A 3-step AI coding workflow for solo founders | Ryan Carson (5x founder)

Summary

Podcast Summary: How I AI – Episode: A 3-step AI Coding Workflow for Solo Founders | Ryan Carson

Host: Claire Vo
Guest: Ryan Carson, 5x Founder
Release Date: May 26, 2025

---

Introduction

In this episode of How I AI, host Claire Vo welcomes Ryan Carson, a seasoned entrepreneur with two decades of experience and five successful startups under his belt. Ryan shares his innovative 3-step AI coding workflow tailored for solo founders, emphasizing practical strategies to leverage AI tools for enhancing productivity and efficiency in startup environments.

---

1. Emphasizing Context in AI Interactions

Ryan begins by highlighting a common mistake among users: rushing through the context provided to AI tools. He states, “I think the biggest mistake that I do, that everyone does, is they try to rush through the context where you just don't have the patience to tell the AI what it actually needs to know to solve your problem” (00:00). Ryan stresses the importance of slow, deliberate input to maximize the effectiveness of AI assistance.

Key Points:

• Patience with Context: Taking the time to provide detailed information ensures AI can better understand and address the problem.
• Hands-On Learning: Ryan advocates for actively engaging with AI tools to discover what works best through experimentation.

---

2. Structuring the AI Coding Workflow

Ryan outlines his structured approach to using AI, which involves creating Product Requirement Documents (PRDs) and detailed task lists to guide the development process.

Creating PRDs:

• Ryan uses AI to generate PRDs, ensuring they are clear and actionable.
• He mentions, “This is the way people are going to pay attention” (03:17), emphasizing the strategic use of AI in project documentation.

Generating Task Lists:

• Utilizing AI to break down PRDs into manageable tasks.
• Ryan explains the importance of a linear, step-by-step process to prevent getting sidetracked: “No matter what, just start small, start simple and get good at that” (21:43).

Notable Quote: “Nobody really knows how to do this stuff. The only way you're really going to figure it out is by getting in here and getting your hands dirty and see what works.” – Ryan Carson (00:00)

---

3. Leveraging Cursor for Development

A significant portion of the discussion revolves around Ryan’s use of Cursor, a VS Code fork, to streamline his coding workflow.

Demonstration Highlights:

• PRD to Task Conversion: Ryan showcases how he uses Cursor to convert a PRD into a structured task list automatically.
• Agent Mode: By utilizing different AI models (e.g., Claude 3.7 Sonnet, Gemini 2.5 Pro), he demonstrates how AI can assist in generating and managing tasks efficiently.

Key Features:

• Rule Files: Ryan has created specific rule files that instruct the AI on how to generate PRDs and task lists, such as specifying the task list format with checkboxes for easy tracking.
• Iterative Process: After generating tasks, Ryan iterates through them, ensuring each subtask is addressed before moving on to the next, maintaining control over the development process.

Notable Quote: “As you code and encode and code with AIs, you start to realize that they're like a genius PhD student. But they can't seem to connect these really simple, obvious things that you and I know.” – Ryan Carson (05:40)

---

4. Integrating MCPs (Meta-Command Prompts)

Ryan discusses the integration of MCPs to enhance Cursor’s functionality, allowing the AI to interact with other applications seamlessly.

Use Cases:

• Postgres Integration: Enables Ryan to query the database without writing SQL, simply by instructing the AI.
• Browser-Based MCPs: Automates tasks like navigating websites or performing frontend testing, reducing manual effort.

Benefits:

• Reduction of Toil: Consolidates multiple tools into a single interface, minimizing the need to switch between applications and manage numerous tabs.
• Enhanced Automation: Streamlines repetitive tasks, allowing Ryan to focus on more critical aspects of development.

Notable Quote: “AI meeting notes are a game changer. The summaries are accurate and extracting action items is super useful for standups, team meetings, one on ones, customer interviews and yes podcast prep.” – Claire Vo (14:24)

---

5. Managing Context with Repo Prompt

To address the limitations of context windows in AI models, Ryan introduces Repo Prompt, a tool that allows precise control over the information fed into the AI.

Functionality:

• Selective Context Inclusion: Enables Ryan to include only relevant parts of his codebase, optimizing the AI’s focus and response quality.
• Customization: Allows for tailored prompts that guide the AI to perform specific tasks, such as improving code maintainability.

Advantages:

• Reduced Black Box Effect: Provides greater transparency and control over what the AI "knows," leading to more reliable and relevant outputs.
• Scalability: Prepares the workflow for future advancements in AI context management as models evolve.

Notable Quote: “Nobody really knows how to do this stuff. The only way you're really going to figure it out is by getting in here and getting your hands dirty and see what works.” – Ryan Carson (00:00)

---

6. Personal Productivity and Workflow Enhancements

Ryan shares insights into his personal workflow, emphasizing the importance of maintaining productivity while managing a multitude of tasks as a solo founder.

Workflow Tips:

• Commitment Strategy: Ryan commits to his codebase after completing significant tasks, ensuring milestones are met without overwhelming the system.
• Tool Integration: Seamless integration of various tools like Cursor, Repo Prompt, and MCPs to create a cohesive development environment.

Notable Quote: “I have been hounding the Cursor team non-stop like why don't you just build this into the core developer experience of the app. I don't understand why this isn't just the way you use cursor.” – Ryan Carson (14:05)

---

Conclusion and Final Thoughts

Ryan Carson encapsulates the transformative potential of AI in the entrepreneurial landscape. By implementing a structured AI coding workflow, solo founders can significantly enhance their productivity and build robust companies with fewer resources. Ryan’s approach demonstrates that with the right strategies and tools, AI can be a powerful ally in overcoming the complexities of startup development.

Final Notable Quote: “I am able for sure to build this company by myself. And I mean you're doing this with Chat PRD. I mean it's bonkers to me that it's actually possible.” – Ryan Carson (33:08)

---

Where to Find Ryan Carson

• Website: ryancarson.com
• Twitter/X: @RyanCarson

---

This episode offers invaluable insights into integrating AI into the startup workflow, making it an essential listen for solo founders and entrepreneurs looking to harness the power of AI to streamline their operations and drive success.

Transcript

[Ryan Carson]

I think the biggest mistake that I do, that everyone does, is they try to rush through the context where you just don't have the patience to tell the AI what it actually needs to know to solve your problem. And I think if we all just slow down a tiny bit and do these two steps, it speeds everything up. Nobody really knows how to do this stuff. The only way you're really going to figure it out is by getting in here and getting your hands dirty and see what works.

[Claire]

That's a place where so many engineers and product managers get stuck in a loop like who's going to take this PRD and actually break it down in the right steps? So even just this, this is such a timesaver for people building products, building.

[Ryan Carson]

This new startup, I literally feel like I'm able to do all of it. Am I able to do it as well as a dedicated product manager? No. Am I able to think as deeply as a cto? No. But I am able for sure to build this company.

[Claire]

This is the way people, I'm telling you, pay attention. Welcome to How I AI. I'm Claire, product leader and AI obsessive, here on a mission to help you build better with these new tools. 2025 is definitely the year of the Vibe coder, but you can't always vibe your way to a scalable execution strategy. In this episode, ryan Carson, a five time founder with 20 years experience, shows us how he brings PRDs, task lists and some advanced prompting techniques to Cursor to make sure he's not just vibing, he's building the right things. Let's get to it. Today's episode is brought to you by Chat prd. I know that many of you are tuning in to how IAI AI to learn practical ways you can apply AI AI and make it easier to build. That's exactly why I built Chat prd. Chat PRD is an AI copilot that helps you write great product docs, automate tedious coordination work, and get strategic coaching from an expert AI CPO. And it's led by everyone from the fastest growing AI startups to large enterprises with hundreds of PMs. Whether you're trying to vibe, code a prototype, teach a first time PM the ropes, or scale efficiently in a large organization, Chat PRD helps you do better, work fast and we're integrated with the tools you love, v0.dev, Google Drive, Slack, linear Confluence and more so you don't have to change your workflow to accelerate with AI. Try ChatPRD free at ChatPRD AI Howiai and let's make product fun again. Hey Ryan, it's nice to have you here.

[Ryan Carson]

Thanks. It's exciting to be here. I've listened to every episode so far and I'm honored to be here myself. I can't wait.

[Claire]

So I'm going to start with an easy question, which is what are the last three things you built with AI?

[Ryan Carson]

I don't know if you call constantly using ChatGPT with your kids building something in AI. I feel like I'm the constant AI coach in our family and I'm always delighted actually with what our kids are doing. And because of that, my amazing 14 year old kiddo Devin, he said, dad, like, you know, I've been thinking about this game and I said, well like let's build it. And so we're building a primitive little side scroller and he's like the creative director. So, so fun. So that's sort of thing one and thing two. I would say thing three is the startup I'm building, which is just this huge amount of work where I'm coding. But then there's just all sorts of little quick things of Vibe code, you know, all the time.

[Claire]

So all day, every day, all day, every day. ChatGPT and vibe coding. I'm going to make us all T shirts and have a T shirt. Okay. So one of the things that I think you do really well compared to other Vibe coders is you bring some structure to the process. You're quite wise about how you use cursor and so I'd love for you to pull up your screen and show us how you get cursor to follow a plan.

[Ryan Carson]

Let's do it. So the reason why I do this is because I've been coding and coding, coding with AI and you just learn as you do this that you really have to get good about context, what you're showing the AI, what you're asking the AI to do. And you end up cutting back all the things you're doing to a manageable amount of things that the AI can actually do. So the process I'm going to show you, I'm in cursor now in case you're listening to the show, you can download it for [e-mail] it's basically a VS code fork, right? So if you ever use VS code, it's a great tool. So what I've done here is open up a basic project that I Vibe coded yesterday just to kind of show you what's going on. This is a stupid little CRM tool for a yacht club. Because I thought that would be kind of funny. So there's that. So, all right, so say that you want to make a change in here and it's a bigger change than just a small, you know, a quick, hey, will you change this thing? Say it's larger. All right, so you would probably want to create a product requirement doc, right? Like prd. And if you're watching the show and you don't know about Claire's chat prd, absolutely. Check it out because it's amazing. But if you need a lighter lift, then here's what I do. So I've created three files over here in my Cursor rules folder and I'll walk you through what they do and how they work. I've also open sourced these and so we can throw those a link in the show notes for you to grab that. So the first one is a simple instruction for the AI to create a product requirement docs. Again, Claire knows everything about this and lives this and breathes this. But to a lot of people that don't know about PRDs, right. It's how you describe a feature that you're wanting to build. And so this rule explains the AI how to write a PRD for the user. So the way you use this is very simple. Right. So I'm going to go over and.

[Claire]

I want to pause really quickly because I love your initial prompt which says this is a PRD that's suitable for a junior developer to understand and implement this feature. That's such an interesting little call out.

[Ryan Carson]

Yeah, well spotted because again, as you code, encode and code with AIs, you start to realize that they're like a genius PhD student. Right. But, but they, they can't seem to connect these really simple, obvious things that you and I know. And so saying junior developer is kind of a way to instruct the AI. Let's keep this at a certain level.

[Claire]

Yep.

[Ryan Carson]

You know, we've got some process, we've got some clarifying questions. You'll see this in action. I'll actually run it.

[Claire]

Great.

[Ryan Carson]

So let's do that.

[Claire]

Great.

[Ryan Carson]

So I'm going to include this file which puts it in the context window and then I'm going to give it a simple instruction which I've pre written, which is I'd like to add a report that shows me all the boat names of members and how many emails they've been sent. This is a big deal. If you're in a yacht club, you.

[Claire]

Have a lot more fun use cases than I do for vibe coding.

[Ryan Carson]

I try, you know. So let's see what happens. So I'm going to go and hit Go. We're in agent mode. For those of you who are astute, you'll notice I'm using Claude 3.7 Sonnet in Max mode. I actually tend to use Gemini 2.5 Pro. And it's funny, I didn't notice that had selected that, but fine, I'm now.

[Claire]

A default 03 girl.

[Ryan Carson]

Ooh, ooh, we'll have to talk.

[Claire]

Yeah. And then when O3 gets stalled out, I go to 3.7 Sonic.

[Ryan Carson]

Right, right. It's funny, I'm pretty much default Gemini 2.5 Pro. I love the max mode. It is sort of expensive. I probably spend maybe 3, 400 bucks a month. Uh, but, you know, worth it. That's okay. Okay, so what we've got here is the AI came back and gave us some clarifying questions on the prd. I'm going to answer a couple of these just to. To show you how this works. So if you're listening along, the AI has said, okay, great, I'll help you create a prd. I have a couple questions for you. The first one is, what is the problem this report is. Is trying to solve? Well, we are. What problem is this? We're trying to give visibility into how many emails people are getting. All right, so that's thing one. Let's go. Let's answer the second one. Who specifically will be using the report? All right, we'll say admins. Where should this report be accessible? You pick. And so there's a couple. I would say there's probably too many questions in here, but one of these things, again, that I want everyone watching to kind of get used to is you'll notice in this PRD rule file, I've done something specific here where I've said I want these questions to be dot notation, where it's 2.1 and 2.2, because you end up. Otherwise the AI would just give you a bunch of questions and it would put. It would put more than one question in a bullet point and it becomes hard to use. So you kind of get used to this specificity. Right. So I'm just going to say the rest. Make your best judgement.

[Claire]

I do the exact same prompt. I say you pick whatever you think is best.

[Ryan Carson]

Yeah, because I'm kind of lazy. Right. So, all right, so let's do that. So it's going to fire up and start creating this prd. Now, what I've chosen is, is, you know, over here I've got a task folder PRD in there and then we're going to generate a list of tasks in a minute. So it says, okay, great, I'll now create it and it's generating it. So that will happen in a minute. I'm going to actually nip over to my browser because I do want to show you a couple other interesting things. So first of all, this is my amazing yacht club member of the app that we just five coded. Now we're going to pop this in the link, but this is the repo that has these prompts in it. We'll give those to you. But there's this really cool open source tool called Taskmaster. This is open source, it's completely free and it's like a hyped up version of what I'm showing you. So it runs as a command line interface tool. It's great. It actually was too much for me. I wanted less. Less power, less control or less power, more control. So this is a great alternative to that. So I'm going to head back into.

[Claire]

Cursor just to kind of recap where we are so far. So you have a cursor rules files that gives rules and instructions for generating a prd. You generate the PRD in agent mode using whatever your preferred model is. That puts that PRD markdown file in a tasks folder that you've put in in your repo. And now we're going to look at that PRD and show how you work through it to build something.

[Ryan Carson]

Exactly. Okay, you're a good student. So here is our prd. It's pretty straightforward. If you've ever looked at a prd. I'm going to show you. So you've got functional requirements, non goals, design considerations, et cetera. Right, and let's back up, like what are we doing here? What we're doing is making it clear to the large language model what we want done. I think the biggest mistake that I do, that everyone does, is they try to rush through the context where you just don't have the patience to tell the AI what it actually needs to know to solve your problem. And I think if we all just slow down a tiny bit and do these two steps, it speeds everything up. Right, so we've got a prd. It's not rocket science here. Now next, what we want to do is generate tasks for this. So let's go and generate the task based off this prd. So if you're listening, I'm back in cursor and I'm including the file that generates the task. It's called Generate Tasks. And I'm going to say please generate tasks tasks for. Then I'm going to tag the prd.

[Claire]

Got it. So this is another rule, probably similar to your generate prd, one that explains what a task is and how to do it well. And then you're giving it the context of the PRD itself.

[Ryan Carson]

Exactly. So let's have a quick look at the generate task list. So the goal is to guide an AI assistant in creating a detailed step by step task list. This is what I want the list to look like. This is the process you'll see. It's going to ask me a couple questions and it's going to pump out tasks in this format as a markdown file.

[Claire]

I have to ask, how did you create these rules? These. It's a lovely prompt. It's well structured, it's clear. How did you get good at writing.

[Ryan Carson]

These instructions prompts the same way you did, basically. I tried a couple things. They didn't work. I got more specific and then of course, you know, I had a very intelligent LLM write this for me and then I edit it. You know, again, you sort of learn some of the tricks of the trade. Like, I want this task list to be in markdown and I want, I want there to be checkboxes so we can check them off. I mean, silly stuff like that. So the biggest thing I want people to walk away from the show is, you know what? Nobody really knows how to do this stuff. The only way you're really going to figure it out is by getting in here and getting your hands dirty and see what works and then stick with a model that you consistently like. Like, I'm getting to know Gemini 2.5 Pro really well, like what it's good at, what it's not good at. So let's see what it's good at. All right, So I just said, please generate tasks for this prd. I tagged the file. We're using a reasoning model, so we're seeing the thinking tokens kind of whiz by.

[Claire]

And all this thinking might cost you a little bit more, but you get a little bit more visibility, you learn more, and looks like it's doing a good job.

[Ryan Carson]

Amen. Yeah, I feel like for the extra 5 cents, like, this is absolutely worth it. So in, in this instruction, it, it, the instruction is give me some basic tasks and then ask me if they're okay and then tell me to go to proceed. So you'll see it says ready to generate the subtasks respond with go to proceed.

[Claire]

You know, as I'm looking at this side by side, what I really like about your generate tasks instructions is you've given it in a very explicit process. It's you get this file, you do step one, you get this next step. And it's not quite an agent, but it really brings in this like agentic thinking of where are the decision points, where are the user interaction points. But in sort of more this linear step by step chat mode.

[Ryan Carson]

Exactly. And I have been hounding the Cursor team non stop like why don't you just build this into the core developer experience of the app. I don't understand why this isn't just the way you use cursor. And they keep saying we're doing it so.

[Claire]

And for those listening that delightful is when cursor is done generating.

[Ryan Carson]

Isn't that the best? I love that.

[Claire]

I love it. This episode is brought to you by Notion. Notion is now your do everything AI tool for work. With new AI meeting notes, enterprise search and research mode. Everyone on your team gets a note taker, researcher, doc drafter, brainstormer. Your new AI team is here, right where your team already works. I've been a long time Notion user and having using the new Notion AI features for the last few weeks. I can't imagine working without them. AI meeting notes are a game changer. The summaries are accurate and extracting action items is super useful for standups, team meetings, one on ones, customer interviews and yes podcast prep Notions. AI meeting notes are now an essential part of my team's workflow. The fastest growing companies like OpenAI, RAMP, Vercel and Cursor all use Notion to get more done. Try all of Notion's new AI features for free by signing up with your work [e-mail] howiai so we're going to accept those changes.

[Ryan Carson]

We're going to hop over here and let's just kind of see what it did right. So.

[Claire]

Oh wow.

[Ryan Carson]

I know, it's fun, isn't it? So what you've got up here is the relevant files. Now this is a trick I learned from a friend on X where my thinking here is that this should help the LLM just remember what files are we really focusing on. Even though I will specifically tag these in the context, I think it's helpful. One of the things I want briefly touch in I probably anthropomorphize LLMs, probably too much, but because they're trained on human output on the web, you know my Belief is we need to give LLMs like the right context and be as helpful as we can so they can actually solve our problems. Right.

[Claire]

I, I completely agree. I'm also very polite to, to the LLMs. So I get people to people to do work. It's how I'm going to get the agents to do work.

[Ryan Carson]

Right. So why wouldn't you, you know, be treat an agent like you would treat a human. That's the way I do it.

[Claire]

So I agree.

[Ryan Carson]

All right, so then we've got, you know, pretty detailed list of tasks, right? We've got 1, 2, 3 for with subtasks. We've even got sub subtasks here. And then we're going to start iterating on this. So here's how it works. I've got another rule called task list. How much? Probably need to rename because that doesn't really make sense. But this is the instructions for iterating through these tasks. So I'll kind of walk you through that. So this is task list management. These are guidelines for managing task lists in markdown files to track progress, the task completion. We want to do one subtask at a time. Like this is really important that the AI doesn't start trying to do all the tasks. When you finish a subtask, immediately mark it as complete and then you'll see. I say stop after each subtask and wait for the users. Go ahead. And that's just a little bit more clarity here.

[Claire]

If people see me shaking my head, it's because I am realizing now I'm using cursor like such an amateur. That substitute. I doubt that this is so good. I'm just floating through the ether saying, you know, 03, take me away. Maybe I'm, I'm overconfident in my product management skills and so I'm putting this all into the chat. But this is, this is the way people, I'm telling you, pay attention.

[Ryan Carson]

I appreciate that. I mean, I think the answer is yes to both those. I mean, sometimes you do just need to roll and see what happens. But I'm learning over and over that if I don't follow this process, I end up down some rabbit hole and I have to revert. Right. So let's go ahead and continue here. What I'm doing now is I'm tagging the task list rule which tells the AI how to act. And then I'm going to say, let's start. And then I'm going to tag the.

[Claire]

Tasks, the task list. So we got a PRD we got a task list, and now we have a set of rules that knows how to work through a task list and actually get work done.

[Ryan Carson]

It does. Exactly. So, all right, so let's start. It's going to think about it, and it's looking through this big list of tasks right now. And so what it's saying is, okay, let's start the first subtask. Define Prisma schema email campaign. I'll start by reading the existing Prisma campaign. Okay. See, existing. Blah, blah, blah. You know, so it's just thinking it through and boom, it has checked off.

[Claire]

1.1 with a delightful noise. I have a question. Are you hooking it all into Git? How are you doing sort of the change management here?

[Ryan Carson]

Yep. So what I tend to do is I will commit after I finish either one of the bullet, one of the. One of the parent tasks if I feel like the app is in a state that it's workable.

[Claire]

Yep.

[Ryan Carson]

I will commit at that point.

[Claire]

Got it.

[Ryan Carson]

If I don't, I won't commit until all of these tasks are done.

[Claire]

Oh, wow.

[Ryan Carson]

Which, you know, is probably, you know, half a day of work. You know, you kind of get used to, like, oh, all right. If I had to revert now. Yeah. How bad would it be?

[Claire]

Yep.

[Ryan Carson]

And I try to think about, well, what would I need to undo? So it said, all right, shall I proceed with subtask 1.2? And I'm going to say yes. Sometimes I'm really lazy and I just say, why, as in the letter Y. So it's just going to keep working. Now, we don't need to go through this whole thing, but I just wanted to show all of your amazing listeners and audience this is a pretty easy process to follow. And I've built huge features with this. I mean, you know, 10,000 lines of code reliably and almost never had trouble. I still feel like this human in a loop part is really important, where after each task you are kind of checking what's happening. I've noticed that it often does introduce some small problem or there's a linter, you know, error, and then you got to go fix it. So.

[Claire]

And, you know, this is great to get the actual engineering work done, but if I just take a step back for product managers out there that don't know where to get started with cursor, even if you just did the PRD task list part. I'm looking at this task list right now, and it's got basically, like, epics and tasks in it, and that's A place where so many engineers and product managers get stuck in a loop like who's going to take this PRD and actually break it down in the right steps that are going to work in our code base. So even just this is such a time saver for people building products?

[Ryan Carson]

I think so. And now you can over engineer this process. You know, this is literally a markdown file. It's somewhat hand cranked. You know, I thought, oh, maybe I'll use, you know, Asana's mcp, you know, server and create Asana tasks and yeah, and I was like, no, like it's actually easier for me just to see a markdown file and know what's happening and I can even add tasks to it. So my encouragement to everybody is just start small, start simple and get good at that and get comfortable at that and then you can graduate from there.

[Claire]

And 30 chime noises later we are going to have a report about your yacht club. That's right, emails. I mean, speaking of mcps, are you using MCPS at all in your cursor experience? How is that fitting into your workflow?

[Ryan Carson]

I am. So I'm going to show you a couple of those now. I wasn't using many at the beginning and then the first MCP I started using was for postgres because it's really useful to ask the AI, hey, can you go see if this data is actually in the database? So I started that and then I've gone down the rabbit hole. So I'm going to show you a couple MCP servers that I think are really useful. So let me go ahead and share my screen. Okay, so what you are seeing now is on the left I've got browser base, it's the actual backend. I've got a free account so I just want to try this out and see how well it works. I'm going to show you the fun that you can do with an MCP here. So on the right I've got cursor and I'm in my cursor settings and I go to MCP and you'll see down here I've got a browser based mcp.

[Claire]

Yep.

[Ryan Carson]

Which I've set up. I've got stagehand as well, which is really fun. So let me show you how this works. So we're going to go back into sort of new chats on agent mode and I'm going to say navigate to chat PRD and take a screen grab. Now let's see if the MCP gods cooperate because I did this this morning and I was like, wow, this is super cool. Okay, so what we should see over here in a minute. Let me refresh this to see it did. Oh, my God, this is so cool. Okay, so in the cloud. Ooh. So what I'm doing is controlling a headless browser in the cloud from Cursor.

[Claire]

The future is now with Bonkers.

[Ryan Carson]

Well, it's like, okay, what use is this? Like, that's kind of cool. I mean, let's actually do something kind of fun. So I'll say navigate to pricing. Okay. So we should actually see the cursor move over here in this headless browser in the cloud.

[Claire]

You're just showing off at this point.

[Ryan Carson]

I just learned this this morning and I was thinking, oh, my God, this is so neat. Let's see if it actually works. Yep, there it goes.

[Claire]

Whoa.

[Ryan Carson]

So again, well, besides kind of a parlor trick, like, what actual use is this? I think it's going to unlock a huge amount of front end testing for me. Yeah, right. So as you know, like, it's really kludgy right now trying to squash bugs on the front end when you're like taking a screen grab and you're pasting into Cursor and you're like, no, I mean over there. So now we have this ability to start automating sentence behavior right inside Cursor. So that was kind of fun trick. I thought I would show you now. If you're watching this, you're like, what it really what we're doing here is I'll go back to the MCP part of Cursor. What we're doing is basically giving Cursor the ability to interact with other apps. Right. And so we're saying, okay, browser base is pretty cool. You can have this browser in the cloud you can do things with. I want to be able to tell the AI what to do. I don't want to have to know how to call the APIs and do all that stuff. So that is what I thought was a lot of fun.

[Claire]

And can you walk us through just a couple of the use cases of the ones we're seeing here? So browser base lets you basically browse the web and do a couple things through the text window in Cursor. What are some of these other ones that you find useful?

[Ryan Carson]

So Postgres is probably the one I use the most. So this for the startup I'm building, I'm using Postgres for the database in Vercell. And there's just a lot of times where I just want to be able to Tell the AI, is this value in this row in the database? I don't want to have to actually write SQL to do that. So you can go right into the chat window and just say, hey, use the Postgres tool and tell me if this is in the database or not. Which is really cool. Prisma I'm using for this Play project, which is fun. Same with SQLite. So the one I use every day is Postgres.

[Claire]

And one of the things that I love about AI, especially in the sort of dev tools stack, is it just reduces toil. And one of the pieces I feel like is toil for engineers is how many tabs you have to have open to orchestrate working across your task list. Right? You have to have your project management software open so you know, like what task I'm working on and what's next. You have to have your browser open so you can do some work. You're querying your database and all this puts it in a single interface that you can seamlessly switch through in natural language.

[Ryan Carson]

Amen. So I do want to show you one tiny, quick other tool. And I know we're almost out of time.

[Claire]

No, let's do it.

[Ryan Carson]

So you're probably hearing over and over, everyone's listening or watching me, preaching about context. It is just so much more important than I think we understand. And again, if we anthropomorphize, it's like, well, how would you expect anybody to do anything unless you give them the right book or the right piece of paper, right? And so I've started to use a tool called Repo Prompt. Again, I don't have any financial reason to say this. I don't own any of this company, but it's this really great tool for Mac, and I just want to show you how to use it really quick. The question is, why? Like, why would I just use Cursor? Well, the thing about Cursor is there's all this magic happening in the background with the context, where you don't know for sure what is in the context unless you tag it right, which is fine. But they sort of magic that away. And sometimes you really, really want to control the context. So what I've done is I've opened repo prompts. I've got the site on the left, and on the right, I've got the ui and I've opened up the How I AI project, which is that Simple Yacht email app. Okay, so say that I want to throw a lot of these into a prompt to do something. So if I Select the whole repo. Let's go over to compose. Down here. You can see how many tokens that is. All right, so that's 395,000 tokens. Okay, that's way. That's way too many. So let's go ahead and reduce that. So, all right, I know I want some stuff in the app folder. All right, why is it so big? Now we're at, you know, 324,000, still too big. So I think it's probably generated, so you get rid of that. Okay, good. Now we're at 12,000 tokens. So the point is, if you know what context you want, repo prompt is a really powerful way to do that. So I'm going to go ahead and select components Lib. Let's open up the schema for Prisma and scripts. All right, now what? So I go up here and I put in a prompt. How can I improve the maintainability of this code? Then you can do some other neat things like I want to include a stored prompt and I'm going to use the architect version. Now what is that? Well, that is a prompt that repo prompt has written already with a bunch of power moves in should act like an architect versus a dev. Now I go down to copy and I'm going to say I want to include the saved prompts, want to include the files, and I want to include the user instructions. And I'm going to click copy. Now what? Well, I'll show you. So let's go over to O3. Now I could, I could go over to cursor, but I don't know exactly what cursor is going to do to my context. Instead, I'm going to paste it in here. Now what is this? What you've got. Let's start at the bottom. It's basically putting everything in XML tags, right? So you've got user instructions. So that was the prompt I put in. Then the meta prompt is telling it how to execute the prompt and the files that it's including. Let's go up here. So, file contents. This is kind of the key. So each file is included and it's demarked specifically like this. So it says the file with the actual path and it's. So it basically it's very specific. It's saying to the AI, this is exactly the context you need and it's super clear. And then you can execute some sort of prompt on that. I do this for like, heavy lifting stuff where I used to do this all the time with 01 Pro, where I would go into repo prompt, I would select exactly the right context and then I would go into 01 Pro and say, Think super hard about this. I've given you exactly the right context. And you get amazing answers because of that.

[Claire]

Yeah. And these, these new models have such big context windows. But I'm not copying and pasting 12,000 tokens into the chat window.

[Ryan Carson]

Right.

[Claire]

But this tool just does it for you. Really interesting. And then you're getting less of a black boxier.

[Ryan Carson]

Less of a black box. Yeah. And you know, and I have a feeling that this stuff will probably go away. I think, you know, the context windows are going to get bigger. Tools like Cursor are going to get better at managing context. But right now you have to do all this stuff. You can't just wave your wand and hope the LLM is going to write all the right stuff for you.

[Claire]

That's what I've been doing. So now I have a better process to follow here. Okay. Anything else really important in your stack you need to tell us about?

[Ryan Carson]

The most important thing is this. So let me share my screen. So this is ts live set from New York City. This is how I actually code. I just turn on some EDM and late at night code after everyone goes to bed listening to amazing edm. And that is an important part of my stack.

[Claire]

So if I could ask for an additional cursor feature, it would be AI generated streaming EDM matched to the generation pace of your tokens that ends with a drop instead of that cursor.

[Ryan Carson]

I would pay extra money for that.

[Claire]

You heard it here first. Forget all this task management, context windows stuff.

[Ryan Carson]

Forget about that. I want medium.

[Claire]

Okay, we'll spend three minutes on lightning round questions. One, you're a builder, you're a founder. It's clear how this technology is changing the building part of things. How is it in your mind changing the company and the founder side of things?

[Ryan Carson]

Wow. It's a complete rewrite. So I've been fortunate to start three companies and, and see them acquired and one of them, you know, we had about 110 employees and I had a CTO and a VP of ENG and you know, product managers and you know, building this new startup. I literally feel like I'm able to do all of it now. Am I able to do it as well as a dedicated product manager? No. Am I able to think as deeply as a cto? No. But I am able for sure to build this company by myself. And I mean you're doing this with chat pd. I mean It's. It's bonkers to me that it's actually possible. So I. I just can't wait for the future.

[Claire]

I could not agree more. Okay. And then, of course, you showed us how. You're a very thoughtful and organized product manager and manager of your AI, but, you know, it sometime doesn't listen. So what do you do? What's your. What's your tactic for really getting it back on track?

[Ryan Carson]

So I'm just too nice. I. I just say, please think harder about this. Like, I know you can do this. You know, think again about it. And I'm just not a mean person. So as much as I want to say, you know, God damn it, you know, I don't.

[Claire]

I. I have a hypothesis that this is. This is actually a parenting thing, because I do the same thing. I say, I believe you can do this. I believe in you.

[Ryan Carson]

I believe you can.

[Claire]

I believe you can. Well, that's amazing, Ryan. Where can we find you and how can we be helpful?

[Ryan Carson]

I am on X all the time, so. X.com Ryan Carson. And if you want to know a little bit more, just head to ryancarson.com and that is me.

[Claire]

Great. Well, thank you so much.

[Ryan Carson]

It's been a blast. Thank you.

[Claire]

Thanks so much for watching. If you enjoyed this show, please like and subscribe here on YouTube or even better, leave us a comment with your thoughts. You can also find this podcast on Apple Podcasts, Spotify, or your favorite podcast app. Please consider leaving us a rating and review which will help others find the show. You can see all our episodes and learn more about the [e-mail] See you next time.