How I Plan, Build, and Run Loops with Claude Code in 40 Minutes | Thariq Shihipar

As the models have gotten smarter, they need less direction, fewer constraints, and fewer examples. We've got slash loop, we've got slash goal, and we've got workflows. These are all geared at trying to get the agent to run for long periods of time. This was just one shot, like when a one prompt starts to create the caption, and it's created a little overlay, and now it's going to fade to black. My goal for this year is to be more productive, but work less. Hey, Ron. Today I'm really excited to welcome Tharik from the Cloud Code team. This has been a long time coming, so I'm going to ask Tharik to show us how to design loops and workflows to get Cloud to work longer, and how he personally uses Cloud Code, and also the new Cloud Tag. Welcome, sir. Hey, Peter. Yeah, thanks for having me. I've been excited to join for a while. Yeah. All right. So maybe before you demo anything, maybe we can talk about, at a high level, how you and the Cloud Code team think about how do you go from you being the person prompting the agents to kind of design loops? and some of the stuff to get the agent to kind of work by itself like how do you guys think about this totally yeah yeah so i think loops are a pretty general term i think for just different ways of like having the agent get feedback or like sort of uh yeah work for long periods of time in an orchestrated way and so we've got slash loop we've got slash goal and we've got workflows and these are all yeah like you said geared at trying to get the agent to run for long periods of time. Slash goal is one of those things that it helps the agent remind itself what its exit condition is, right? And only allows it to exit once you know it. And so goal is really great for when you have a complicated task and you really need to make sure that this is like done at the end, you really want to prevent any stopping. You kind of also want to give the agent feedback a signal to basically say like, hey, power through things, right? And so I think one of the like, if you were to step into Claude's shoes, sometimes you ask someone asks you to do a task, you run into a like maybe, you know, sort of a complication or something that is maybe not quite up to spec or like doesn't match what the user said, you might stop early and be like, hey, should I keep doing this or not, right? And so goal is one way of just kind of the user indicating like, hey, I've done enough spec and expiration, right? I understand the problem space. Just go execute on it. And if you run into something, you know, fill it in. right so that's how we think about goal and and then workflows are in my opinion maybe like the most powerful form of this where you can you know spin up sub agents to both do the work parallelize the work and verify the work and and so i think especially for non-technical work this can be like a really great way of taking a non-deterministic task and then breaking it down roughly into a deterministic task so yeah i think that's how we think about some of these and uh you know i think i'm gonna do a quick demo but like before that yeah like just on the clock team how do you guys use some of this stuff like do you do like a go make this match design or like go make this number go up or what do you use yeah yeah i mean everyone does different things right based on like kind of the like um based on yeah what they're trying to do i i think like uh you know Jared's talked a lot about the bond rewrite in Rust and how that used workflows, and he's going to be talking more about that. I think anytime you have a deterministic signal, for example, latency, goal is a great thing to just have the agent explore things in an auto-research way. And yeah, I think that... you like let's say you're talking about design right I think one way you want to think about this is like how well can the agent like understand what your like design is to begin with right and and so you might want to like turn it into like if it has a spec that it can verify like if it's a figma file you use the figma mcp and then you're like slash goal make sure that the rendered design matches the figma mcp that's a lot easier than like a screenshot right and and so if you're a screenshot maybe you want to do a workflow uh where you like it's more squishy you know like there's like a rubric that you're evaluating against and you have a verification agent and things like that so got it yeah very dependent on the task so basically the planning matters a lot right to give it because i tried giving a goal to like just build me an amazing game and then and then it kind of went off the rails because like you know it's just like one one line so yeah i mean i think um the the details of like you know there's a lot to figure out in what you want you know there's a lot of work that goes into that yeah got it okay so let's make this really concrete uh You've been sharing really awesome videos on Twitter about using Cloud to make the video. And I think you have a video workflow that you want to share with us, right? Yeah, exactly. So I've had a few people ask about this and I think this is a good sort of demo both for like video editing, but also just like how to think about like a non-technical work. So 10 minutes before I got on this call, I recorded a quick video. And so this is me just like, you know, making a video. Basically what I'm saying is like, hey, it's me. You know, like I'm on the Peter Yang podcast. I'm going to point to where I want an overlay to show up and then I'm. basically saying like, hey, fade to black. So this is like a quick video that I put together. And now the prompt I gave it is this, this is a repo for Peter Yang podcast. There's a sample video here called Peter Yang Recording. Transcribe it using Whisper, then use ReMotion to create a UI that shows the transcript with each individual word being highlighted and different overlays. And yeah, goal, don't stop until the video is fully rendered, right? And so now I like, this was just one shot, like when a one prompt, right? And what it gave me is this. So it's transcribed it. It obviously doesn't know my name is Tariq, right? it's like overlaid the text, or sorry, it's created the caption, and it's created a little overlay, and now it's going to fade to black, right? Oh, awesome. Okay, so you basically set out the instructions out loud, right? I set it out loud, yeah, exactly. And of course, there are many ways that you can do this, but it's like now in this directory, you know... transcribed everything, right? Using whisper, it's created the remotion stuff. Yeah, this is like the very basic start to video editing workflow that I have, which is, yeah, I think a good signal for like how to do non-technical work in Cloud Code. So you kind of just manually with the prompt stuff, but then you probably save it into a skill or something, right? Yeah. So right now I don't have a skill. I think one of the things I try and do first is really figure out what I want before I turn it into a skill. And so what are the edge cases here? One of the things I noticed that I had to prompt it towards is getting better at figuring out where my hand was or where I was pointing towards. And even now, I'm not thrilled with where this showed up. Yeah, like you can imagine that one direction I could take this in is I could be like, oh, I want to track my fingers or track my face and then give the agent more metadata, right? So that it can then do interesting overlays. This episode is brought to you by Whisperflow. Whisperflow saves me at least three hours a week. and is one of my favorite AI apps by far. It's just so much faster to dictate to AI using your voice than to type. You just talk naturally and it outputs clean, ready-to-send text. Whisperflow even removes filler words and formats your sentences for you. I use Whisperflow for everything, including drafting newsletter posts, writing product specs, replying on Slack, and more. It works on Mac, Windows, iPhone, and Android. across all of your favorite apps. Try it free at whisperflow.com and use my code PeterWhisperflow to get six months free. That's PeterWhisperflow. Now back to our episode. I think you had another tab that had like a plan or something. Is that for the video skill? Yeah. Yeah. So I think I want to talk, I'd love to talk a little bit about how I got here. You know what I mean? So I think like even to do this prompt, I think it took a bunch of planning and learning to get here, right? And then I think that like one of the things that I, I think when we talk about plans, we often are talking about things where it's like just one shot, right? Like you plan and then you do something and that's it. But I think planning is more of this iterative process of like exploring, investigating, finding out. what you don't know, what you want, right? And then like together, like in the end that sort of simplifies itself. But so like here's an example, but while we do this, I would love to do something where it's like, okay, I'm going to give it, okay. I want to say like, I want to update the UI of these overlays, right? And I want to use I want to use Peter Yang's style. Here's his blog. Create a HTML artifact for exploring different designs for the overlays and captions. Design variations. Okay, so this is like an example. To me, this is also planning, right? Because like what I'm doing is sort of like, I'm trying to figure out what I want here, right? And so it's more of like exploration. You can see one of the important things I'm doing is like I'm giving it a reference, right? So when I give it, you know, your website, it can now fetch the HTML and start doing this. So like this is sort of like a plan that will run while I sort of go over the other, you know, kind of things I do when I'm planning, right? So one of them is like, okay, what, how does transcription work, right? And this is actually, I think, pretty important to know because like it informs a lot of the edge cases so uh this this transcription uses whisper and so um uh you know like cloud code sort of put this explainer together which is honestly like kind of amazing um yeah the important thing for me is like the uh like ways things can go wrong right and this is something i prompted it in the plan was like i want to explain whisper to me and understand what the edge cases are Right. And so one of the things that says like silence can become thanks for watching. Right. Or yeah, a word can be split into two chunks. It doesn't know. It doesn't have speaker recognition. Right. And so there are a bunch of different like edge cases here where I think all of this is quite like good. And this sort of like helped me build a confidence in using whisper. Right. Yeah. But having these edge cases and knowing sort of what the limits are up front. really helped me like avoid this case where I build this complicated workflow during whisper and then you know I realized there are things going wrong um and I like sort of didn't have these unknown unknowns right and so this case is sort of like me sort of doing planning but really it's like me discovering my unknowns and um I think that can take a lot of different shapes it can be learning it can be technical specs right it can be mock-ups and exploration um yeah i'm starting to like i feel like the word plant is maybe uh too broad right now so it's more like exploration and understanding like what you're trying to do basically yeah i like to say uh like getting rid of your unknowns you know like i think whenever you have a task it kind of like almost always uh there's a lot that you don't know Either you don't know how things work or what you want. And it's very, very iterative. And so it's not just like you write it all down once and then you implement it. I think there's many steps and different passes. And dude, this is a beautiful plan, man. Is this like the claw template or something? It has images? This is using the front-end design plugin, I think. Yeah, there are uglier plans here. I've got this re-motion plan. I think that the design of it doesn't matter so much. You really just want to make sure it's something that you really do read and get a sense of not all of it, but there's important parts in it. And I think one failure in what I see is that people still glaze over the plans and explainers. Yeah, it becomes really because AI can write all these crazy markdown files and they're usually pretty long. and then yeah at some point like i just get lazy i'm like okay you know just just do it just do it yeah yeah yeah exactly i think that's like the thing that you know it happens to all of us right like the a like the prompt box can definitely just be a lazy button right where you're just like hey just do the thing um but usually you know like uh you end up paying for that right because if you're if you're trying to do something serious uh and you know like you're taking the lazy step at each way it'll end up taking longer maybe costing longer too so um so it's kind of this iterative so you're asking about like the the whisper and then you kind of like learn a little bit more and then you ask it to make another plan and at some point you have a plan that you can share right yeah exactly yeah yeah so i i i did a lot of for this video recognition stuff i did a lot of like you know research into how different video algorithms worked. I think I did one on video segmentation. I wanted to put text behind a subject. And so this was something I explored and learned more about. And I ended up finding that there wasn't something reliable enough here for me to use. But yeah, I think there was just a lot of this iterative process of finding out what do I want and what is possible before I could do it. It looks like this overlay is maybe almost done, so we'll see it soon. And how about on the team? Have you got the rest of the team to review HTML? Is that a markdown? Yeah, for sure. I think everyone is different, but I think HTML Artifacts, we launched Artifacts, right? Currently, it's only on Teams and Enterprise, but hopefully coming to Max and Pro. And yeah, that's like how we share things now at the company. It's like we ask Claude to make an artifact and this can be, you know, of a plan, of a PR that we've already done. It can be, you know, like a status report, like an incident report, things like that. So yeah, it's definitely how we do it. Yeah. All right. Let's see what I generated here. Yeah, let's do it. So let's say open overlay style. Okay, so yeah, here are some of the options it's made. I think it's probably maybe indexed more on the sub-stack brand versus your brand. You know what I mean? Yeah, because I don't have a brand. Yeah, yeah, yeah. No, I think you do, right? I think you do. I think you've got the red and white. We can probably iterate on it there. But this is one of the things where I'm like, there's quite a lot of difference between these different designs, right? One of the ways I like to plan is to do this exploration, especially because I'm not a designer. I just really only know it when I see it. Got it. Just to wrap up the planning conversation, I've been writing product specs for 10 years and they usually have what's the problem we're solving, what's the solution, what's the goal, so on and so forth. But I feel like part of this stuff is read by agents now. And I feel like the different sections of your spec needs to change. Or maybe like the prospect and technical spec is like one thing. Like how do you guys do it on the team? Like you have like one session for the humans to read and one session for the agents to read? Or how do you think about it? Yeah, good question. Good question. I think that it is very tied together, right? Like I think a spec kind of can evolve even towards like planning. Like I think one of the things I think I'm showing here, let me see. Yeah, I think like one of the things that you sort of see sometimes is that when you run something, the model can find things that it didn't anticipate or you didn't anticipate when you're implementing, right? I see. This is like, I don't think of specking just happening at the start, right? It's like you start with like the human. request and then the agent does some like technical exploration it comes back maybe you do some mock-ups some explainers trying to understand your unknowns you refine that uh you give it to the agent again it might start implementing it i i ask it to keep implementation notes as it goes so that it like finds out you know like what are the you know what are things that we were not expecting about this implementation and once we have that we can actually you know respect if we need to right like it depending on how things go so yeah i think it's much less like there's like one handoff of spec to implementation and more just like back and forth process yeah yeah because i guess it's pretty cheap to build now so you can just like maybe ask people to build a simplest version of this and like there's probably a lot of bugs and issues and they're gonna keep iterating right yeah exactly or like the prototype version of this right like that's what how i think about these overlays these are like prototypes of the you know of the design right and okay um if we like uh like it then we can do the more expensive version which is instead of html we can do it in react that means you have to like you know sort of re-render the video and do all the code changes um so like what's the like smallest step you can take to prove out the concept that you want to like You prove out the spec more. I love how it takes implementation notes so the next time you start a new section, you can just refer to the HTML. It's like a living document. Yeah, exactly. Got it. What percent of your work now is done through Cloud Tech on Slack versus in the terminal or the Cloud app? Yeah, I think that the way for me it's trending is that there's a lot of parallel stuff happening in Cloud Tag. And so any multi-clotting is often happening in Cloud Tag unless there's a reason why it needs to happen locally. I think one of the things we put a lot of time into is making sure that our environment can run in remote. And so, yeah, multi-clotting is happening in Cloud Tag. Initial explorations, PR specs, trying to understand something that's happening in cloud tag. And then once I get into, there's usually one thing I'm focusing on and that's happening in cloud code. And it's like more, you know, like back and forth iterative. Right. And so, yeah, that's how I'm using it. But I think everyone at the company has sort of like different like approaches and mixes to it. And when you say like, what do you mean by multi-clouding? Oh, yeah. Just like if I have multiple tasks happening at once, especially if I'm trying to involve someone else. If I've got a PR that I'm trying to get merged, one thing I'll do is I'll ask it to babysit the PR fixed test and then tag a reviewer and my reviewer will get tagged in the same Slack channel and we'll be able to talk there. But just generally, multicloudings, like anything, any background work where before I was having, you know, like five different clods in my cloud code. Now, like it's mostly one active cloud code session and then a bunch of cloud tag sessions. Oh, interesting. Okay. And so you talk to cloud tag both through like DMs on Slack and also like in shared team channels, I'm guessing, or primary. Yeah. Yeah. In Slack. Yeah. Both in my private, like I have a, yeah, my. Tharic, Claude Slack channel where I do most of my work. And then we have team channels, like feedback and things like that where we, or like project specific engineering channels as well. That's like a common pattern we see. Yeah. I guess it makes sense because I do think like these coding apps right now are like primary single player experiences. Like you're kind of talking to the agents for different threads. And if you think about it, like the Claude app actually kind of looks similar to Slack. There's like a bunch of threads. It's just like Slack has a bunch of channels. So I guess the idea is Slack is now the multiplayer cloud experience, right? Because everyone's there already. Yeah, I mean, I think this is where it's starting, right? I think ultimately we think cloud will be this sort of proactive agent that's sort of meeting you where you are. And I think Slack is where Anthropic is, right? And yeah, it's a very natural way to explore. And yeah, it's surprisingly good at coding. There are some people who just do all of their coding almost completely in cloud tag, yeah. Maybe this is a dumb question, but cloud could easily trigger skills and stuff. But if I'm in cloud tag, do I just tag cloud and slash the skill? Yeah, you can just tell if you use the skill. Okay, that makes sense. Yeah, yeah, yeah. I think there's still UX iteration we're working on around all of this stuff. Do you agree? I feel like the future for this, because you're giving a talk on human agent interaction. I feel like the future is just like the agent is just like another employee. You got an onboarding employee. You can talk to it through Slack. You can give it a phone call. What do you think? I think it's a good question. I think these metaphors can sometimes be helpful, but also limiting in some ways. one of the things, you know, when we talk about identity is that like in Cloud Tag, every agent, every channel has its own memory, right? And so that is like, I think one choice, right? Like you could also imagine that there are like, you know, multiple clouds you tag, like each one has a different Slack identity and you're tagging them and things like that. And I'm not, like, I think it is kind of helpful to think of an agent that is like sort of has persistence and uh you know uh memory but um i think they're also different from co-workers in in some ways right but i think they're like they're proactive and like you know yeah it's proactive it has memory it has identity um but yeah it's like uh just sort of like an evolution of cloud code and i think we want to see where like you know uh where the models will uh will take us there versus sort of like putting it into a box you know Yeah, that's a good point. It definitely has a lot better memory than any human. Better and worse sometimes. It's spiky, right? Yeah, makes sense. Why don't I do something fun? I want to show you my Cloud Code setup. I think we talked about this in person. I feel pretty proud of this. I built this podcast production skill. What it does is it takes a transcript of an interview that I did. I actually interviewed your colleague, Jess. generates a bunch of stuff for me so it generates thumbnails and like stuff to cut so basically i just tag it and i paste the transcript and then it starts generating like you know click baited youtube thumbnails and stuff yeah yeah so generous and stuff and like i basically give it like my examples to try to keep it on track yeah But I guess this skill is trying to do a lot of things. I'm curious if you have any feedback. Yeah, this is cool. Can I see what it produces? The clips or like... Oh, what it produces? Yeah. So some of it what it produces is just like pure text. It's like, here's a newsletter post or some takeaways. And then I have this other skill called the video post skills. It's kind of similar to yours, but I'm sure it's not as sophisticated. But it basically takes the YouTube video for this thing. And then it extracts it. and then it gives me some ideas for clips to make yeah yeah does it do the clips as well yes it actually does so i i said do two and then it uses uh i don't actually know what it uses it uses a bunch of random stuff too too probably fmp and stuff right yeah probably fmp and then it makes a it makes a video yeah and it has captions yeah yeah that's awesome so yeah it's not perfect yeah but yeah yeah i mean um this is great how like uh how well do you feel like it matches what you want you know like or do you know like what it would look like to be better um i wish it could like add some like you know b-rolls and the stuff that you showed me like overlays and stuff like that and like i i wish it was smart enough to know how to pull in like for the video clip like um you know if i want the cloud logo or something you can just find it online yeah yeah so should i just tell clock code to do all this stuff or I think you can. Yeah. I mean, I think that like, are you working in one persistent repo or like, I think one of the things I think about is like, sometimes you want a skill, sometimes you want a repo with a lot of scripts and things that you are like, you know, like it's more of like a workspace that you're working in. Right. And like, I think of a skill. Yeah. Like, I think sometimes the skill can be instructions on how to create that workspace. Right. And so. That's something to think about because the more scripts and things you build up, the less it has to do from scratch. I have all my skills at the user level. There's a personal OS folder that has all the output and stuff. I think you can build a video editing harness here. I'm curious about the thumbnails. Do you ever use an image gen API like Gemini or even OpenAI or something like that? I found it really bad at changing my face. For example, if I have a smiling thing and then I have a shocked face, it makes me look so broad. But I think it's pretty good at like... Like, I don't know, if I give up my face and I tell you to change the background and the text, it's pretty, pretty good. Yeah. Yeah. I mean, I think Claude is quite good at, like, one of the things that Claude is good at is using other tools. So, like, you could give it, like, the Gemini or OpenAI Image Gen APIs. Yeah. And then you can ask it to look at your faces that it generates as well, you know, and sort of, like, tweak it there. So it can do this, like, interactively and progressively as well, which can be helpful, you know. Oh, okay. Interesting. Yeah. so so basically so basically what i do is i basically just chain a bunch of skills to get together like like you know cool prepare this thing and then use thumbnail and so on and so forth i feel like i i know how to use skills now but like some of the other stuff you talked about online like dynamic workflows and stuff like yeah right i have no clue yeah how would we use a workflow for for something like this right i i think like one thing you can imagine is like when you're using i i think your thumbnails example was a good one where or sorry your shorts example was a good one where maybe you want to generate 10 different shorts or five different shorts or something. Workflows are a great example for that, right? So you can like say, hey, like the main agent decides which five areas of the clip, you know, you want to like create a short for, right? And then... the workflow spins off the sub-agent for each one. You also give it maybe a rubric for like, what does a good clip look like, right? And then each one is verifying against it. And then you're getting back at the end this like, each clip has a maximum amount of compute put into it to make sure that it's matching what you want. Versus like, if you're doing two or three simultaneously sometimes, I think like, Claude might verify or put less work into any individual clip. I see. And to create a workflow, that's just how to make a workflow, basically? Yeah. Just be like, hey, create 10 clips here, use a workflow. This is my rubric to verify what a good clip looks like. And this can also be a skill. So you can package a skill with a workflow. and then the workflow is just a JS file and you can ask it to save the JS file into the skill and now you have this reusable skill that you can use. And this is a dumb question, but the main advantage over doing this workflow thing versus just using the skill is it can spin up sub-agents and keep the context clean? Yeah, one of it is context. I think the other one is laziness and verification, right? So like if you have a, you know, like a short is one example of something where you don't have a deterministic like, hey, is this a good short or not? Right. And so if you have a rubric and you have a like uh you know verification agent that reads the rubric and then it looks like oh it like hey let me review the short to make sure it's good and give feedback right uh that's something that the workflow enables as well and and we found that like you know we call it self-preferential bias like when a model prefers its own outputs it's going to be like more lenient at like um uh it's going to be more lenient at like you know verifying it so okay so basically you want to have a separate cloud doing the work versus verifying the work, right? Yeah. And in this case, like a separate cloud coordinating the work so that your main agent is coordinating it, each one doing the work and then verifying. Yeah. Okay. And this way, like the three separate clouds have like different context windows and it's not just like less bias. Yeah, exactly. And they will both all use more compute. I think like they'll put more like, you know, less likely for it to like stop early. Yeah. Think more. Yeah. Okay. Got it. Awesome dude. Well let me ask you some high level questions. Do you mostly use Cloud in the terminal or do you actually use the app? I'm a mix of terminal and desktop. Obviously we do a lot of what we call ant fooding. So it's sort of like whatever I feel like I need to test the most. Got it. Do you have any tips for like... I feel like sometimes I get exhausted. There's like five threads going on at once for five different things and then I'm just like, they're constantly paying me. It's actually worse than having back-to-back meetings in some way. There are tips for how to keep your own cuffs window clean. Yeah, I mean, this is a good question. I think that this is like my goal for this year is to be more productive but work less. you know, and so I think this is like, I think something we should all sort of be able to push ourselves on. I think that like, you know, like I think one thing we try and do is sort of like, I try to have like one project I'm focusing on, you know, and so even if there are other things that I just need to get unblocked, like I need to have this build and merge and, you know, things like and explore something, like I think one project that I'm really focusing on is very helpful just because I find that the thing that cost me the most time is when I'm like, yeah, maybe a little bit lazy and now I've like done a bunch of, I'm like sort of multitasking these things. I do a lazy prompt and then I'm like, oh, like I've wasted this time now, you know? And so, yeah, I think that there's like, just because like, I think there's a optimal amount of multi-clotting depending on, you know, who you are, what you're doing. But for me, at least it's something where like, I tend to have like one task where I'm going to eat. focusing on the most. Maybe the agents take care of the rest or something. Yeah, or even prioritization for yourself. I think it could be a good angle. Makes sense. Do you have concerns? I worry that because the agents work pretty hard and keep going. Maybe this is my problem. Like I said, I don't actually read everything that it produces carefully. So then I worry that the whole repo will just turn to slop at some point. Do you have any routines or jobs that clean this stuff up periodically? Yeah, so I mean, obviously we have things like Simplify, which Boris put out that simplifies the repo. I think it depends on what you're using it for as well. I think someone like... when you're using it for the outputs, like you're using it for the video outputs, those are pretty, like, you know, maybe the quality of the code matters less, you know, and the agents are very, like, you know, persistent and they'll figure it out. But I find organizations often more for me than the agent to sort of, like, you know, make me feel better about the workspace if I'm only caring about the outputs. But yeah, you can always just ask it to. to simplify or organize. Okay, got it. Do you try to minimize and keep the constant window clean? Do you try not to have a bunch of MCPs on or Cloudlet MD has a super long? Do you try to optimize that? Yes, I think that one of the things we've noticed, especially as the models have gone smarter, is that you know we'll be talking more about this we we cut down the cloud code system prompt by 80 percent um and the reason is that as the models have gotten smarter they need less direction they need fewer constraints and they need um fewer examples you know and so a lot of our system prompt would be like okay like here's the bash tool here are like five examples of using the bash tool never do it in these cases right and um the models are now kind of aligned enough that they know like hey uh we don't need to, like, we don't, the examples are almost constraining it, you know, because now it's like, oh, like, you want things like this example. And so if you remove the examples, it actually can be more free format. And like, the constraints can also constrain it too, because like, you oftentimes when you say never you don't really mean never you just mean like most of the time don't do this and if you give it the reason you don't want to do it instead that can be more effective than the like don't do this constraint so I think that like all this to say is that like you want to trim your context I feel like claw.mbs are probably too long right now and you probably want to shorten them more and more right so probably a lot of skills are too long um i think mcp is you know depends on the mcp i think like obviously some of them can take up a lot of context but i think a lot of the mcp team has put a lot of work into this to you know make it better with tool search and things like that so but yeah definitely cloud.ind is like any sort of instructions the models just need like more room to run oftentimes yeah then do you like instead of saying like uh you know like for example let's say writing a twitter post like instead of saying like hey make sure it's like 280 characters or less and do not do this like do you give it like more like principles to follow like you know like how do you prompt it then like is it more like yeah i think a twitter post is a good example where you might give your give it context on yourself so you're like hey i am you know i work on cloud code i'm anthropic uh this is sort of like some of yeah some of the principles we follow obviously 280 characters are still like a good like sort of constraint because that's like it does need to happen, right? But you can even just say it's a tweet and it will like sort of know, or this is a good example where you might say like, hey, keep it under 280 characters, but let's say that maybe there's a version of it that's better as a tweet thread with two tweets, you know what I mean? And so like in giving it the sense of like, hey, I want to write a tweet thread. I'd prefer it to be one tweet, you know? Gives it more freedom and flexibility, yeah, to find something good. Okay, got it. Okay. And then let me ask this. So Boris has been saying coding is a solved problem, right? And I feel like there's becoming more technical these days is a little bit... I guess my question is for someone like me who wants to actually learn how to work with agents more to actually learn what they're doing, how do you actually become more technical? It's not about the syntax or anything, right? Is it just using it more or how do you... Yeah, I mean, I think the first step is motivating yourself to learn things. You know, I mean, I think that is like, honestly, really hard. And like, I find myself doing this as well, where like, you know, if you don't need to learn something to get the job done, maybe you won't, right? But I think that like, it is really important. I think the goal of learning to be more technical is to know my unknown unknowns right and so there are some things that like being technical and knowing the syntax of TypeScript is not really very helpful you know but I think like being technical and knowing like okay like hey What are the like trade-offs of different backend services and what are the different video encryption libraries and how do they work and what's the difference between a local or remote video encryption or transcription library, right? These are all like I think pretty helpful, right? And so I think oftentimes I'm trying to learn the constraints of the system. right? And so like what is possible? How is it doing it right now? How good could it be? You know, like what if we did something else? And Claude can often brainstorm and teach you this if you like push it, right? But you really do have to push it. I think like this is like, you know, just the hardest thing about education and what everyone says is sort of like it feels good to like try and learn something, but like actually learning something is more work. It should feel like work. I think Kaparthi says this a lot. Education should feel like work more than fun. Yeah, that's actually really cool. For example, the video thing, it's actually easier to just keep prompting cloud to just do it and then look at the output and then not actually learn anything, dude. Just go figure it out and then it figures out. But the fact that you actually generate these pretty detailed HTML reports and read them. I think it's probably the exception to it. I think most people don't do this. Yeah, I mean, I think it's something I'm trying to push. Yeah, but like, I think that like, this is how you can learn to make just like... I think the question for you is like, okay, like how do you go from making good shorts to making like really like the best shorts, like highest production quality shorts out there? You know what I mean? And I think if that's the goal, right? Like I think you need to like then sort of probably learn more about like both about video production and editing and like the technical concepts, right? And then push yourself that way. And I think that like, I think we all want to push ourselves towards like being better and faster and not just faster. Yeah. Okay, so maybe I'll add some custom instructions to my cloud. Be like, hey, make sure you generate HTML reports for everything so I can read them. Yeah, yeah, yeah. Well, I mean, you know, yeah, I think it's something you want to push yourself to as well, you know, to like figure out when you want to understand if something is working. Got it. Awesome, man. Thank you for giving the gift of Cloud Code to all of us. And yeah, really excited for what's next, dude. I don't know if you probably can't share anything, but you know, really excited for what's next. A lot of what's next is called tag. It'll keep getting better, but I think it's just something that it's hard for us to understate how much it's changed to work at Anthropic here. So excited for everyone else to get on board or to try it out. If you have a really capable employee, you're not going to micromanage them, right? You just tag them on Slack and they can't do this. Yeah, totally. Or you want to talk iteratively with other people and collaborate. You should build it to a point where I can walk by Claude's desk and ask some questions. Yeah, like a robot. That could be a hack project for you. I feel like you could already do that. Cool. All right, Tharik. Really great chatting. I think people know where to find you online, so I don't think we have to talk about that. Sounds good.

Thariq works on the Claude Code team, and I’ve wanted to see how he builds for a long time. In our episode, he showed how to use /goal to keep Claude working, how he plans with Claude to remove unknowns before building, and how he runs a team of agents in Slack. He also shared why his team cut Claude Code’s system prompt by 80% and how he creates polished launch videos with Claude.

Thariq and I talked about:

(00:00) Goals, loops, and workflows to make Claude work longer
(04:48) Live demo: Creating a polished video with one prompt
(08:17) Plan by removing unknowns before you build
(14:32) How Anthropic uses HTML artifacts for planning
(18:35) Running parallel Claude tasks through Slack
(27:34) Using separate creator and verifier sub-agents
(31:08) How Thariq stays focused while Claude works in parallel
(34:07) Why Anthropic cut Claude Code’s system prompt by 80%
(37:01) How to become more technical when AI writes the code

Thanks to our sponsors:

Riverside: All-in-one AI studio for podcasts and video https://creators.riverside.com/PeterYang

Linear: The AI agent platform for modern teams https://linear.app/behind-the-craft

Wispr Flow: 4x faster than typing with your voice https://ref.wisprflow.ai/peteryang

📌 Get the takeaways: https://creatoreconomy.so/p/how-i-plan-build-and-run-loops-with-claude-code-thariq-shihipar

📌 Get my personal AI OS with useful AI skills, $270 in AI tool credits, live monthly workshops, and courses on Hermes and Codex agents: https://www.behindthecraft.com/

Where to find Thariq:

LinkedIn: https://x.com/trq212
Website: https://www.thariq.io/

Subscribe to this channel - more interviews coming soon!