Episode Categories:
Resources:
Join the discussion on LinkedIn: Got something to say? Let us know on LinkedIn and network with other AI leaders
Upcoming Episodes: Check out the upcoming Everyday AI Livestream lineup
Connect with Jordan Wilson: LinkedIn Profile
Start Here Series in our Inner Circle Community: Join for free access
Desktop AI Agents: Mastering Plans, Goals, Loops, and Subagents for Business Impact
As AI technology rapidly advances beyond the age of custom GPTs and chatbot prompting, mastering the next generation of desktop AI agents has become a critical business skill. No longer a specialized talent, understanding the detailed functionality of autonomous desktop agents—and their unique vocabulary—is fast becoming an essential operational competency. The core concepts described below, drawn directly from recent industry discussions, break down how desktop AI agents like those used in Codex and Claude Code function in practical business settings.
Harnessing Desktop Agent Platforms for Autonomous Productivity
Desktop AI agents operate through specialized "harnesses," such as Codex and Claude Desktop, which serve as environments where models interact with tools, files, and the broader system autonomously over extended periods. Unlike standard chatbots limited to reactive, single tasks, these harnesses support proactive and multi-layered automations. A key distinction is that these agents can read, write, and modify files, access browsers, and run scheduled operations, essentially functioning as digital workers with the permission and context awareness critical for effective enterprise use.
Planning Workflows: The Strategic Blueprint for AI Agents
One concept discussed was the role of plans within desktop agent workflows. In harnesses like Codex and Claude, a plan is not a vague intention but a detailed step-by-step outline of the intended agent actions before execution begins. This approach resembles architectural blueprints, providing clarity on which files, tools, or app changes the agent will touch. The plan mode exposes assumptions—such as approval points and verification checks—helping prevent missteps that would otherwise lead to inefficient or costly runaway processes. Approving and refining these plans places effective guardrails, which is paramount when agents undertake high-impact business work that may run unattended for extended periods.
Defining Goals: Anchoring AI Outputs to Business Deliverables
Goal setting, as differentiated from planning, establishes the “finish line” for agent-driven projects. Strong goals define not only the output, but also the audience, materials, and completion criteria. Codex surfaces goal status visually in the workflow, allowing clear oversight of multi-step objectives. Without disciplined goal definition, agents can loop endlessly toward ambiguous or unattainable outcomes, resulting in wasted computational resources and management time. In tightly managing goals, businesses secure results that are not just technically correct, but aligned with operational priorities.
Loop Automation: Scheduling and Verifying Repetitive Agent Work
A key theme that emerged was the strategic role of loops. Loops enable agents to repeat verified task sequences at scheduled intervals—such as checking regulatory websites or triaging shared inboxes. In Codex, loops are built as schedulable automations or skills, while Claude’s collaborative interface offers visibility into progress via side panels. The business benefit emerges when each looped step includes explicit verification mechanisms. Clarity in task confirmation at each cycle ensures AI output retains integrity throughout operational use, avoiding the pitfalls of context drift and excessive unchecked iterations.
Subagents: Enabling Parallelized and Specialized AI Task Management
The discussion explored how subagents function within advanced desktop harnesses. Subagents are specialized helper agents, each with carefully defined roles and separate context windows. By assigning precise tasks—such as reviewing code security, auditing feature sets, or optimizing frontend design—subagents divide complex projects into manageable, parallelized workstreams. Codex offers real-time monitoring and custom naming of subagents; Claude surfaces their outputs in organized panels. For larger undertakings, pre-configured agent skill tiers can automate the delegation, oversight, and contrarian review required for high-stakes production environments.
Operator Supervision: Translating Agent Lingo to Business Oversight
Several points were raised, including the operational shift from simply using AI tools to actively supervising and refining agent workflows. The modern differentiator lies in the ability to define robust handoffs: specifying plans, goals, permissions, and verification at each stage. Effective use of agent lingo—such as plan, goal, loop, and subagent—moves beyond technical jargon to become the backbone of reliable, scalable digital delegation.
Infrastructure Constraints: Building Reliable Autonomous Workflows
A practical constraint associated with desktop harnesses is dependence on local machine uptime and connectivity. Agents require an active, powered-on system to operate seamlessly. Any interruption—such as a sleeping laptop or disconnected internet—halts agent progress, underscoring the need for robust IT infrastructure and explicit continuity planning.
Conclusion: Agent Fluency as an Essential Business Skill
The conversation focused on the evolving skillset required to manage modern AI agents for business. Moving beyond prompt engineering and chatbot tuning, fluency in desktop agent vocabulary and workflow design now sets effective operators apart. Businesses able to structure, monitor, and refine agent-driven projects leverage these tools not just for point solutions, but to create repeatable, scalable systems—driving genuine operational value in an AI-powered era.
Topics Covered in This Episode:
- Desktop Agent Vocabulary Primer
- Agent Harnesses: Codex vs. Claude Code
- Desktop Agent Plans: Features and Workflow
- Goal Setting in Codex and Claude Desktop
- Plan vs. Goal: Key Differences
- Agent Loops: Automation and Verification
- Sub Agents: Parallel Task Management
- Context Windows and Task Delegation
- Guardrails, Verification, and Cost Control
- Transition from Chatbots to Autonomous Agents
Episode Transcript
Jordan Wilson [00:00:17]:
Remember back in 2024 when knowing how to use a custom GPT was a differentiator? Or in 2025 when knowing the difference between a skill and a project and Claude could be a competitive advantage for your company's AI efforts. Well, those days are gone, and so is most of the useful lingo because controlling front end chatbots and models and modes are now table stakes. Differentiator now is controlling long running desktop agents, and it sounds easy in theory until you realize that the language you've been building up on the front end AI chatbot era and the language of the long running autonomous agents are not exactly compatible. So today, we're giving you the primer and establishing some baseline vocabulary and concepts you'll need heading into 2027 when long running AI agents become the new norm. So here is the big picture. Agent vocabulary is now an essential skill set. And, yeah, it's changing all the time, which is one of the reasons why we do this thing every day. But agents can obviously read and write files.
Jordan Wilson [00:01:35]:
They can run tools, call their own, create their own apps and plugins. They can fix mistakes and work for hours unattended, which is both a good and a bad thing depending on, how active you are in your agents. And every new term now names a problem you only hit once an agent run runs law. Right? So so so much of the previous, terminology that we use with AI chatbots, right, you had an instant feedback loop for yourself whether it worked or not, and that is kind of gone. You really have to be paying attention. And not knowing the words now, well, means you might set a vague goal. You might put up weak guardrails, and that run that you think might fix the problem as you go take a walk might not really go anywhere. And learning this new agentic language is becoming as essential as learning how to prompt as that was helpful.
Jordan Wilson [00:02:30]:
So on today's show, we're going to learn what loops, goals, plans, and sub agents actually mean without the jargon. We're gonna go over how all of these terms work in codex and claw desktop, so you can know how these features work together. You're gonna learn why fluency in these terms is the skill separating operators from spectators, and you're gonna know the mental model that makes the whole vocabulary click starting now. Alright. If you're new here, welcome. This is the start here series. The start here series is part of everyday AI's ongoing effort to give whether you're a new listener or a seasoned AI expert to give everyone an essential podcast series to both learn the AI basics and double down on your AI knowledge. So if that's what you're trying to do, sweet.
Jordan Wilson [00:03:28]:
Me too. Let's do it together. Make sure to go to starthereseries.com. That's going to give you exclusive access to our inner circle community, and you're gonna be redirected straight into our start here series space, which has a playlist, for all of these episodes all in order. So it's easy to, go through them all as well as, you can read about them all on the page and connect with other people who are along the journey with you. So if you missed our last start here series, that was volume 29 where we talked about the open source surge and if models like GLM 5.2, make open source and enterprise priority. But today, we are talking about the desk top agent lingo simplified. So first, let's zoom out completely.
Jordan Wilson [00:04:17]:
Alright. So if you are not someone that's using codex or claw desktop or anti gravity or cursor. Some of this might not make a ton of sense, and that's okay. And maybe this show is more for you than anyone else, because if you are using something like codex or, claw desktop every single day for hours, this episode will probably be a review at best, but I think still helpful. So if you're like, okay. I don't use these tools. No. You need to listen up, and you should start using them.
Jordan Wilson [00:04:54]:
But I want to talk about the shift, obviously, from the, AI chatbot that's just very reactive versus the proactive autonomous desktop worker. And really what separates them is the harness. Right? So, sometimes when you talk about a model, you talk a lot about the harness or where it lives and how it accesses how it how they access all of these tools. Right? So let's just use an example. Codecs from OpenAI. Right. It's my favorite harness. It's the one I use most, but a lot of people don't even know.
Jordan Wilson [00:05:28]:
You can use other models inside Codecs. Codecs is the harness. Right. You can't do that with Claude Code. You can do that with inside gravity, codex, and some others, Cursor as well. So the harness is how all of these, agentic tools come together, and they can work over long term. Right? When you see all these stories, you're like, oh, this person had an agent running over the weekend or overnight. Well, that's really made possible by the harnesses that these companies create that give the models and the tools essentially a sandbox to do all this.
Jordan Wilson [00:06:02]:
And, you know, it's kind of, today's episode is really a primer on understanding what happens under this the hood of the harness, so to speak. So we're not gonna get super technical. This is, for beginners and maybe intermediate people as well, but that's what we're truly trying to understand. And like I said, even if you're not using these desktop tools now, I think most people will be using them, come 2027. Right? We've heard from Microsoft that they're coming out with their super app. Right? We tackled, super apps, on the show and on the start here series. What episode was that? Bringing that up here. That was our episode, seven ninety nine or volume 28 of the Start Here series.
Jordan Wilson [00:06:46]:
So, you know, Microsoft is bringing out a super app. So these super apps, or these agentic harnesses, right, if you wanna get a more technical term. Essentially, they are a much more powerful version of a web based chatbot that can run autonomously on your computer. You can run them in loops. You can run goals. We're gonna go over all these things. You can schedule automations. So the big difference is, well, it can act autonomously.
Jordan Wilson [00:07:11]:
It can share the context, across different chats, and it can read and write, to your computer. So any file just like a human really would. It can use your actual computer with computer use. It can use your browsers. Right? Has built in browsers. So, you you know, definitely go listen to the, AI super apps episode, if you want a little bit more primer. But let's get straight into it now. So let's talk about plans.
Jordan Wilson [00:07:39]:
And I think plans are actually one of the more underrated features of these harnesses specifically in quad code and in codex. Right? Every once in a while, I'll ask people how they're using, these different harnesses, and people don't really talk about or use plans as much as they should. So a plan essentially just reveals the route before an agent asks, or acts. So a plan shows the intended steps before, you know, the files, the tools, the app changes, all of those things, and planning exposes the assumptions. Right? So likely files, approval points, and verification steps. So plan modes matter because desktop agents can change work fast, and they can work for a very long time. Right. So it's kind of like, a blueprint for a building.
Jordan Wilson [00:08:29]:
Right? You wouldn't just if you had unlimited resources and you wanted to build a building, you wouldn't just go to someone and be like, hey. Go build a building. Or if you're building a custom house, you wouldn't just be like, hey. I want a house and make it awesome. Right. You probably sit down with an architect, and you go over the blueprints, the floor plans, zoning restrictions, requirements, all those things. Right? It's might sound tedious, but you're probably gonna get a much better result in long run if you sit down and have the conversation with said architect or, general contractor. Right? Whatever it is.
Jordan Wilson [00:08:59]:
That's the same thing a plan is. It is literally a plan. So a lot of people will usually just point, you you know, claw desktop or codex, to a folder or share a little bit of context and say, get to work, buddy. Not a good idea. So the plans are essential. So codex, right, uses, the kind of plan pair and execute as collaboration gears. So it it reads and analyzes, and then it proposes things to you. And then it waits for you to approve it before implementation.
Jordan Wilson [00:09:31]:
So similarly, that's how clawed desktop works. It actually works out nicely that these work very similarly in clawed desktop and in codecs. So if you're actually using these and if you wanna see, like, how does this work, where's the button. Right? Codecs has a plan button. I don't believe clawed desktop has it, but you can invoke them each the same way, which is just a backslash and then a plan. Right? And then they'll kind of walk you through, and then you will approve the plan. So in the same way, how I am a very, adamant telling people, like, make sure you read the chain of thought after you've gone through, you know, and and gotten an output out of a large language model. I am that much, in favor of using plan mode.
Jordan Wilson [00:10:16]:
It is the equivalent on the front end. Right. So if you've never used these harnesses, think of something like Google's, Google Gemini's deep research actually does a really good job of this. Right? Before you go out and do a deep research with Google Gemini, it actually gives you a plan to approve so you can see it. And if something's wrong, you can modify it. And this is really important because when we talk about the the the shift from token maxing to token efficiency, Right? Depending on how you set these agents up and what kind of task you're giving them, they might run for a long time. And, you know, if you are using these on a company plan, chances are you're paying via the API. So not having a plan in the same way telling, a builder to build you an amazing house can be a very expensive step to overlook.
Jordan Wilson [00:11:03]:
Plan plan mode, you have to think. It's not slowing you down. A lot of people are just like, I wanna build. I wanna break stuff. I wanna burn tokens. No. It's a guardrail. Right? Not a slowdown.
Jordan Wilson [00:11:12]:
So planning separates thinking from doing, but it's not, you know, it's not enough because risky work still needs, right, that read only access, the work trees, the checkpoints. And then once your route is approved, you know, then the permissions kind of define the real blast radius. So don't just rush into giving a long running agent, keys to the castle or, you know, giving it access to just run for hours and burn through your API bill. Alright. Next, let's talk about goals. Alright. And I I I kind of put these in an order that I think might make sense for most. I generally will start with a plan, and the way I actually do it is I use a plan and then, parlay, the findings of that into a goal.
Jordan Wilson [00:12:04]:
So it's a little confusing, and, cloud code and codex work a little bit differently. In for plan mode, it will still work through your plan. But a lot of times, it will stop once it's gone through the steps. So the biggest difference between a plan and a goal is on the front end. A plan literally just outlines it, and you can see, codex or cloud code work through each step, and there is a visual indicator which is great. Goal is a little bit different. Goal is you literally give it an angle, and it will not stop in in sometimes loop until it hits that goal. Right? So, a lot of times, you have to be careful using goal if you don't go through a plan mode first or if you don't go through an old school best practice prompt engineering, context engineering like we used to teach with prime prop polish to to really share that context and have an understanding with the model of what ultimately the output looks like.
Jordan Wilson [00:12:59]:
So if you just blindly and a lot of people do this. Right? They just blindly throw a bunch of contacts at codecs or cloud desktop, and they give it a goal, and it will keep going until it hits that goal. And if that goal is maybe unattainable, yeah. That's where you can have it work for, hours on end or maybe a day or longer, and all of a sudden, yeah, your, your your bills through the roof. So, let's talk a little bit about goals. So it's really defining the finish line before you start any motion. And like I said, I always go through a planning phase first. I usually make the plan kind of beg, to work through it.
Jordan Wilson [00:13:37]:
Let, you know, codex or, Claude go through and do some work, then I'll see you know, there's always gonna be shortcomings the first time you give some something to someone. So I'll see where it went wrong. I'll go through, read the summarized chain of thought, then I will kind of re prompt it and then make that as a goal. Alright. And sometimes I'll literally just copy and paste the original plan, make some modifications, obviously, because some things on the list or on the steps of the goals are gonna get crossed off, some things aren't. So I usually do a lot of manual nitpicking, transitioning from a, a plan to the goal. But the goal is the outcome and agent checks across the long run. And strong goals specify the audience deliverable source material in the done condition, which is why I think it is usually best in general terms for, you you know, general knowledge work.
Jordan Wilson [00:14:25]:
And, again, I'm coming at this from, like, a general knowledge work. Yes. I do some coding software, dev stuff, building myself, you know, cool projects and, products extensions, all those things. But I am talking about this through general knowledge work. So even if you're not, you know, writing software or, you know, vibe coding something, let's just say your vibe working, I still think that this holds true. So weak goals make plans, loops, and sub agents drift quietly, which I think it's important to go through, especially if you're talking about, a project that you wanna do. Right? If you're just trying to knock off a, a task that might normally take you or a single agent on the web, you know, five, ten minutes to go through, I don't think you necessarily have to go through the plan and the goal in combination. But if you're talking about knocking out an actual project, which is what these systems are capable of doing right now that might take a human two, three, four, five hours or two, three, four, five days.
Jordan Wilson [00:15:25]:
That's when I think it, you you know, when you're talking about your ROI and what you have to invest on the front end, this is one of those things where you're gonna have to build the bridge in order to save the four days driving around the mountain. So goals differ a little bit, across codex in Claude. So codex goals are a little bit more persistent and editable and also visual in the composer. There's a nice little toggle, button in the goal first threads, in codecs, kinda keep the objective across turns and sessions. Claude code, via the desktop version, not the, CLI. It does still support the backslash goal in the same way, but, Cowork is a little bit differently. Works a little bit different. That's the other thing.
Jordan Wilson [00:16:09]:
People, you know, and for me, I personally use, you know, codecs, and I do have to tell people this because if not, it would be extremely irresponsible of me. You know, the big difference between codecs and clawed desktop is clawed desktop is fragmented. There is a chat, a co work, and a code tab, and those tabs have no clue what the other is doing. So there's, you know, certain things that work really well in co work goal, such as the visual indicators that don't always work as well in the code version of goal. So, you know, even as we go over individual features, because Claude code by default, or sorry, Claude desktop by default is siloed, between the chat, the co work, and the code. You know, even things like goal work a little bit differently, in co work and in cloud code. Alright. Another thing to keep in mind, a goal is not just a step by step prompt.
Jordan Wilson [00:17:05]:
Right? So over specified steps can actually fight the agent's own planning process. So you don't have to know everything going into it. Right? You don't have to, like, be like, oh my gosh. I can't use this plan thing and the goal thing because I don't have experience. I'm not a software engineer. Absolutely not. Right? You have to be able to communicate and understand what you want and then work with an agent to, you know, go through the steps to get there. But under specified outcomes make the agents invent missing, like, success criteria, and that's what you absolutely want to avoid.
Jordan Wilson [00:17:36]:
Alright. So now let's talk about loops. Right? So loops are kind of the, newish trend, right? Even though we had the Ralph loops, you know, many many quarters ago. Now loops are making their, viral reappearance again. So loops, essentially can turn plans approved plans into agent work. Right. So similarly, like a heartbeat if you're using OpenClaw. Right.
Jordan Wilson [00:18:06]:
So think of it like this. It's it's something that you can schedule to happen over and over and over and over again. So a loop means, you you know, the agent is gonna observe, plan, act, check, adjust, and repeat. It is literally a loop. So a chatbot would run once while a long running agent can loop many times if you give it that instruction. So the loop only becomes useful when the agent verifies each step. Otherwise, you're just burning tokens like you're still trying to climb the, internal meta, you you know, token burning leaderboard. AI moves too fast to follow, but you're expected to keep up.
Jordan Wilson [00:18:49]:
Otherwise, your career or company might lag behind while AI native competitors leap ahead. But you don't have 10 a day to understand it all. That's what I do for you. But after 700 plus episodes of Everyday AI, the most common questions I get is, where do I start? That's why we created the Start Here series, an ongoing podcast series of more than a dozen episodes you can listen to in order. It covers the AI basics for beginners and sharpens the skills of AI champions pushing their companies forward. In the ongoing series, we explain complex trends in simple language that you can turn into action. There's three ways to jump in. Number one, go scroll back to the first one in episode six ninety one.
Jordan Wilson [00:19:33]:
Number two, tap the link in your show notes at any time for the start here series, or you can just go to starthereseries.com, which also gives you free access to our inner circle community where you can connect with other business leaders doing the same. The Start Here series will slow down the pace of AI so you can get ahead. So, you know, loop review looks a little bit different in each product. So codex, runs every task loop inside a project organized thread. So, you know, you could also, build loops as skills or automations. Right? So you can just tell them, hey. Here's what I want you to do. Right? Every, you know, every hour I want you to go through, you know, triage my email, my calendar, in my drive, you you know, respond to any emails that I might want to update any decks, and I want you to do this every hour.
Jordan Wilson [00:20:28]:
I want you to do this, you know, every day. Right. So that's an example of a very oversimplified example of what could be considered a loop. Right? So Claude Cowork, again, a little bit different. It shows the steps with citations to the files and the messages, which I really like. I like that, that piece in Cowork, a little bit more than I like it in Claude Code because it has that dedicated side panel on the right. So even if you are running technically a loop, you can see those steps visually get checked off. Cloud code surfaces the plans, the task, the sub agents, the diffs in the progress panels.
Jordan Wilson [00:21:00]:
The biggest thing to talk about when, you know, talking about loops is having very clear verification. Right? Whether you wanna run something, a first time. Right? I would literally and I've done this before. You can work through, just go through a natural language, work with codex, work with Claude Code, and say, hey. I want to create a loop. I want to ultimately save this as a skill or an automation, or, you know, usually both. Save it as a skill and an automation that you can schedule and run. But say, hey.
Jordan Wilson [00:21:30]:
Instead of giving you the full loop, I wanna work with you, through this here. You know, here's ultimately what I wanna do. I wanna, you know, check this website, you know, twice a day. You know, this is my whole company. We live and die by this website. Right? It could be industry news. Could be, I I don't know, stocks, finances, etcetera. Right? But think if if if you are someone that has to pay very close attention to the market, something in health care, I don't know, FDA regulations, and there is all these things pinging all the time.
Jordan Wilson [00:22:03]:
Right? Maybe you want to create a loop that you train or you help build a skill set with codex or quad code that goes in there every so often. You know, you see what's new. You run it through your context, your decision making process, etcetera. Work through those steps in the loop one by one so the, so these harness or the model in the harness can understand what verification looks like, what success looks like at each step of the loop. If not, bad loops, bad. Right? Bad loops turn into producing, you know, overly polished work that just is maybe wrong. Because when one loop gets overloaded, then sub agents are maybe going to split the work. Alright.
Jordan Wilson [00:22:46]:
So loops are great. You can save them as a skill in automation. Think of it similar to, like, a heartbeat, if you've used open claw, the great thing. All it takes is natural language. Right? I do think in this aspect, codex is a little bit better, at setting these up. I think that they're, because not being fragmented, it's a little bit easier to just chat, with codex in natural language to set up those loops. Alright. And then last but not least, we have sub agents.
Jordan Wilson [00:23:15]:
So, alright, sub agents like loops are where things get very interesting and potentially dangerous if you are not, being hands on. So if you're being, laissez faire human in the loop and then setting all these things off, I wouldn't recommend going too heavy in the pains on, loops and sub agents. It will get expensive quickly. If you are very hands on, I think loops and sub agents are great. So here's what sub agents are. Well, they're just helper agents with focused assignments and separate context windows. So they help with parallel work, not just vague request to think harder. The real value though is context hygiene before the consolidation begins.
Jordan Wilson [00:24:00]:
So sub agents control, kind of, a different aspect of a job. So one easy thing. Right? An example of how I use sub agents, in codex, and in Claude. So you can just use them, by invoking them. Say use sub agents for this. A lot of people are like, how do you use sub agents? Well, you natural language. Use sub agents for this. So as an example, one thing I like to do is I like to build with codex.
Jordan Wilson [00:24:34]:
Alright. So I build with codex. A lot of people are like, oh, Claude is better at front end. Yeah. It's way better at front end, but I don't know. Codex has this thing called the most powerful AI, image model in the world. So start with the, AI image gen in codex. Use the front end skill, takes three seconds, and you generally will have a much better front end, if you are building, you know, piece of software.
Jordan Wilson [00:24:57]:
That's just what I'm using as an example. Right? If you use the image gen in the front end design skill, you're gonna have way better than what you get off cloud code if you do that. If not, obviously, cloud code is gonna be better. But one reason or one way I use sub agents, I I love Claude's ability to, really investigate and use sub agents across multiple things. So I'll sometimes, I'll assign, you know, I'll say, hey, Claude. I want you to do these sub agents. I want you to look at, you know, one, look at the entire, repo. Number, you know, two, look at the feature set.
Jordan Wilson [00:25:27]:
Three, look at the language. Right? So then each sub agents, can really have a more defined and refined, kind of, task. Right? So it's the same thing. If you just walked into a room of 20 employees and they're there to help you, and you say, hey, 20 employees, go help me with this project. Here's where we're at. Have fun. Right? They might decide upon themselves. Okay.
Jordan Wilson [00:25:51]:
Let's split this up. But if you say, hey, designer. Go look at the design. Hey, copywriter. Go look at the copy. Hey, engineer. Go look at the, I don't know, the security on the back end. Make sure everything's, you know, tightened up.
Jordan Wilson [00:26:01]:
So all you have to do is, well, say go use sub agents. Obviously, these models are smart enough where you can just say that's broadly, and they will, you you know, usually, you know, assign one sub agent to a specific task. Usually, I'll just broadly say, go use sub agents and poke holes in a b c, and then I'll see exactly how they did it. Claude and Codex allow you to click, onto a sub agent and see exactly what they're working on in real time, which is cool. I love how Codex names them. The Claude, names, I forgot how they name them. But, you know, usually, I'll do a quick general sub agent run if it is a big project that's super important, right, that I can spend kind of the token budget on. I'll see what they did, what went wrong, what didn't, you know, how it can be improved.
Jordan Wilson [00:26:48]:
And then I'll probably assign roles the second time I have another group of sub agents do it. Sometimes I'll have sub agents work on the front end before the work actually starts to scope it and make sure it makes sense on where they're spending their time. Sometimes I'll have them work on the back end after the work is done or a combination of the both. And the best thing is, well, you can just tell codex or Claude, like, hey. Have sub agents work on the front end before you start this project to make sure everything is correct. Then go do the work, then have a separate group of sub agents really tear it apart on the back end. Right? That's all you really need to say, and they will do that. It it is kind of like this having this parallel work stream that can disagree, duplicate, you know, miss shared constraints, and that's great.
Jordan Wilson [00:27:30]:
And then the main agent can compare findings, resolve conflicts, synthesize. I've even set up a skill that has, like, a three tier, kind of, agentic management system, so I don't even have to go through and type this. Right? So if I know a project is pretty big or if I'm gonna be working, you know, it's like, hey. I'm setting this off to work overnight. It's it's an ongoing project, and I'm not gonna go through the the planning and goal. I know I have this, you know, sub agent, system where I, you know, say, hey. This one's gonna go in and be a contrary, or, contrarian and, you know, tear apart all this and second guess every single thing that we do before it goes to production, whatever it may be. So that's just, a way to go through sub agents.
Jordan Wilson [00:28:12]:
Alright. So now as we wrap up, the real constraint here is actually your machine. This is the big thing to keep in mind because your machine has to be on. It has to be, right. You have to have these programs open. So, yeah, you can do all these great things like control your computer, right, and and control the browser. And think of that as well as we talk about, you you know, the desktop lingo is it's literally as if you were talking to a human sitting in front of the computer, but it has to be on. Right? A sleeping laptop can break remote steering.
Jordan Wilson [00:28:41]:
You know, if you run out of power, if your Internet goes off, everything, well, from an agentic perspective stops where that's a little bit different. The advantage of using on the front end chatbot, those, you know, singular tasks, those singular one off prompts can continue to go on. But the beginner mistake is not managing anything. Right? The beginner mistake is being like, wow. These things are super powerful. These agents, I can just go in and, you know, drop it some context and say, go do this work and, wow, look at it. You're gonna get just slop work almost every time. Right? Because also bad handoffs say research this, organize that, make that better, and then you just use the output.
Jordan Wilson [00:29:16]:
Right. Good handoffs are well defining the goal, the plan, the permissions, the workload, the verification, the sub agents, the loops. Right. That's the differentiator now, not just saying, oh, I use codex. Oh, I use Claude Code desktop. Right? The handoff turns the agent lingo into repeatable desktop delegation. So like I said, the new skill is number one, understanding how to talk to your agents, but then using those skills to supervise work, not just prompt. Right? The agentic layer is growing thicker and thicker by the day.
Jordan Wilson [00:29:50]:
That doesn't mean the human layer, both, you know, I call it the, you know, the agentic human sandwich. Right? We are the bun. We are providing, the input and the context on the front end and then ultimately the verification. But that doesn't mean we're hands off in the agentic layer. We have to constantly be monitoring, improving. So we don't just, you know, blindly let these agents loop and, you know, blindly assign work to sub agents. Right, we can just spend more time, as the bun and far less time as the meats to use my old saying there. Alright.
Jordan Wilson [00:30:20]:
I hope this one was helpful going over the basics of desktop agent lingo, simplifying goals, loops, plans, and sub agents, and a little bit of how they work in to in codex and in clawed code on the desktop. So if this was helpful, please go to starthereseries.com. If you haven't already, make sure to subscribe to the podcast. I would really appreciate that. Thanks for tuning in. Hope to see you back tomorrow and every day for more everyday AI. Thanks, y'all.