uh if all those tools are in the same Uh if all those tools are in the same Uh if all those tools are in the same place, then it's not an agent making MCP place, then it's not an agent making MCP place, then it's not an agent making MCP calls all over the place and you're calls all over the place and you're calls all over the place and you're using different interfaces. You can, you using different interfaces. You can, you using different interfaces. You can, you know, work on the mock-up and the design know, work on the mock-up and the design know, work on the mock-up and the design of something. You can work on the data of something. You can work on the data of something. You can work on the data model with a Prisma, you know, graphic model with a Prisma, you know, graphic model with a Prisma, you know, graphic design. You can design the architecture design. You can design the architecture design. You can design the architecture with Excalidraw and you can do that all with Excalidraw and you can do that all with Excalidraw and you can do that all in a single set of agents uh agent in a single set of agents uh agent in a single set of agents uh agent sessions that don't lose context. Mhm.

sessions that don't lose context. Mhm. sessions that don't lose context. Mhm. But this is quite opinionated and I But this is quite opinionated and I But this is quite opinionated and I think this is the moment, right? None of think this is the moment, right? None of think this is the moment, right? None of us are experts, we're all trying to us are experts, we're all trying to us are experts, we're all trying to figure it out, but you have a advanced figure it out, but you have a advanced figure it out, but you have a advanced and extensive experience in software and extensive experience in software and extensive experience in software engineering. Like I said that, you know, engineering. Like I said that, you know, engineering. Like I said that, you know, you were VP of software engineering at you were VP of software engineering at you were VP of software engineering at safe Salesforce. So you know what you're safe Salesforce. So you know what you're safe Salesforce. So you know what you're doing. doing. doing. When when you at Nimble list are making When when you at Nimble list are making When when you at Nimble list are making a decision about what is the opinion a decision about what is the opinion a decision about what is the opinion that we're going to put bake into the that we're going to put bake into the that we're going to put bake into the product? Like Excalidraw matters, PDF product? Like Excalidraw matters, PDF product? Like Excalidraw matters, PDF viewers matter, data model, you know, viewers matter, data model, you know, viewers matter, data model, you know, data models matter. data models matter. data models matter. How do you decide what's the right thing How do you decide what's the right thing How do you decide what's the right thing to plug in out of the box? to plug in out of the box? to plug in out of the box? The biggest thing I can say is that I The biggest thing I can say is that I The biggest thing I can say is that I use it and I see whether it helps me. use it and I see whether it helps me. use it and I see whether it helps me. Uh and you know, I'm using all of these Uh and you know, I'm using all of these Uh and you know, I'm using all of these tools to build Nimble list and I've got tools to build Nimble list and I've got tools to build Nimble list and I've got my data model and I'm and my ENT and I'm my data model and I'm and my ENT and I'm my data model and I'm and my ENT and I'm trying to figure out is this the right trying to figure out is this the right trying to figure out is this the right storage model for, you know, multi-agent storage model for, you know, multi-agent storage model for, you know, multi-agent uh storage of all this, you know, uh storage of all this, you know, uh storage of all this, you know, session behavior. And session behavior. And session behavior. And if it works for me, then I figure it if it works for me, then I figure it if it works for me, then I figure it might work for some other people. Mhm. might work for some other people. Mhm. might work for some other people. Mhm. Now the planning stuff, you've built in Now the planning stuff, you've built in Now the planning stuff, you've built in a a little SQL database, you've got a a little SQL database, you've got a a little SQL database, you've got planning, decisions, bugs, tasks.

planning, decisions, bugs, tasks. planning, decisions, bugs, tasks. I noticed that that is being checked in. I noticed that that is being checked in. I noticed that that is being checked in. You're versioning that. You're plugging You're versioning that. You're plugging You're versioning that. You're plugging that into the flow as opposed to like that into the flow as opposed to like that into the flow as opposed to like using GitHub or or Jira. Is that a using GitHub or or Jira. Is that a using GitHub or or Jira. Is that a conscious choice as well? conscious choice as well? conscious choice as well? It's It's one of those things we're It's It's one of those things we're It's It's one of those things we're experimenting with right now. Some of experimenting with right now. Some of experimenting with right now. Some of our files we do end up checking into Git our files we do end up checking into Git our files we do end up checking into Git as just the mechanism to share, but as just the mechanism to share, but as just the mechanism to share, but we're also experimenting with, you know, we're also experimenting with, you know, we're also experimenting with, you know, basically collaborative basically collaborative basically collaborative document sharing. So real-time, you document sharing. So real-time, you document sharing. So real-time, you know, markdown editing. Uh it's know, markdown editing. Uh it's know, markdown editing. Uh it's essentially, you know, a local Google essentially, you know, a local Google essentially, you know, a local Google Doc, you know, sitting inside of Nimble Doc, you know, sitting inside of Nimble Doc, you know, sitting inside of Nimble list. And uh and we're getting some list. And uh and we're getting some list. And uh and we're getting some pretty interesting results from that in pretty interesting results from that in pretty interesting results from that in sort of the collab team collaboration sort of the collab team collaboration sort of the collab team collaboration side. Yeah. Now hopefully you'll This is side. Yeah. Now hopefully you'll This is side. Yeah. Now hopefully you'll This is a compliment, don't take this wrong, but a compliment, don't take this wrong, but a compliment, don't take this wrong, but like it doesn't it doesn't feel like like it doesn't it doesn't feel like like it doesn't it doesn't feel like Vibes. It feels like a software Vibes. It feels like a software Vibes. It feels like a software development life cycle tool. And the development life cycle tool. And the development life cycle tool. And the reason I say that is that you put the reason I say that is that you put the reason I say that is that you put the file viewer up front. file viewer up front. file viewer up front. You're not trying to hide files and You're not trying to hide files and You're not trying to hide files and diffs from me, which I'm finding to be diffs from me, which I'm finding to be diffs from me, which I'm finding to be somewhat unique in the space. So many AI somewhat unique in the space. So many AI somewhat unique in the space. So many AI tools are hiding my code from me.

tools are hiding my code from me. tools are hiding my code from me. I think that's true and and nothing I think that's true and and nothing I think that's true and and nothing against those tools, you know, they're against those tools, you know, they're against those tools, you know, they're they're fantastic for, you know, the they're fantastic for, you know, the they're fantastic for, you know, the jobs that they're trying to enable, but jobs that they're trying to enable, but jobs that they're trying to enable, but if you really if the the if you really if the the if you really if the the end result is great software and it's end result is great software and it's end result is great software and it's the entire product including all the the entire product including all the the entire product including all the work that you put into designs, that's work that you put into designs, that's work that you put into designs, that's all of your, you know, work. And we just all of your, you know, work. And we just all of your, you know, work. And we just think that, you know, open formats that think that, you know, open formats that think that, you know, open formats that are on disk, not sitting in some, you are on disk, not sitting in some, you are on disk, not sitting in some, you know, database or tool or out in the know, database or tool or out in the know, database or tool or out in the cloud or, you know, you get sort of just cloud or, you know, you get sort of just cloud or, you know, you get sort of just a thin view of it that's like here's the a thin view of it that's like here's the a thin view of it that's like here's the running view, but to get to the code is, running view, but to get to the code is, running view, but to get to the code is, you know, challenging. Uh we figure you know, challenging. Uh we figure you know, challenging. Uh we figure just, you know, local first, open just, you know, local first, open just, you know, local first, open formats first, use the tools that are formats first, use the tools that are formats first, use the tools that are out there and make them accessible. Mhm. out there and make them accessible. Mhm. out there and make them accessible. Mhm. Now you've got Claude, you've got Open Now you've got Claude, you've got Open Now you've got Claude, you've got Open AI, you've got pluggable agent AI, you've got pluggable agent AI, you've got pluggable agent providers. providers. providers. Also notably you have my friends at LM Also notably you have my friends at LM Also notably you have my friends at LM Studio. I love those guys. Uh so you can Studio. I love those guys. Uh so you can Studio. I love those guys. Uh so you can connect to local LLMs. Have you had good connect to local LLMs. Have you had good connect to local LLMs. Have you had good experience with that? I feel like I need experience with that? I feel like I need experience with that? I feel like I need a really beefy machine to get valuable a really beefy machine to get valuable a really beefy machine to get valuable uh insights. uh insights. uh insights. I think that's true today. You know, it I think that's true today. You know, it I think that's true today. You know, it depends on the task. Some people are depends on the task. Some people are depends on the task. Some people are using Nimble list not to just software using Nimble list not to just software using Nimble list not to just software code, but to, you know, just do code, but to, you know, just do code, but to, you know, just do prototyping or even other business tasks prototyping or even other business tasks prototyping or even other business tasks and I think they're finding more and I think they're finding more and I think they're finding more success. The coding task with the just success. The coding task with the just success. The coding task with the just the size of the context needed um is the size of the context needed um is the size of the context needed um is still a challenge, but you also see still a challenge, but you also see still a challenge, but you also see advancements every week and I think the advancements every week and I think the advancements every week and I think the models are going to get smaller and more models are going to get smaller and more models are going to get smaller and more efficient and we're going to do more efficient and we're going to do more efficient and we're going to do more local work in the future as well. Mhm.

local work in the future as well. Mhm. local work in the future as well. Mhm. I know I'm jumping around a little bit, I know I'm jumping around a little bit, I know I'm jumping around a little bit, but I've got like 40 tabs open and I've but I've got like 40 tabs open and I've but I've got like 40 tabs open and I've got Nimble list open doing two different got Nimble list open doing two different got Nimble list open doing two different things right now. And one of the other things right now. And one of the other things right now. And one of the other things that I think you do that's really things that I think you do that's really things that I think you do that's really cool, which is opinionated, but I cool, which is opinionated, but I cool, which is opinionated, but I haven't quite cracked it in my head yet haven't quite cracked it in my head yet haven't quite cracked it in my head yet is the Kanban stuff. is the Kanban stuff. is the Kanban stuff. How is that stored? Explain how you How is that stored? Explain how you How is that stored? Explain how you think about Kanban boards because you think about Kanban boards because you think about Kanban boards because you can move around from an inbox item, like can move around from an inbox item, like can move around from an inbox item, like a thing that's happening in a session, a thing that's happening in a session, a thing that's happening in a session, move it over to the backlog, move it move it over to the backlog, move it move it over to the backlog, move it over from planning to implementing, and over from planning to implementing, and over from planning to implementing, and move it all the way through the Kanban. move it all the way through the Kanban. move it all the way through the Kanban. Can the agents take action on that? And Can the agents take action on that? And Can the agents take action on that? And could I start That's where the visual could I start That's where the visual could I start That's where the visual thing start becoming interesting to me. thing start becoming interesting to me. thing start becoming interesting to me. Yeah, that's right. And we're Yeah, that's right. And we're Yeah, that's right. And we're experimenting with more of, you know, experimenting with more of, you know, experimenting with more of, you know, the kind of collaborative agent the kind of collaborative agent the kind of collaborative agent task management. So, the the agent can task management. So, the the agent can task management. So, the the agent can create the tasks on the Kanban and create the tasks on the Kanban and create the tasks on the Kanban and manage the flow of the sessions from, manage the flow of the sessions from, manage the flow of the sessions from, you know, planning to implementing to you know, planning to implementing to you know, planning to implementing to user validation. user validation. user validation. And all of that's, you know, And all of that's, you know, And all of that's, you know, customizable by the user by updating customizable by the user by updating customizable by the user by updating their agent files and saying, "Hey, you their agent files and saying, "Hey, you their agent files and saying, "Hey, you know, when Nimblelist, when you create a know, when Nimblelist, when you create a know, when Nimblelist, when you create a plan and we're going through these plan and we're going through these plan and we're going through these steps, here's what here's the, you know, steps, here's what here's the, you know, steps, here's what here's the, you know, the columns I want to use and here's the columns I want to use and here's the columns I want to use and here's what I want you to move it to ready for what I want you to move it to ready for what I want you to move it to ready for development or, you know, validating."

development or, you know, validating." development or, you know, validating." And, you know, you can let the agent And, you know, you can let the agent And, you know, you can let the agent help you organize the the chaos. help you organize the the chaos. help you organize the the chaos. And and and it's one of the chaotic And and and it's one of the chaotic And and and it's one of the chaotic things that I find myself doing a lot is things that I find myself doing a lot is things that I find myself doing a lot is is markups where I'll have my agent on is markups where I'll have my agent on is markups where I'll have my agent on one side and then I'll have a playwright one side and then I'll have a playwright one side and then I'll have a playwright or a markdown file or some kind of or a markdown file or some kind of or a markdown file or some kind of markup or some live HTML. But with markup or some live HTML. But with markup or some live HTML. But with Nimblelist, and help me understand how Nimblelist, and help me understand how Nimblelist, and help me understand how you do this, you can circle the screen, you do this, you can circle the screen, you do this, you can circle the screen, say, "Put something there." and then say, "Put something there." and then say, "Put something there." and then mention it, mention it, mention it, like, "Put this here." or "Put it in the like, "Put this here." or "Put it in the like, "Put this here." or "Put it in the circle area." circle area." circle area." So, you're you're you're closing a loop So, you're you're you're closing a loop So, you're you're you're closing a loop that I didn't realize needed to be that I didn't realize needed to be that I didn't realize needed to be closed because I usually find myself closed because I usually find myself closed because I usually find myself trying to describe the the thing, like, trying to describe the the thing, like, trying to describe the the thing, like, "Use this CSS ID." when I really just "Use this CSS ID." when I really just "Use this CSS ID." when I really just want to point at it and go, "That one." want to point at it and go, "That one." want to point at it and go, "That one." That's right. And we have, you know, That's right. And we have, you know, That's right. And we have, you know, within our extension system, there's within our extension system, there's within our extension system, there's this API to this API to this API to do a deeper level of integration with do a deeper level of integration with do a deeper level of integration with the agents. So that, you know, when the agents. So that, you know, when the agents. So that, you know, when you're in the ERD diagram, you can click you're in the ERD diagram, you can click you're in the ERD diagram, you can click a particular, a particular, a particular, you know, table and say, "These are the you know, table and say, "These are the you know, table and say, "These are the changes I want to make to this." And you changes I want to make to this." And you changes I want to make to this." And you don't have to tell it what table it's don't have to tell it what table it's don't have to tell it what table it's getting that as a link. Or in a mock-up, getting that as a link. Or in a mock-up, getting that as a link. Or in a mock-up, like you said, drawing. And so, we're like you said, drawing. And so, we're like you said, drawing. And so, we're just trying to improve that just trying to improve that just trying to improve that that bandwidth between the user and the that bandwidth between the user and the that bandwidth between the user and the agent. And I think things like drawing agent. And I think things like drawing agent. And I think things like drawing or, you know, pointing, you can you can or, you know, pointing, you can you can or, you know, pointing, you can you can make a lot of make a lot of make a lot of make it a lot simpler for for a user to make it a lot simpler for for a user to make it a lot simpler for for a user to instruct an agent cuz it's really about instruct an agent cuz it's really about instruct an agent cuz it's really about how much control can the user deliver to how much control can the user deliver to how much control can the user deliver to the agent. And how much, you know, how the agent. And how much, you know, how the agent. And how much, you know, how much typing. That's why I think voice is much typing. That's why I think voice is much typing. That's why I think voice is also going to be really important.

also going to be really important. also going to be really important. How do we improve that bandwidth? Yeah, How do we improve that bandwidth? Yeah, How do we improve that bandwidth? Yeah, you think about voice, I I would like to you think about voice, I I would like to you think about voice, I I would like to be able to not sit down. I want to stand be able to not sit down. I want to stand be able to not sit down. I want to stand up and steeple my fingers and walk up and steeple my fingers and walk up and steeple my fingers and walk around my office around my office around my office Yeah. Talking to it. Yeah. Talking to it. Yeah. Talking to it. You know, and if you think about You know, and if you think about You know, and if you think about something like uh a Prisma file or something like uh a Prisma file or something like uh a Prisma file or looking at a database schema, looking at a database schema, looking at a database schema, uh you know, I can edit the Prisma file, uh you know, I can edit the Prisma file, uh you know, I can edit the Prisma file, I can talk to the chat and let it edit I can talk to the chat and let it edit I can talk to the chat and let it edit the Prisma file. But I think too many AI the Prisma file. But I think too many AI the Prisma file. But I think too many AI tools fall into the all input goes tools fall into the all input goes tools fall into the all input goes through here now. And with Nimblelist, through here now. And with Nimblelist, through here now. And with Nimblelist, you seem to be you seem to be you seem to be walking a tightrope between talking to walking a tightrope between talking to walking a tightrope between talking to the chat and editing the actual files the chat and editing the actual files the chat and editing the actual files themselves. themselves. themselves. Yeah, that's right. And, you know, if Yeah, that's right. And, you know, if Yeah, that's right. And, you know, if there's a a way that we can get to there's a a way that we can get to there's a a way that we can get to multiple inputs, you know, things like multiple inputs, you know, things like multiple inputs, you know, things like talking to talking to talking to the AI while drawing, um pointing, you the AI while drawing, um pointing, you the AI while drawing, um pointing, you know, "Here's what I want you to do know, "Here's what I want you to do know, "Here's what I want you to do here." I think there's just some really here." I think there's just some really here." I think there's just some really interesting things we can do in the interesting things we can do in the interesting things we can do in the future. future. future. You know, I was I was talking to a You know, I was I was talking to a You know, I was I was talking to a friend who is a certain age about uh friend who is a certain age about uh friend who is a certain age about uh Star Trek. I'm not sure, you know, I'm Star Trek. I'm not sure, you know, I'm Star Trek. I'm not sure, you know, I'm not sure how old you are, but Star Trek not sure how old you are, but Star Trek not sure how old you are, but Star Trek 4 when Scotty goes back in time and he 4 when Scotty goes back in time and he 4 when Scotty goes back in time and he picks up the mouse and he's like, picks up the mouse and he's like, picks up the mouse and he's like, "Computer." you know, like, of course "Computer." you know, like, of course "Computer." you know, like, of course you would talk to computer. Why wouldn't you would talk to computer. Why wouldn't you would talk to computer. Why wouldn't you talk to it like that? And the guy's you talk to it like that? And the guy's you talk to it like that? And the guy's like, "Just use the keyboard."

like, "Just use the keyboard." like, "Just use the keyboard." I feel like we're right there. Like I feel like we're right there. Like I feel like we're right there. Like right on the edge. We're almost there. right on the edge. We're almost there. right on the edge. We're almost there. Yeah, I I've had some moments of Yeah, I I've had some moments of Yeah, I I've had some moments of absolute pure delight in the sort of absolute pure delight in the sort of absolute pure delight in the sort of interactive voice. interactive voice. interactive voice. You know, it's it's still in testing, You know, it's it's still in testing, You know, it's it's still in testing, but but but it I basically have a voice agent that it I basically have a voice agent that it I basically have a voice agent that can control a coding agent. Um it can can control a coding agent. Um it can can control a coding agent. Um it can control the whole set of coding agents control the whole set of coding agents control the whole set of coding agents and it's I'm talking to it and it's and it's I'm talking to it and it's and it's I'm talking to it and it's firing off prompts and it's just a much firing off prompts and it's just a much firing off prompts and it's just a much higher rate of speed and it can wake up higher rate of speed and it can wake up higher rate of speed and it can wake up and and notify me. And I can be walking and and notify me. And I can be walking and and notify me. And I can be walking around, you know, the yard around, you know, the yard around, you know, the yard having a conversation, controlling having a conversation, controlling having a conversation, controlling multiple agents all through my my multiple agents all through my my multiple agents all through my my headphones. It's pretty It's pretty headphones. It's pretty It's pretty headphones. It's pretty It's pretty cool. Yeah, it is cool. And I think also cool. Yeah, it is cool. And I think also cool. Yeah, it is cool. And I think also it's worth noting that people it's worth noting that people it's worth noting that people oversimplify and they think it's I talk oversimplify and they think it's I talk oversimplify and they think it's I talk to it, it talks to me. But the trick is to it, it talks to me. But the trick is to it, it talks to me. But the trick is you can talk faster than you can type you can talk faster than you can type you can talk faster than you can type and you can read faster than it can and you can read faster than it can and you can read faster than it can talk. talk. talk. That's right. That's right. That's right. >> Asymmetrical, isn't it? Yeah. >> Asymmetrical, isn't it? Yeah. >> Asymmetrical, isn't it? Yeah. Yeah. Yeah, I think Yeah. Yeah, I think Yeah. Yeah, I think and not just, you know, you can read and not just, you know, you can read and not just, you know, you can read faster than it can it can speak, you can faster than it can it can speak, you can faster than it can it can speak, you can just the higher bandwidth of like, let's just the higher bandwidth of like, let's just the higher bandwidth of like, let's see, a layout or a diagram. There's you see, a layout or a diagram. There's you see, a layout or a diagram. There's you just can convey so much more information just can convey so much more information just can convey so much more information than trying to explain it. So.

than trying to explain it. So. than trying to explain it. So. Yeah, absolutely. Is it fair to say that Yeah, absolutely. Is it fair to say that Yeah, absolutely. Is it fair to say that this kind of visual stuff has been like this kind of visual stuff has been like this kind of visual stuff has been like a bigger part of your career cuz you a bigger part of your career cuz you a bigger part of your career cuz you worked on Interaction Studio at worked on Interaction Studio at worked on Interaction Studio at Salesforce and you came in from your Salesforce and you came in from your Salesforce and you came in from your first company that you founded, first company that you founded, first company that you founded, Evergage? Evergage? Evergage? So, like, has this been percolating in So, like, has this been percolating in So, like, has this been percolating in your brain since even before AI coding your brain since even before AI coding your brain since even before AI coding agents? agents? agents? Well, I always Well, I always Well, I always loved focusing on the user experience. loved focusing on the user experience. loved focusing on the user experience. You know, different jobs have different You know, different jobs have different You know, different jobs have different requirements. And so, at Evergage, we requirements. And so, at Evergage, we requirements. And so, at Evergage, we focused on personalization, helping to, focused on personalization, helping to, focused on personalization, helping to, you know, confine and narrow up any you know, confine and narrow up any you know, confine and narrow up any experience, any digital experience, so experience, any digital experience, so experience, any digital experience, so that it was, you know, tailored to what that it was, you know, tailored to what that it was, you know, tailored to what the user was trying to accomplish. the user was trying to accomplish. the user was trying to accomplish. And so, yeah, I think there's a there's And so, yeah, I think there's a there's And so, yeah, I think there's a there's an angle of an angle of an angle of personalizing the, you know, the the personalizing the, you know, the the personalizing the, you know, the the pane of glass for the job that you're pane of glass for the job that you're pane of glass for the job that you're trying to solve. I think that's always trying to solve. I think that's always trying to solve. I think that's always been something that interested me. Um I been something that interested me. Um I been something that interested me. Um I love data visualization and user, love data visualization and user, love data visualization and user, you know, user experience elements and you know, user experience elements and you know, user experience elements and and I think we're just in an incredible and I think we're just in an incredible and I think we're just in an incredible age right now where age right now where age right now where you know, the the what's possible is you know, the the what's possible is you know, the the what's possible is advancing so quickly that you just have advancing so quickly that you just have advancing so quickly that you just have to try things.

to try things. to try things. I uh I feel like I'm pretty far along in I uh I feel like I'm pretty far along in I uh I feel like I'm pretty far along in my journey, but I'm learning like every my journey, but I'm learning like every my journey, but I'm learning like every day. day. day. But I'm also, I think, But I'm also, I think, But I'm also, I think, a little bit hamstrung by a little bit hamstrung by a little bit hamstrung by knowing how it absorbs the tokens. And I knowing how it absorbs the tokens. And I knowing how it absorbs the tokens. And I wonder in your experience as you're wonder in your experience as you're wonder in your experience as you're creating data models, mermaid charts, creating data models, mermaid charts, creating data models, mermaid charts, Excalidraws, mockups, Excalidraws, mockups, Excalidraws, mockups, it can't see stuff even if you give it a it can't see stuff even if you give it a it can't see stuff even if you give it a screenshot. screenshot. screenshot. It can't really see stuff or can it? It can't really see stuff or can it? It can't really see stuff or can it? Like, how much better are is your result Like, how much better are is your result Like, how much better are is your result because you're planning visually because you're planning visually because you're planning visually than my results, which is a lot of than my results, which is a lot of than my results, which is a lot of prose? prose? prose? Yeah, I mean, I think that's true that Yeah, I mean, I think that's true that Yeah, I mean, I think that's true that the, the, the, you know, the you know, the you know, the the agent doesn't get any benefit the agent doesn't get any benefit the agent doesn't get any benefit necessarily from necessarily from necessarily from looking at a ERD diagram instead of just looking at a ERD diagram instead of just looking at a ERD diagram instead of just the raw Prisma. the raw Prisma. the raw Prisma. But the user does. And so, a fair bit of But the user does. And so, a fair bit of But the user does. And so, a fair bit of what the agent does, you know, I'm what the agent does, you know, I'm what the agent does, you know, I'm perfectly fine with it spending tokens perfectly fine with it spending tokens perfectly fine with it spending tokens to improve how it communicates with me. to improve how it communicates with me. to improve how it communicates with me. And I kind of feel like that's that's And I kind of feel like that's that's And I kind of feel like that's that's what we're doing with this.

what we're doing with this. what we're doing with this. Um Um Um That inverted the way I thought you were That inverted the way I thought you were That inverted the way I thought you were going to That's interesting. So, it's as going to That's interesting. So, it's as going to That's interesting. So, it's as much about me understanding what's going much about me understanding what's going much about me understanding what's going on as it is about the agent. If I'm on as it is about the agent. If I'm on as it is about the agent. If I'm going to control it, if I'm going to going to control it, if I'm going to going to control it, if I'm going to steer it and, you know, accomplish the steer it and, you know, accomplish the steer it and, you know, accomplish the task I'm trying to accomplish, I need task I'm trying to accomplish, I need task I'm trying to accomplish, I need that that support from the agent. I want that that support from the agent. I want that that support from the agent. I want the agent spending its time trying to the agent spending its time trying to the agent spending its time trying to help me help me help me control it. So, yeah. control it. So, yeah. control it. So, yeah. And you mentioned that you're using And you mentioned that you're using And you mentioned that you're using Nimblelist to write Nimblelist. And I Nimblelist to write Nimblelist. And I Nimblelist to write Nimblelist. And I was always fascinated when I was talking was always fascinated when I was talking was always fascinated when I was talking to like Anders Hejlsberg on who made C# to like Anders Hejlsberg on who made C# to like Anders Hejlsberg on who made C# and it's like, "Now we've got the and it's like, "Now we've got the and it's like, "Now we've got the compiler building the language. The compiler building the language. The compiler building the language. The compiler builds this itself now." How compiler builds this itself now." How compiler builds this itself now." How What was that like? When did you get to What was that like? When did you get to What was that like? When did you get to the point where like Nimblelist could the point where like Nimblelist could the point where like Nimblelist could basically talk to itself and make its basically talk to itself and make its basically talk to itself and make its own self? Cuz I assume you started You own self? Cuz I assume you started You own self? Cuz I assume you started You didn't vibe the thing, but now you're in didn't vibe the thing, but now you're in didn't vibe the thing, but now you're in this line of loop where it's building this line of loop where it's building this line of loop where it's building its own its own body. its own its own body. its own its own body. Yeah, we It was pretty quickly that we Yeah, we It was pretty quickly that we Yeah, we It was pretty quickly that we got to the point where the coding got to the point where the coding got to the point where the coding happened more in Nimblelist than happened more in Nimblelist than happened more in Nimblelist than anywhere else. anywhere else. anywhere else. And And And you know, I still have other IDEs that I you know, I still have other IDEs that I you know, I still have other IDEs that I use and um use and um use and um and whatnot, but and whatnot, but and whatnot, but the, you know, people talk about the the, you know, people talk about the the, you know, people talk about the harness. And a lot of what I've done harness. And a lot of what I've done harness. And a lot of what I've done with Nimblelist over time is with Nimblelist over time is with Nimblelist over time is create more and more control for the create more and more control for the create more and more control for the agent with Nimblelist. So, agent with Nimblelist. So, agent with Nimblelist. So, you know, as the agent is, you know, you know, as the agent is, you know, you know, as the agent is, you know, doing coding on Nimblelist, it can read doing coding on Nimblelist, it can read doing coding on Nimblelist, it can read the log files live, it can, you know, the log files live, it can, you know, the log files live, it can, you know, create the database live, it can read create the database live, it can read create the database live, it can read the settings live, can the settings live, can the settings live, can actually navigate the UI and take actually navigate the UI and take actually navigate the UI and take screenshots. Mhm. And, you know, look at screenshots. Mhm. And, you know, look at screenshots. Mhm. And, you know, look at the DOM. And so,

the DOM. And so, the DOM. And so, now, you know, I'm trying to get it to, now, you know, I'm trying to get it to, now, you know, I'm trying to get it to, you know, control and optimize the, you know, control and optimize the, you know, control and optimize the, you know, the layout of something and I you know, the layout of something and I you know, the layout of something and I can say, you know, here's what I want it can say, you know, here's what I want it can say, you know, here's what I want it to look like. And now it can basically to look like. And now it can basically to look like. And now it can basically loop until it's done. loop until it's done. loop until it's done. And it's not a forced Ralph loop where And it's not a forced Ralph loop where And it's not a forced Ralph loop where it's just banging on the keyboard until it's just banging on the keyboard until it's just banging on the keyboard until it gets it right. Like it's it's it gets it right. Like it's it's it gets it right. Like it's it's executing and goal seeking towards a executing and goal seeking towards a executing and goal seeking towards a plan. plan. plan. That's right. Yeah, you know, the more That's right. Yeah, you know, the more That's right. Yeah, you know, the more complicated the the task, you know, the complicated the the task, you know, the complicated the the task, you know, the more time you want to spend on the more time you want to spend on the more time you want to spend on the harness, on, you know, did the right harness, on, you know, did the right harness, on, you know, did the right results come out, the test cases, are results come out, the test cases, are results come out, the test cases, are the test cases, you know, covering what the test cases, you know, covering what the test cases, you know, covering what we're trying to accomplish. It doesn't we're trying to accomplish. It doesn't we're trying to accomplish. It doesn't It isn't necessarily going to do the It isn't necessarily going to do the It isn't necessarily going to do the best thing or have the best taste when best thing or have the best taste when best thing or have the best taste when it's like, "Hey, design me a UI." and it's like, "Hey, design me a UI." and it's like, "Hey, design me a UI." and it's like, "Well, I designed it and then it's like, "Well, I designed it and then it's like, "Well, I designed it and then I took a screenshot." It's not usually I took a screenshot." It's not usually I took a screenshot." It's not usually going to fix, you know, what is going to fix, you know, what is going to fix, you know, what is things that a human would would find things that a human would would find things that a human would would find wrong with it. wrong with it. wrong with it. But it'll make it work. You know, it'll But it'll make it work. You know, it'll But it'll make it work. You know, it'll make it work and exercise it, make sure make it work and exercise it, make sure make it work and exercise it, make sure it's functional, and then the human can it's functional, and then the human can it's functional, and then the human can come in and, you know, put the the taste come in and, you know, put the the taste come in and, you know, put the the taste and the touch on it.

and the touch on it. and the touch on it. So, you've got both Codex and Claude So, you've got both Codex and Claude So, you've got both Codex and Claude Code today. It's all pluggable. So, Code today. It's all pluggable. So, Code today. It's all pluggable. So, you're an AI native workspace built on you're an AI native workspace built on you're an AI native workspace built on top of each of them. top of each of them. top of each of them. Do you bounce between them? Cuz I use Do you bounce between them? Cuz I use Do you bounce between them? Cuz I use GitHub Copilot and I feel like GitHub Copilot and I feel like GitHub Copilot and I feel like Claude is fine. It's great. Opus is Claude is fine. It's great. Opus is Claude is fine. It's great. Opus is good. But if I only had Opus available, good. But if I only had Opus available, good. But if I only had Opus available, I would feel frustrated. And I feel the I would feel frustrated. And I feel the I would feel frustrated. And I feel the same about Codex. So, I like Copilot same about Codex. So, I like Copilot same about Codex. So, I like Copilot because I can bounce around between because I can bounce around between because I can bounce around between models. models. models. I'm assuming you did the same thing and I'm assuming you did the same thing and I'm assuming you did the same thing and you're switching models as you do your you're switching models as you do your you're switching models as you do your job. job. job. That's right. Yeah, every day I'm I am That's right. Yeah, every day I'm I am That's right. Yeah, every day I'm I am having one agent review the work of the having one agent review the work of the having one agent review the work of the other agent. I find that extremely other agent. I find that extremely other agent. I find that extremely valuable. And so we have this concept in valuable. And so we have this concept in valuable. And so we have this concept in Nimblelist called work streams where I Nimblelist called work streams where I Nimblelist called work streams where I can kind of group sessions. And I do can kind of group sessions. And I do can kind of group sessions. And I do that frequently. I make a Claude code that frequently. I make a Claude code that frequently. I make a Claude code session and then have Codex review the session and then have Codex review the session and then have Codex review the plan that Claude code came up with it. plan that Claude code came up with it. plan that Claude code came up with it. They usually usually find some errors. They usually usually find some errors. They usually usually find some errors. Then I'll have Claude code implement. Then I'll have Claude code implement. Then I'll have Claude code implement. I'll have Codex review the I'll have Codex review the I'll have Codex review the implementation. It's, you know, it's a implementation. It's, you know, it's a implementation. It's, you know, it's a cycle. cycle. cycle. Okay. But I I I love using multiple Okay. But I I I love using multiple Okay. But I I I love using multiple models. Yeah, yeah. And then we've seen models. Yeah, yeah. And then we've seen models. Yeah, yeah. And then we've seen things like I had Steve Yegge on the things like I had Steve Yegge on the things like I had Steve Yegge on the show a while back and talking about show a while back and talking about show a while back and talking about things like beads and squads. And then things like beads and squads. And then things like beads and squads. And then there's a fellow at Microsoft named there's a fellow at Microsoft named there's a fellow at Microsoft named Brady Gaster who has this thing called Brady Gaster who has this thing called Brady Gaster who has this thing called squads as gastown.

squads as gastown. squads as gastown. You've you're building in kind of You've you're building in kind of You've you're building in kind of automations and tracking and things like automations and tracking and things like automations and tracking and things like that as well. It seems like you're kind that as well. It seems like you're kind that as well. It seems like you're kind of borrowing from things and building of borrowing from things and building of borrowing from things and building them into to Nimblelist. But I can I them into to Nimblelist. But I can I them into to Nimblelist. But I can I still use my favorite wacky squad thing still use my favorite wacky squad thing still use my favorite wacky squad thing or agent thing or gastown or would or agent thing or gastown or would or agent thing or gastown or would Nimblelist fight with me? Nimblelist fight with me? Nimblelist fight with me? Yeah, no. I think you absolutely can. Yeah, no. I think you absolutely can. Yeah, no. I think you absolutely can. And I think what we're trying to do is And I think what we're trying to do is And I think what we're trying to do is figure out the best way to figure out the best way to figure out the best way to lay that out within the user experience. lay that out within the user experience. lay that out within the user experience. Cuz we do we we built in teammates, you Cuz we do we we built in teammates, you Cuz we do we we built in teammates, you know, the Claude version. And I find it know, the Claude version. And I find it know, the Claude version. And I find it to be to be to be I don't use it as much as I thought I I don't use it as much as I thought I I don't use it as much as I thought I would use it. It's just Isn't that would use it. It's just Isn't that would use it. It's just Isn't that funny? You know, I feel the same way. funny? You know, I feel the same way. funny? You know, I feel the same way. Yeah, I think it's just there's only so Yeah, I think it's just there's only so Yeah, I think it's just there's only so much you can do by instructing a model. much you can do by instructing a model. much you can do by instructing a model. And so when I'm sitting there going, And so when I'm sitting there going, And so when I'm sitting there going, "Okay, actually I'm finding more value "Okay, actually I'm finding more value "Okay, actually I'm finding more value for one model reviewing another model's for one model reviewing another model's for one model reviewing another model's work than I am from saying, "Pretend work than I am from saying, "Pretend work than I am from saying, "Pretend you're a designer, you know." Um you're a designer, you know." Um you're a designer, you know." Um You know, that's a conversation that You know, that's a conversation that You know, that's a conversation that people need to have. And I I I've been people need to have. And I I I've been people need to have. And I I I've been I'm interested for folks who are who are I'm interested for folks who are who are I'm interested for folks who are who are listening right now or watching this on listening right now or watching this on listening right now or watching this on YouTube to let me know because YouTube to let me know because YouTube to let me know because they really want me to go and use these they really want me to go and use these they really want me to go and use these squads. And then like, "You're an expert squads. And then like, "You're an expert squads. And then like, "You're an expert database person." It's like database person." It's like database person." It's like you're not.

you're not. you're not. And telling him that you are does it And telling him that you are does it And telling him that you are does it They're like, "No, it it fires synapses They're like, "No, it it fires synapses They're like, "No, it it fires synapses and it spins it." I was like, "I don't and it spins it." I was like, "I don't and it spins it." I was like, "I don't I'm pretty sure that's not how it works I'm pretty sure that's not how it works I'm pretty sure that's not how it works there, bud." The only argument that I there, bud." The only argument that I there, bud." The only argument that I can get for effectively can get for effectively can get for effectively anthropomorphizing my teams and naming anthropomorphizing my teams and naming anthropomorphizing my teams and naming them and make You're the database and them and make You're the database and them and make You're the database and you're the you're the you're the is context window savings. Like, "Okay, is context window savings. Like, "Okay, is context window savings. Like, "Okay, you are thinking about and focusing on you are thinking about and focusing on you are thinking about and focusing on react so you don't have to hold the react so you don't have to hold the react so you don't have to hold the whole thing in your head." whole thing in your head." whole thing in your head." That's right. I mean I That is the one That's right. I mean I That is the one That's right. I mean I That is the one thing I do find that it actually thing I do find that it actually thing I do find that it actually valuable with is valuable with is valuable with is knowing that what conversation I'm going knowing that what conversation I'm going knowing that what conversation I'm going to have with that particular agent, that to have with that particular agent, that to have with that particular agent, that teammate. You know, we'll focus on one teammate. You know, we'll focus on one teammate. You know, we'll focus on one area so I can improve my, you know, area so I can improve my, you know, area so I can improve my, you know, conversation with that agent by having a conversation with that agent by having a conversation with that agent by having a focus for it. focus for it. focus for it. That's actually the more valuable part That's actually the more valuable part That's actually the more valuable part is, you know, just interacting with me. is, you know, just interacting with me. is, you know, just interacting with me. Yeah. Then necessarily that it does a Yeah. Then necessarily that it does a Yeah. Then necessarily that it does a better job. Well, you know, strong better job. Well, you know, strong better job. Well, you know, strong opinions weekly held. Certainly I don't opinions weekly held. Certainly I don't opinions weekly held. Certainly I don't want to want to want to say that this is say that this is say that this is wrong, but it does feel like it's not wrong, but it does feel like it's not wrong, but it does feel like it's not right for me yet because it hasn't right for me yet because it hasn't right for me yet because it hasn't clicked. And if it was obviously better, clicked. And if it was obviously better, clicked. And if it was obviously better, we'd all be we'd all be doing it. But we'd all be we'd all be doing it. But we'd all be we'd all be doing it. But it's it's fascinating to watch people it's it's fascinating to watch people it's it's fascinating to watch people swarm up on a problem swarm up on a problem swarm up on a problem with with anthropomorphized specific with with anthropomorphized specific with with anthropomorphized specific headers effectively. Like, you're you're headers effectively. Like, you're you're headers effectively. Like, you're you're the UI, you're the tester, you're that.

the UI, you're the tester, you're that. the UI, you're the tester, you're that. But it certainly it sounds like But it certainly it sounds like But it certainly it sounds like Nimblelist won't stand in my way if I Nimblelist won't stand in my way if I Nimblelist won't stand in my way if I choose to do it that way. choose to do it that way. choose to do it that way. That's right. Yeah. Yeah, that's pretty That's right. Yeah. Yeah, that's pretty That's right. Yeah. Yeah, that's pretty cool. You said you use other tools as cool. You said you use other tools as cool. You said you use other tools as well. I assume like what VS code or well. I assume like what VS code or well. I assume like what VS code or cursor, you're bouncing around seeing cursor, you're bouncing around seeing cursor, you're bouncing around seeing what different people are coming up with what different people are coming up with what different people are coming up with in different ideas. in different ideas. in different ideas. Yeah, I use them I use Yeah, I use them I use Yeah, I use them I use at least VS code, cursor, and, you know, at least VS code, cursor, and, you know, at least VS code, cursor, and, you know, the JetBrains series on a the JetBrains series on a the JetBrains series on a on a daily basis. Um on a daily basis. Um on a daily basis. Um If not a weekly basis, but If not a weekly basis, but If not a weekly basis, but you know, it's it's largely about making you know, it's it's largely about making you know, it's it's largely about making sure I still have sure I still have sure I still have contact with how other people are contact with how other people are contact with how other people are thinking about this cuz it's it's a leap thinking about this cuz it's it's a leap thinking about this cuz it's it's a leap to go from to go from to go from you know, the code first experience or you know, the code first experience or you know, the code first experience or seeing what some others are doing which seeing what some others are doing which seeing what some others are doing which is, you know, really flipping it and is, you know, really flipping it and is, you know, really flipping it and saying, "Well, forget the code. Let's saying, "Well, forget the code. Let's saying, "Well, forget the code. Let's just do, you know, session management." just do, you know, session management." just do, you know, session management." And I think I'm just trying to find that And I think I'm just trying to find that And I think I'm just trying to find that balance that's probably somewhere in the balance that's probably somewhere in the balance that's probably somewhere in the middle. Um middle. Um middle. Um Yeah, it it is such a challenge to to Yeah, it it is such a challenge to to Yeah, it it is such a challenge to to manage so many like it's it's we all manage so many like it's it's we all manage so many like it's it's we all multitask now. Like I'm I'm almost multitask now. Like I'm I'm almost multitask now. Like I'm I'm almost Like I can't I said hamstrung before, Like I can't I said hamstrung before, Like I can't I said hamstrung before, but it's there's an analysis paralysis but it's there's an analysis paralysis but it's there's an analysis paralysis that happens. And the paging back in that happens. And the paging back in that happens. And the paging back in like, "What was I what was I working on like, "What was I what was I working on like, "What was I what was I working on again in that other session?" I want to again in that other session?" I want to again in that other session?" I want to give it as much time as I can to turn to give it as much time as I can to turn to give it as much time as I can to turn to do its job. I was actually Let me Let me do its job. I was actually Let me Let me do its job. I was actually Let me Let me back up. I was in an interesting little back up. I was in an interesting little back up. I was in an interesting little lowercase A argument with a coworker lowercase A argument with a coworker lowercase A argument with a coworker today.

today. today. I tend to do what myself and Mark I tend to do what myself and Mark I tend to do what myself and Mark Pernice call code code sculpting Pernice call code code sculpting Pernice call code code sculpting where I give it a good size task and we where I give it a good size task and we where I give it a good size task and we rough it out. And then it's sculpt rough it out. And then it's sculpt rough it out. And then it's sculpt sculpt sculpt sculpt. And you might do sculpt sculpt sculpt. And you might do sculpt sculpt sculpt. And you might do 40 to 50 turns. 40 to 50 turns. 40 to 50 turns. And my coworker is still 3 hours later And my coworker is still 3 hours later And my coworker is still 3 hours later in the day here working on the plan.md. in the day here working on the plan.md. in the day here working on the plan.md. Which I I call it the prose compiler. Which I I call it the prose compiler. Which I I call it the prose compiler. You know, he's trying to make this giant You know, he's trying to make this giant You know, he's trying to make this giant 40-page spec that's so clear that it 40-page spec that's so clear that it 40-page spec that's so clear that it would build in an autopilot. And I I would build in an autopilot. And I I would build in an autopilot. And I I keep coming back to like it's not a keep coming back to like it's not a keep coming back to like it's not a compiler and you could run that plan compiler and you could run that plan compiler and you could run that plan five times through five different five times through five different five times through five different models, you get five different products models, you get five different products models, you get five different products because the plan is never going to be as because the plan is never going to be as because the plan is never going to be as specific as the code. So like specific as the code. So like specific as the code. So like I'm I'm working analogies in my head. I'm I'm working analogies in my head. I'm I'm working analogies in my head. You know, like ice We know how to take a You know, like ice We know how to take a You know, like ice We know how to take a chainsaw and they make like ice chainsaw and they make like ice chainsaw and they make like ice sculpture. sculpture. sculpture. They start with a giant block and they They start with a giant block and they They start with a giant block and they just hack at it. They just hack at it. just hack at it. They just hack at it. just hack at it. They just hack at it. And they go, "That kind of shaped like a And they go, "That kind of shaped like a And they go, "That kind of shaped like a horse." horse." horse." And then the work starts. And then the work starts. And then the work starts. Are you are you a big upfront planner or Are you are you a big upfront planner or Are you are you a big upfront planner or are you a code sculptor?

are you a code sculptor? are you a code sculptor? Well, the models have really advanced in Well, the models have really advanced in Well, the models have really advanced in the past year. You know, a year ago, the past year. You know, a year ago, the past year. You know, a year ago, yes, you really needed to spend time on yes, you really needed to spend time on yes, you really needed to spend time on a plan if you were going to get valuable a plan if you were going to get valuable a plan if you were going to get valuable work out of it. I think what has work out of it. I think what has work out of it. I think what has happened is I've shifted I still do happened is I've shifted I still do happened is I've shifted I still do plans for just about everything. But plans for just about everything. But plans for just about everything. But what I've focused on is making sure that what I've focused on is making sure that what I've focused on is making sure that the plan isn't the instruction to the the plan isn't the instruction to the the plan isn't the instruction to the agent, it's the documentation of what I agent, it's the documentation of what I agent, it's the documentation of what I want. Because I like being able to come want. Because I like being able to come want. Because I like being able to come back to it. I like being able to back to it. I like being able to back to it. I like being able to reference a second session to that plan reference a second session to that plan reference a second session to that plan and say, "You know, is this correct? You and say, "You know, is this correct? You and say, "You know, is this correct? You know, did you forget anything?" And and know, did you forget anything?" And and know, did you forget anything?" And and specifically it's not about specifically it's not about specifically it's not about this is what I This is how I want you to this is what I This is how I want you to this is what I This is how I want you to solve this agent. It's about here is the solve this agent. It's about here is the solve this agent. It's about here is the motivation behind it. And here are the motivation behind it. And here are the motivation behind it. And here are the important, you know, important, you know, important, you know, aspects that you can't miss. And that's aspects that you can't miss. And that's aspects that you can't miss. And that's that gives me durable long-term mapping that gives me durable long-term mapping that gives me durable long-term mapping to what I'm trying to accomplish, not to what I'm trying to accomplish, not to what I'm trying to accomplish, not just one single session that I gave it just one single session that I gave it just one single session that I gave it instructions and maybe I spend time, you instructions and maybe I spend time, you instructions and maybe I spend time, you know, sculpting the code which I do, you know, sculpting the code which I do, you know, sculpting the code which I do, you know, especially naming and and know, especially naming and and know, especially naming and and organization and architecture.

organization and architecture. organization and architecture. But But But that the why is is critical to document. that the why is is critical to document. that the why is is critical to document. And so that's what I end up doing in And so that's what I end up doing in And so that's what I end up doing in those plan files more and more. It's those plan files more and more. It's those plan files more and more. It's funny. Sometimes I feel like I will get funny. Sometimes I feel like I will get funny. Sometimes I feel like I will get the code done, review the code, and then the code done, review the code, and then the code done, review the code, and then I'll back up and I'll say, "Write me a I'll back up and I'll say, "Write me a I'll back up and I'll say, "Write me a markdown to talk about what we just markdown to talk about what we just markdown to talk about what we just did." And then I wonder if I'm being a did." And then I wonder if I'm being a did." And then I wonder if I'm being a phony doing that. phony doing that. phony doing that. Yeah, I do that a lot, too. I Those are Yeah, I do that a lot, too. I Those are Yeah, I do that a lot, too. I Those are not my plan files, those are my design not my plan files, those are my design not my plan files, those are my design architectural, you know, they're they're architectural, you know, they're they're architectural, you know, they're they're docs or historical documents. Exactly, docs or historical documents. Exactly, docs or historical documents. Exactly, my artifacts. So my artifacts. So my artifacts. So and I do that a lot, too. Especially, and I do that a lot, too. Especially, and I do that a lot, too. Especially, you know, if I accomplish something you know, if I accomplish something you know, if I accomplish something that's big and important, I don't I that's big and important, I don't I that's big and important, I don't I don't want the model to, you know, veer don't want the model to, you know, veer don't want the model to, you know, veer off. And so it's really off. And so it's really off. And so it's really it's an anchor. I do the same thing. it's an anchor. I do the same thing. it's an anchor. I do the same thing. What I'll do is I I think about it What I'll do is I I think about it What I'll do is I I think about it almost on a subsystem by subsystem almost on a subsystem by subsystem almost on a subsystem by subsystem basis. So like I had a really basis. So like I had a really basis. So like I had a really interesting problem with dots per inch interesting problem with dots per inch interesting problem with dots per inch issues on Windows and multi-monitor. issues on Windows and multi-monitor. issues on Windows and multi-monitor. And I felt like we, the collective royal And I felt like we, the collective royal And I felt like we, the collective royal we, had accomplished something. I said, we, had accomplished something. I said, we, had accomplished something. I said, "All right, write down everything that "All right, write down everything that "All right, write down everything that we learned, you know, for future we learned, you know, for future we learned, you know, for future generations and myself tomorrow generations and myself tomorrow generations and myself tomorrow so that we can remember cuz I don't cuz so that we can remember cuz I don't cuz so that we can remember cuz I don't cuz like why did we We were cuz we weren't like why did we We were cuz we weren't like why did we We were cuz we weren't just turning. We were Googling and stack just turning. We were Googling and stack just turning. We were Googling and stack overflowing all the classic programming overflowing all the classic programming overflowing all the classic programming and just thinking. And then I was like, and just thinking. And then I was like, and just thinking. And then I was like, "Oh, that's how it works." And I know "Oh, that's how it works." And I know "Oh, that's how it works." And I know for a fact that tomorrow morning the AI for a fact that tomorrow morning the AI for a fact that tomorrow morning the AI is going to have forgotten it all.

is going to have forgotten it all. is going to have forgotten it all. So like if we ever get it again. So like if we ever get it again. So like if we ever get it again. But but you got to keep that so that, But but you got to keep that so that, But but you got to keep that so that, you know, the creating that that you know, the creating that that you know, the creating that that knowledge management of just all of the knowledge management of just all of the knowledge management of just all of the work. And there's a lot of things that work. And there's a lot of things that work. And there's a lot of things that are not code that come out that that are are not code that come out that that are are not code that come out that that are part of that knowledge management. part of that knowledge management. part of that knowledge management. Another thing I just as we get towards Another thing I just as we get towards Another thing I just as we get towards the end here, I wanted to call out is the end here, I wanted to call out is the end here, I wanted to call out is that you were quite early on the idea of that you were quite early on the idea of that you were quite early on the idea of managing agents on the go. managing agents on the go. managing agents on the go. Like everything everyone's moving fast, Like everything everyone's moving fast, Like everything everyone's moving fast, but you were thinking about the idea but you were thinking about the idea but you were thinking about the idea that you're going to have to connect to that you're going to have to connect to that you're going to have to connect to these cuz the agent's running on your these cuz the agent's running on your these cuz the agent's running on your machine and you've gone to lunch. You're machine and you've gone to lunch. You're machine and you've gone to lunch. You're gone for a walk. And you might just need gone for a walk. And you might just need gone for a walk. And you might just need to say yes or you might need to steer to say yes or you might need to steer to say yes or you might need to steer it. it. it. Is that a mobile app that you pair or is Is that a mobile app that you pair or is Is that a mobile app that you pair or is that a tunnel through Engrock? How do that a tunnel through Engrock? How do that a tunnel through Engrock? How do you do that? Yes, it's We just wanted a, you do that? Yes, it's We just wanted a, you do that? Yes, it's We just wanted a, you know, kind of seamless native you know, kind of seamless native you know, kind of seamless native experience. So we built experience. So we built experience. So we built iOS first, Android coming. But, you iOS first, Android coming. But, you iOS first, Android coming. But, you know, it's it's really just Nimblelist know, it's it's really just Nimblelist know, it's it's really just Nimblelist in a in a phone experience that's just, in a in a phone experience that's just, in a in a phone experience that's just, you know, a window of glass into back to you know, a window of glass into back to you know, a window of glass into back to your machine. We're doing end-to-end your machine. We're doing end-to-end your machine. We're doing end-to-end encryption tunneling just to make it, encryption tunneling just to make it, encryption tunneling just to make it, you know, seamless. you know, seamless. you know, seamless. >> using secure web sockets through the >> using secure web sockets through the >> using secure web sockets through the Nimblelist servers, but it's ultimately Nimblelist servers, but it's ultimately Nimblelist servers, but it's ultimately Exactly.

Exactly. Exactly. >> tunneling. >> tunneling. >> tunneling. Yeah, exactly. And, you know, Yeah, exactly. And, you know, Yeah, exactly. And, you know, just giving you that that that high just giving you that that that high just giving you that that that high bandwidth ability to answer a question bandwidth ability to answer a question bandwidth ability to answer a question to the, you know, to the agent or to get to the, you know, to the agent or to get to the, you know, to the agent or to get notified and say, "Oh, it's done, you notified and say, "Oh, it's done, you notified and say, "Oh, it's done, you know." So I can be, know." So I can be, know." So I can be, you know, making lunch and you know, making lunch and you know, making lunch and you know, get notified. I I find that you know, get notified. I I find that you know, get notified. I I find that really valuable. Sometimes I'll go for, really valuable. Sometimes I'll go for, really valuable. Sometimes I'll go for, you know, walks out in nature and I'll you know, walks out in nature and I'll you know, walks out in nature and I'll be able to have a little bit of a voice be able to have a little bit of a voice be able to have a little bit of a voice conversation, kick off a few researches. conversation, kick off a few researches. conversation, kick off a few researches. I'm not necessarily coding at those I'm not necessarily coding at those I'm not necessarily coding at those times, but I I'll be like, "Here's an times, but I I'll be like, "Here's an times, but I I'll be like, "Here's an idea. Let's What about this? Go do idea. Let's What about this? Go do idea. Let's What about this? Go do research on that." And I find that, you research on that." And I find that, you research on that." And I find that, you know, freeing. know, freeing. know, freeing. You know, some people think it's funny You know, some people think it's funny You know, some people think it's funny that you say that it's freeing cuz I that you say that it's freeing cuz I that you say that it's freeing cuz I find it freeing as well. Some people find it freeing as well. Some people find it freeing as well. Some people say, "Well, you're just tying me even say, "Well, you're just tying me even say, "Well, you're just tying me even more to the work, you know." But I think more to the work, you know." But I think more to the work, you know." But I think that they don't understand that the that they don't understand that the that they don't understand that the personality of the programmer personality of the programmer personality of the programmer is such that if if if the agent could is such that if if if the agent could is such that if if if the agent could let you know when you're in the shower let you know when you're in the shower let you know when you're in the shower that it it just had an important that it it just had an important that it it just had an important insight, most programmers' personalities insight, most programmers' personalities insight, most programmers' personalities would want to know that right away would want to know that right away would want to know that right away because we need that little dopamine hit because we need that little dopamine hit because we need that little dopamine hit that says, "We solved it. Let's go.

that says, "We solved it. Let's go. that says, "We solved it. Let's go. Let's go." And I don't want to lose 12 Let's go." And I don't want to lose 12 Let's go." And I don't want to lose 12 hours because I forgot to check hours because I forgot to check hours because I forgot to check a notification. a notification. a notification. Yeah, it's exactly right. And, you know, Yeah, it's exactly right. And, you know, Yeah, it's exactly right. And, you know, programmers programmers programmers sit at their desk all day. And, you sit at their desk all day. And, you sit at their desk all day. And, you know, this it feels like this gives me know, this it feels like this gives me know, this it feels like this gives me the freedom to not feel like I have to the freedom to not feel like I have to the freedom to not feel like I have to be to be able to keep my agents busy. be to be able to keep my agents busy. be to be able to keep my agents busy. And I I And I I And I I That Yeah, that does sound like freedom That Yeah, that does sound like freedom That Yeah, that does sound like freedom to me. to me. to me. Yeah, it does sound like freedom. So, Yeah, it does sound like freedom. So, Yeah, it does sound like freedom. So, today people can go to Nimblyst, n i m b today people can go to Nimblyst, n i m b today people can go to Nimblyst, n i m b a l y s t, Nimblyst. a l y s t, Nimblyst. a l y s t, Nimblyst. Uh and it's it's free for individuals. Uh and it's it's free for individuals. Uh and it's it's free for individuals. You just check it out. I downloaded it. You just check it out. I downloaded it. You just check it out. I downloaded it. Didn't take any time at all to get it Didn't take any time at all to get it Didn't take any time at all to get it set up. I have Plaid and Core X already. set up. I have Plaid and Core X already. set up. I have Plaid and Core X already. It picked it up. It picked it up. It picked it up. Um right now it works on on Windows, it Um right now it works on on Windows, it Um right now it works on on Windows, it works on Mac, it works on Linux. Is it a works on Mac, it works on Linux. Is it a works on Mac, it works on Linux. Is it a Tauri app or a Electron app? Tauri app or a Electron app? Tauri app or a Electron app? Electron, yeah. Electron app, so it Electron, yeah. Electron app, so it Electron, yeah. Electron app, so it works everywhere, works cross-platform. works everywhere, works cross-platform. works everywhere, works cross-platform. How do we give you feedback? How do we, How do we give you feedback? How do we, How do we give you feedback? How do we, you know, get involved? Because, you you know, get involved? Because, you you know, get involved? Because, you know, if I bump into an issue on on know, if I bump into an issue on on know, if I bump into an issue on on Windows or it doesn't work the way I Windows or it doesn't work the way I Windows or it doesn't work the way I expect, where would I talk about that? expect, where would I talk about that? expect, where would I talk about that? Well, we've got a great Discord server, Well, we've got a great Discord server, Well, we've got a great Discord server, so feel free to drop in there. And so feel free to drop in there. And so feel free to drop in there. And there's a feedback button right in there's a feedback button right in there's a feedback button right in Nimblyst where you can drop us a note, Nimblyst where you can drop us a note, Nimblyst where you can drop us a note, so so so yeah, love to hear from you. Yeah, yeah, love to hear from you. Yeah, yeah, love to hear from you. Yeah, there's also a community on GitHub. Just there's also a community on GitHub. Just there's also a community on GitHub. Just at the bottom footer there of at the bottom footer there of at the bottom footer there of nimblyst.com, you can see the community nimblyst.com, you can see the community nimblyst.com, you can see the community section. Both GitHub, Discord, and then section. Both GitHub, Discord, and then section. Both GitHub, Discord, and then all the socials. You're everywhere.

all the socials. You're everywhere. all the socials. You're everywhere. That's right. Very cool. Well, thanks so That's right. Very cool. Well, thanks so That's right. Very cool. Well, thanks so much, Greg Hinkle, for chatting with me much, Greg Hinkle, for chatting with me much, Greg Hinkle, for chatting with me today. today. today. Thank you very much, Scott. Thank you very much, Scott. Thank you very much, Scott. This has been another episode of This has been another episode of This has been another episode of Hanselminutes, and we'll see you again Hanselminutes, and we'll see you again Hanselminutes, and we'll see you again next week.