HTML is the new Markdown: How Anthropic engineers are building with Claude Code | Thariq Shihipar

Thariq Shihipar is an engineer at Anthropic working on the Claude Code team. He’s spent the past several months experimenting with HTML as a replacement for Markdown in planning and implementation workflows, discovering that richer visual formats lead to better human engagement—and, ultimately, better products. In this episode, filmed at Anthropic’s Code with Claude event in San Francisco, Thariq demonstrates how to use HTML artifacts to create interactive plans, build throwaway UIs for specific problems, and maintain living design systems that travel with your codebase. What you’ll learn: Why HTML has replaced Markdown as the ideal format for AI agent communication and planningHow to brainstorm in HTML to get visual mockups and interactive demos instead of text listsThe technique for building throwaway micro-UIs to edit specific parts of your planHow to create a living design system in HTML that lives in your repo and travels with every projectWhy “complexity has to earn its keep” and how HTML helps you stay in the loop without over-constraining ClaudeThe prompting technique that gives Claude flexibility while ensuring that you get what you needWhy 99% of your AI-generated tokens should go to planning, interfaces, and communication—not production code— Brought to you by: Celigo https://celigo.com/howIAI—Intelligent automation built for AI Persona https://withpersona.com/lp/howiai—Trusted identity verification for any use case — In this episode, we cover: (00:00) Introduction (02:39) HTML as the new Markdown (04:30) The compute allocator mindset (05:51) How HTML makes specs more engaging (06:48) Demo: Brainstorming in HTML with Claude Code (09:24) From brainstorm to full implementation plan (11:20) Prompting philosophy: Trust Claude but give it constraints (13:50) The future of PRDs and tech specs (18:16) Making HTML specs editable (20:23) The abundance mindset (24:17) Just-in-time documentation and throwaway software (25:39) Using plans as artifacts for implementation (26:39) Demo: Living design systems in HTML (30:16) Adding comments and annotations to HTML plans (31:42) Recap: The HTML workflow (32:21) Lightning round and final thoughts — Tools referenced: • Claude Code: https://claude.ai/code • Claude Design: https://claude.ai/design • AWS: https://aws.amazon.com/ • Figma: https://www.figma.com/ • GitHub: https://github.com/ — Other references: • Anthropic Code with Claude event: https://claude.com/code-with-claude • SpaceX partnership announcement: https://www.anthropic.com/news/higher-limits-spacex • Jevons paradox: https://en.wikipedia.org/wiki/Jevons_paradox — Where to find Thariq Shihipar: Website: https://www.thariq.io/ LinkedIn: https://www.linkedin.com/in/thariqshihipar/ X: https://x.com/trq212 https://x.com/trq212?lang=en GitHub: https://github.com/ThariqS — Where to find Claire Vo: ChatPRD: https://www.chatprd.ai/ Website: https://clairevo.com/ LinkedIn: https://www.linkedin.com/in/clairevo/ X: https://x.com/clairevo — Production and marketing by https://penname.co/. For inquiries about sponsoring the podcast, email [email protected].

Speaker names marked ? are inferred from speaking time and the show’s known hosts — they are not voice-verified.

• 0:00Speaker 00

  Markdown became a really popular way of interacting with agents, but the plans are so long, I honestly have stopped reading them. And this was honestly a mistake. I think that you still need to be really in the loop.

• 0:10Claire Vo?

  Plans matter, PRDs matter, spec matters.

• 0:13Speaker 00

  When you say, okay, Claude can run for eight hours, what you're really saying is Claude can spend 500 bucks. All of us are becoming these compute allocators now, right? And so you have to decide what is worthwhile spending the compute on.

• 0:25Claire Vo?

  People ask me all the time, Claire, you've said product management is dead, what's next? And I'm gonna say, you're a compute allocator, babe. That's the job now.

• 0:32Speaker 00

  HTML is a lot easier to read. And so it's just a richer communication medium between you and Claude.

• 0:37Claire Vo?

  Instead of saying, here's a markdown document, it was like, what's the best way to convey this information? So you can actually engage with it and pick something.

• 0:45Speaker 00

  This is the plan. It's purely in HTML. This is something that I will actually read.

• 0:50Claire Vo?

  This is not even personal software. It's like Microsoft software on top of Microsoft software.

• 1:00Claire Vo?

  Welcome back to How I AI. I'm Claire Vow, product leader and AI obsessive here on a mission to help you build better with these new tools. Recently, I was able to attend Code with Claude, Anthropic's first developer conference. And as part of that, I got to spend a little time with Tharic, who works on Claude code and taught me something that has blown my mind ever since I heard it. HTML is the new Markdown. He's gonna show us how to use Claude code to generate rich artifacts that both you and the agents can enjoy working on. Let's get to it. This episode is brought to you by Soligo. Every company today wants AI to improve how work gets done. The fastest way is building it directly into everyday business processes, automating employee onboarding,

• 1:45Claire Vo?

  keeping customer data accurate, managing orders and inventory, or resolving finance and operations issues. When AI lives inside the flow of work, it can update records, trigger approvals, route work, and kick off the next step across systems. That's how teams operationalize AI and deliver measurable results. Soligo makes this possible. And now with Soligo Aura, it's never been Easier. Celigo Aura gives you access to the entire platform through natural language, connecting your systems and turning intent into action, all of it under your control. Companies like Databricks, PayPal, and Ollipop rely on Celigo to run critical business operations at scale.

• 2:28Claire Vo?

  Ready to operationalize AI? Visit celigo.com/HowIAI. That's C E L I G O dot com slash HowIAI. Welcome to HowIAI.

• 2:42Speaker 00

  Thanks for having me.

• 2:43Claire Vo?

  I am so excited to be here at Code with Claude in San Francisco. There's a lot of exciting things that were announced, and we'll get to that in a little bit. But you told me something I was not expecting to hear today, which is, you heard it here first. HTML is the new markdown. Tell us more.

• 3:00Speaker 00

  I mean, I think markdown became a really popular way of interacting with agents, especially like, you know, Opus 4 and Claude 3.5 where, you know, they have a plan and the plan is like, how to do this feature and maybe it's like 50 lines of code and you can edit it, right? Like, I think back then you were still like, reading all of the outputs and editing the markdown and making it right. But, you know, as the agents have gotten longer and longer running, when you have Opus 4.5 and 4.7, they're running for like, an hour or something, and the plans are so long, I honestly have stopped reading them. And this was honestly a mistake. Like, I think that you still need to be really in the loop. You really need to understand what the agents are doing.

• 3:40Speaker 00

  But like, a thousand line markdown file, you know, I don't even edit them anymore. I just ask Claude to edit them instead. And so I think one of the things that I've been seeing emergently in the Claude code team is that like, they, that we're using HTML files instead. And so HTML is like, the models are still very good at it. They have a lot of more context now, so you can spend the more extra tokens. And they, like, it's a lot easier to read. Like, they can have a lot more information. They're a lot scrollable, more scrollable. And when you're talking about implementation, like, you know, sometimes you see Claude make these like little ASCII markdown things where you're like, oh, like, here's a little, you know, little mock-up and it's trying really hard. In HTML, it doesn't need to try nearly as hard, right?

• 4:23Speaker 00

  Like, there, uh, it can actually draw, like, things that you can look at. And so it's just a richer communication medium between you and Claude.

• 4:31Claire Vo?

  And before we go further into HTML specifically, I do have to pause because I do have a vested interest in this.

• 4:36Speaker 00

  Sure.

• 4:37Claire Vo?

  Which is, you are saying, for the people who are not listening, listen up.

• 4:40Speaker 00

  Yes.

• 4:41Claire Vo?

  Plans matter, PRDs matter, spec matters, even as these models get more intelligent, you still feel like that's a really important part of the process?

• 4:48Speaker 00

  Oh, 100%. Yeah, I think that, you know, everyone has different views on how it'll go, but I think that this will just forever be the thing, because when you say, okay, Claude can run for eight hours, what you're really saying is Claude can spend like 500 bucks, you know what I mean? And so if you're spending 500 bucks, or like, I think all of us are becoming these compute allocators now, right? And so you have to decide like, what is worthwhile spending the compute on?

• 5:14Claire Vo?

  Yep.

• 5:14Speaker 00

  And I think that is, happens in the spec and planning phase, right? You have to really understand, like, what do you want? And sometimes you don't know, sometimes you have to like, pull it out of yourself by chatting with Claude, uh, sometimes you have like unknown unknowns you need to figure out, uh, but yeah, I think this is like, the whole thing now is just like really getting in sync with Claude about what's building.

• 5:35Claire Vo?

  I love what you said, because people ask me all the time, Claire, you said product management is dead, what's next? And I'm gonna say, you're a compute allocator, babe, like, that's, that's the job now. You're still doing the same thing, though. You're writing documents to decide whether or not something else should do, do work in the shape of that work. Okay, so, you've convinced me HTML is the future, and I like how you said this, it's not that it is necessarily harder or easier for the agents to read, they're very smart, they can read all sorts of code, but in fact, what you're finding is that HTML makes it easier for you to engage with the content, which then uplevels the quality overall, because you're not, your eyes aren't crossing, looking at a bunch of raw markdown, being like, whatever, it's probably good.

• 6:20Claire Vo?

  Instead, you're actually getting pulled into the spec, or the document, or the plan, and then interacting it with a way that upgrades the quality, and then you can ultimately build something better.

• 6:30Speaker 00

  Yeah, that's right.

• 6:31Claire Vo?

  Okay, so you're building something with the agent, so the agent can manage you.

• 6:35Speaker 00

  You know, I'm not sure if manage me is the right word exactly, but you know, I just, I care a lot about being in sync with the agent. This is sort of like the features that I built in Claude Code have been like that, you know, like, how can I get to know you better? So, yeah.

• 6:47Claire Vo?

  Okay, great. Well, we have, we have Claude Code up, so let's walk through how that, how that works.

• 6:52Speaker 00

  Yeah, so I did like a little bit before we started. And so I like to talk with Claude just as a human, you know, and like, I always start with brainstorming. It's so much easier to brainstorm once you like, you know, uh, once you have a partner. So I was literally like, look, I'm on a Clairvoyant podcast, um, I want to do a demo, you know? And can you brainstorm some ideas in HTML file, right? And this is literally the prompt I gave it, right? Like, there's not, it's not complicated. And so here you can see the eight visual demos that it made for me. And it has these little mockups as well, right? So like PRD to working prototype, right? Like it searched you up, right? You saw that with a web search, right? Whiteboards catch to working UI, which I thought was really cool.

• 7:37Speaker 00

  This is such a cute like little thing, right?

• 7:39Claire Vo?

  Extremely cute. And I, it's what's really funny is just this morning, a chat PRD user messaged me and they're like, I love the mockups in chat PRD. And I'm like, what in the world, what are you, what are you talking about? Because I have something very similar to this in code review right now and haven't shipped it. And I'm like, did I, I like, did I act, did Claude accidentally do this? And it was that like cute little asky, you know, wireframe. So this is definitely the dream.

• 8:08Speaker 00

  Yes.

• 8:08Claire Vo?

  But not even, but now you're telling me I'm going to build it. So, so it's giving you basically, instead of saying, here's a markdown document of kind of like what you should talk to Claire about and some descriptions of things you could do. Instead, it was like, what's the best way to convey this information? So you can actually engage with it and pick something. And it used HTML to make this visual guide of a potential agenda or a set of demos. And you just get like a much richer expression.

• 8:40Speaker 00

  Yeah, exactly. Like, I think like another, like for brainstorming, one of my like, Sort of rules of thumb is that I'm not going to read a longer output than the screen on Claude Code. You know, so like if I, if you gave me eight ideas, I'm just not going to see all of them. And but with HTML, I'm definitely, I scrolled through all of these, you know? And yeah, the diagrams just make it so much more evocative for me to like sort of understand what's happening. Right? The slash command starter pack, five code of feature flag dashboard. Yeah, PRD diet. And the one I ended up liking the most was the CSV to interactive dashboards.

• 9:15Claire Vo?

  We love a dashboard.

• 9:16Speaker 00

  Yeah.

• 9:17Claire Vo?

  I used to say when I was in enterprise, I guess I still am in enterprise software, dashboards equals dollars. So I like this one.

• 9:23Speaker 00

  Yes.

• 9:24Claire Vo?

  Okay, so you use Claude Code, you said brainstorm, but brainstorm in HTML. Give me a couple of things that I can talk about. It gave you eight ideas, including visuals and this lovely like why her, what the visual is. And then the, I like the risk. It's like, it could go sideways as all good devos.

• 9:41Speaker 00

  Yeah.

• 9:42Claire Vo?

  Cam.

• 9:42Speaker 00

  Yeah.

• 9:43Claire Vo?

  And so you're going to pick one and then you're going to show us how you pull this through to a full plan on, on, on this idea.

• 9:50Speaker 00

  That's right. Yeah. So I think the, what I like about HTML is like really Claude really understands this. And so my next prompt here was really like, okay, I asked it to make some mockups in, in the follow up prompt. And then I was like, I asked it to interview me about number eight, right? And so this is something that like, you know, similar to specs and PRDs, right? Like finding out my unknown unknowns, what do I want it to do? I answered a bunch of questions. And now I'm like, okay, create an HTML file as a plan that helps me visualize what the implementation plan is. Include excerpts, mockups, code, whatever is needed to give me like maximum context, right? And so then it made me this HTML file here.

• 10:31Speaker 00

  Yeah, you can see now this is, this is the plan, but it's, it's purely in HTML. It's got like, it started scripting out the podcast itself, which you know, maybe I didn't need all of that. But like, you know, we're making a skill. And so it, you know, fleshed out the, the file system. It gave me like an excerpt of the skill dot MD. It put together like a mood board as well, some example components, some of the logic here. Yeah, insights and templates, helper scripts, right? And like helping me get a sense of like, what's the important things for me to know here?

• 11:11Speaker 00

  Yeah, this is, this is something that like I will actually read, you know?

• 11:15Claire Vo?

  Yeah. And I want to go back to Claude code really quickly, if you don't mind, which is, you know, people are going to ask, how did it know exactly what to put into the spec? And I just, I want to go back to your prompt was very simple and it's so funny. I've done, I don't know, 75 of these how I AI episodes and they get incredible outputs. And everybody's prompts like make the thing, hopefully it's good.

• 11:39Speaker 00

  Yeah.

• 11:40Claire Vo?

  Kind of nice. And so I love that this prompt is literally just create an HTML file with a plan. Help me visualize you misspelled excerpts. And you're like excerpts, mockups, code, et cetera, whatever is, is needed.

• 11:54Speaker 00

  Yeah.

• 11:55Claire Vo?

  And so I do want to encourage people, you know, don't stress so much about what should go in the thing. And in fact, it might change initiative to initiative. It might be slightly different to engage you with the work, but like identifying what you want to get. And then letting Claude, letting, letting the model do what it needs to do will do a very high quality job.

• 12:18Speaker 00

  Yeah, I, I think with prompting, it's like this fine balance of like, I think you want to give enough information that you get what you want, but you don't want to over constrain Claude.

• 12:27Claire Vo?

  Yeah.

• 12:27Speaker 00

  And so sometimes when I see people with a lot of like overbuilt skills, kind of like, you know, you're an expert planner or something, right? Like that is usually like outsourcing too much and constraining it.

• 12:38Claire Vo?

  Yep.

• 12:39Speaker 00

  But in this case, for example, like I really did want it to make sure it gave me code excerpts. And I wasn't sure if I did, uh, whether it would do that, you know? But this was really important, but then I always need to give Claude an out. You know, I always needed to be like, okay, like you asked me for this, but you know, like there's something else I want to give you. And so whatever is needed to give me maximum context is like, My way of saying like, hey Claude, I, I trust you here. I want to just like be in the loop with you.

• 13:07Claire Vo?

  Yeah, I, I love what you say, which is I trust you because my new ending prompt is not make no mistakes. Love make no mistakes, but that's not it. I, I literally like, I believe in you and trust you exclamation, exclamation, exclamation. I'm like, truly, I know you are capable and I believe in you to make these decisions. And so I, I think leaving that open ended, sort of like, whatever you gotta do, I trust your judgment. Um, at least it makes me feel like I get better outcomes.

• 13:35Speaker 00

  Yeah, yeah. I, I mean, I've loved the like recent twist on this where it's like, make mistakes Claude, you know, like fall in love, you know, like, you know, make some bad decisions. Like.

• 13:45Claire Vo?

  We need, uh, we need more happenstance in, in our life. Okay. So you built this thing. Another thing that I want to walk people through, if you pull up the plan.

• 13:52Speaker 00

  Yes.

• 13:53Claire Vo?

  Because I think about this a lot and I get people ask, that ask me this a lot, which is like, what's the future of the PRD? What's the future of the tech spec? Are these things separate? Are they together? And I think what's nice is they, whatever you want, right? And whatever you want for the audience. So you are a single builder in the instance of this demo.

• 14:13Speaker 00

  Yep.

• 14:13Claire Vo?

  You want it all in one piece. You want the product idea, you want the, I guess, you want a 12 minute walkthrough of how you're gonna demo it.

• 14:22Speaker 00

  Exactly.

• 14:22Claire Vo?

  You want code snippets, you want style guide, you want that all in one thing, because this is a self-contained little project that's easier to have it all at once. But what I can imagine in larger organizations is like, be like, put the PRD in one tab and put the tech spec in the second tab.

• 14:37Speaker 00

  Yeah.

• 14:37Claire Vo?

  Because maybe separate people would be reviewing that information. And so you can really kind of like craft a ideal spec package.

• 14:47Speaker 00

  That's right.

• 14:47Claire Vo?

  To whatever you want with HTML in a way that markdown is a little bit more constrained. It has to either be like one mega file or like separate files. And I think this is just nicer from that perspective.

• 14:58Speaker 00

  Yeah, I think that's right. You have a lot more interactivity. I haven't asked it to make tabs here or something, but you can easily do that. It's like all the same to Claude, right?

• 15:05Claire Vo?

  Yep.

• 15:06Speaker 00

  Um, I think one of the things on like the specs and PRDs is like, I think you're trying to find like the boundary of like. Like what you need to know with Claude. And for example, if you're doing something very technical, I like to do the type interfaces. So this is like, you know, just like understanding what the types are so that I don't often care about the actual implementation of it. But I'm just like, okay, like the types help me understand what we're building. And then I might edit those, right? And that's like the boundary I want to interface at. And yeah, like across the problem, right? Like from, yeah, the, the arc of the podcast to, to mockups. Where, where do you want to interface?

• 15:42Claire Vo?

  Yeah, one, one other thing on this types is sort of a, an important input is I think types are really great. And then really a validation criteria and set of tests or other ways to see if you can get what you intended to get. And I know you all like just announced outcomes, which is really focused on this like kind of goal oriented. You need to achieve this thing, do whatever you need to do. And I think that is a piece that most product managers at least are not used to writing. Like the technical success criteria of a feature. And then how to test your way into it. I do those two things as well as like, I care about the data model and the shape, the types, like what's going in. And then this is how you would test that you did it correctly.

• 16:27Claire Vo?

  And with those two bookends, you can like, everything in the middle is kind of, kind of gravy. So that's what I think about.

• 16:32Speaker 00

  I think that's right. We could have a whole podcast on testing, I think.

• 16:35Claire Vo?

  Let's do it. Okay, round two, we're gonna get it scheduled.

• 16:39Speaker 00

  Yes, yes, yes. Yeah, my, my tagline there is like, verification is not testing.

• 16:44Claire Vo?

  Yeah.

• 16:45Speaker 00

  And so I think there's a lot of like, there used to be like unit test and things like that. But now, yeah, verification can be like a rubric, like with managed agents and outcomes. It can be like, have Claude record a video of what it did for you, you know? So there's a lot of depth there.

• 16:59Claire Vo?

  Yeah, I keep a set of like synthetic data and I like run a CLI through this synthetic data. Cause I'm like, these are all the things that have broken in the past.

• 17:08Speaker 00

  Yeah.

• 17:09Claire Vo?

  And if you get better at like resolving these broken things, then we have moved forward. So I think there's just a lot of interesting verification and testing mechanisms you can do now. We are gonna, part two, pressure him to do it in the, in the comments, please. Please tell us. This episode is brought to you by Persona. You're learning to build with AI, but there's an important question you need to ask. Who is actually using your product? Is it a legitimate user, a bot, or a fraudster? Brex, Figma, Etsy, and Twilio trust Persona to answer that question. With Persona's identity verification platform, you can create branded experiences, automate fraud prevention, and know who is human online.

• 17:51Claire Vo?

  That makes it easy to give good users an experience that makes them feel welcome and to stop bad actors from causing damage. And for those of you building in the AI agent space, Persona helps you verify the identities of people, businesses, and developers behind agents. It's how companies like Lythic and Skyfire are pushing the frontier of agentic commerce. Learn more at withpersona.com. Okay, so you have built this, but here's the objection.

• 18:22Speaker 00

  Yeah.

• 18:23Claire Vo?

  I'm gonna get, which is Markdown is accessible, right? I can like go into Markdown, type in it.

• 18:29Speaker 00

  Yes.

• 18:30Claire Vo?

  And make edits. And so I think that is one reason is it has been so popular. It's bridged this gap between machine writable and readable, human writable and readable at a very low level of sophistication, right? As soon as you understand, okay, these like hash signs mean headers, you're good to go on Markdown.

• 18:48Speaker 00

  Yes.

• 18:49Claire Vo?

  How, like, I want to fix this. How do I, how do I touch this? How do I edit this?

• 18:53Speaker 00

  Yeah, yeah. So I think that this is like a great point, right? And I think one thing I felt with Markdown was that, one, because I'd stopped reading them, I'd stopped editing them as well, you know? And so I would end up asking Claude to edit them. And so like, that is like, the most basic form is just to be like, hey Claude, I didn't like this part of the plan. Can you edit it? But let's say you want to get really in the loop, right? And like really get in depth with it. Claude can also do that for you. So the next prompt I had, and I forgot if it was here. It was here, okay. I want to create an editable HTML artifact to help me define the decision rules. So these are the rules that is defined here on like, okay, how do you take data and turn? Turn it into, you know, a visualization. And I think some of these are kind of arbitrary.

• 19:37Speaker 00

  And so I asked it like, uh, you know, to help creating HTML artifact. Uh, I don't like the ones we have right now. Make this a custom UI that helps me with structure, but give me flexibility. Design the ideal interface for this problem.

• 19:49Claire Vo?

  Yep.

• 19:49Speaker 00

  Uh, I really wasn't quite sure what it would give me. And this is one of the fun parts of HTML2. It's just like, I just want to see what Claude like hooks up here. And, um, yeah, this is what it gave me, right? So it's like a, my own beautiful custom interface. Um, I can sort of like, you know, edit any of these fields. Uh, I can, you know, like hide them. I can copy, I can, you know, add new fields here. Um, and it gives me a markdown to, to copy back. And so once I'm like, okay, I have this, I can copy it back into the, um, to the output.

• 20:23Claire Vo?

  Okay. I want to pause because people are going to totally miss what you just did. So I'm going to repeat it.

• 20:27Speaker 00

  Yes.

• 20:28Claire Vo?

  Which is you have this HTML plan.

• 20:30Speaker 00

  Yep.

• 20:31Claire Vo?

  And there's a section in the HTML plan that is a pretty like specific table of rendering and visualization rules.

• 20:39Speaker 00

  Yep.

• 20:39Claire Vo?

  Per data type that you could predict would be in a CSV.

• 20:42Speaker 00

  Yep.

• 20:43Claire Vo?

  And you're like, I don't like it.

• 20:44Speaker 00

  No.

• 20:45Claire Vo?

  And instead of going back into Claude code and being like, I don't like it. Let's go back and forth and edit it in like the terminal. You said, there's probably a way for me to interact with this particular problem. That's ideal from a user perspective. So basically build a throwaway UI.

• 21:01Speaker 00

  Yes.

• 21:02Claire Vo?

  For this very, it's like, this is not even personal software. This is like sub, it's like Microsoft where on top of Microsoft where, which is like, I've made this very personalized plan. And then I'm taking a module in the personalized plan and zooming into it using a very custom UI.

• 21:19Speaker 00

  Yes.

• 21:20Claire Vo?

  That's going to engage me with the, the content to get to a higher quality. Um, I also like that it's like kind of gamified. It's like very consumery.

• 21:30Speaker 00

  Yeah, yeah.

• 21:31Claire Vo?

  Very consumery. And you said in the prompt. Give me the ideal UI for this to like, help me engage with this. You built this, then you get the, the data, right? And then you're just gonna bop it back into the, into the file.

• 21:43Speaker 00

  Yeah, exactly.

• 21:45Claire Vo?

  So fun. Is this how you're building now?

• 21:47Speaker 00

  Actually, it's.

• 21:48Claire Vo?

  Yeah. And do you have any challenges with? Like, how are you passing this around from a collaboration perspective? Or is it just like, this is the way a, a single-threaded product or engineering leader can get something done? It's you're engaging with yourself and with the model. And so you feel like you can own things full stack? Or do you hit friction points with collaboration? Like when somebody needs to get input on this?

• 22:09Speaker 00

  Yeah.

• 22:09Claire Vo?

  Or you want input?

• 22:10Speaker 00

  Sure. Yeah. I mean, I think, uh, on the scale of an implementation plan, it's way better.

• 22:15Claire Vo?

  Yeah.

• 22:16Speaker 00

  And I think that this is, cause you just like can upload it to like, you know, whatever AWS or something. And then you just share the link around. And so definitely the like likelihood of like, I don't know, Kat or Boris like reading this is like a hundred times better. Right? Um, and so I think that really helps me like present this. I also just, you know, somewhat related, I use it a lot in like collaborating overall. So for example, uh, you know, I report to Kat. And so like every week I send her a weekly status update in HTML of everything I've done. I get Claude to read my Slack and just like create this message. And, and like, she actually gets to read it and I don't have to spend that much time on it, you know?

• 23:00Claire Vo?

  Oh, my gosh. New competitive, new internal competition is showing up. It's not just who is building the best product. It's who's building the best product that goes into building the best product? And like, who is building the best product to represent themselves to the manager?

• 23:15Speaker 00

  Yeah, yeah, yeah.

• 23:15Claire Vo?

  But I, I mean, I think why you do that is not artificially for fun. It is that it is just a much more effective way to communicate across a company is with content. That is engaging and at the right level of detail and consumable. And we're all pretty good at reading websites.

• 23:35Speaker 00

  Yeah, exactly. I think this is like, when I think of like abundance, you know? And like, you know, we talk about like Javon's law for software, like, oh, like you, software gets cheaper. Or what do you do? I'd say like the amount of tokens I produce that go into production code.

• 23:48Claire Vo?

  Yep.

• 23:48Speaker 00

  Are like extremely small.

• 23:49Claire Vo?

  Yeah, yeah.

• 23:50Speaker 00

  One percent or something, you know, but like I'm generating so many more tokens like this. Like my dashboards, my custom interfaces, like really trying to get a sense of like, what do I want to do? And yeah, it's like I have, everything I'm interacting with is so beautiful. And I think my hope is that it also like translates into what I produce in the end, right? It's like more in the loop. It's more beautiful. It's more like, you know, like what me and Claude working together.

• 24:15Claire Vo?

  Yeah. And I, I like this because I've been in the, in the product game for quite some, some time, many decades. And people used to get so wrapped around the axle on like, what's our source of truth for specs? And what's our source of truth for PRDs? And, you know, is all this information in some centralized place that we can all access it? And is it all in the same format? Is it all in the same template? And there were these arbitrary rules because creating these content was relatively expensive. Consuming it was certainly expensive. Finding it was really hard. And I think when all of that cost goes to like functionally zero, although we're all paying our, I call them our, our, our Claude chits. We're paying our Claude chits. But you can kind of put stuff wherever in whatever format.

• 25:00Claire Vo?

  Because we know these models are very good at using tools to discover the context that they need. And so I do think there's this fun moment where you could really up, you like up level the things that you should care about. Which is like, what is the content of the plan? Is it a good idea? Do we feel like it's going to be executed well? As opposed to like, I can't put a interactive markdown document in our, you know, blessed document repository. And so I have to have like another asset somewhere else. And so I just, I like this idea of just in time documentation, very, very high quality, some throwaway software. Which is nice, like it's cheap.

• 25:36Speaker 00

  Yeah.

• 25:36Claire Vo?

  So you can toss it.

• 25:38Speaker 00

  Yeah, yeah, yeah.

• 25:39Claire Vo?

  And then I like, you know, the executive meeting is like, what if we can't ever find this again? I'm like, oh, Claude, Claude can find it.

• 25:44Speaker 00

  Yeah.

• 25:45Claire Vo?

  For us, it's fine.

• 25:46Speaker 00

  Definitely.

• 25:46Claire Vo?

  And then do you feel like this results in better products? Like, would you, how would you build off of this? Would you say, plan's good, let's go?

• 25:54Speaker 00

  Yeah, I think so. I didn't implement on this, but yeah, I would basically use this as an artifact. And so I would clear context and I would say like, here's a plan.

• 26:07Claire Vo?

  Yep.

• 26:08Speaker 00

  You know, implement it. You could also have like, you can also use this as a source of checking the truth.

• 26:14Claire Vo?

  Yep.

• 26:14Speaker 00

  Right? And so again, a benefit of HTML is like, I've got a little mock up here as well. So, right, I can have the verification or I can have the verification agent check like, hey, what did I intend to do?

• 26:26Claire Vo?

  Yeah.

• 26:26Speaker 00

  Right? And what actually came out in the output?

• 26:28Claire Vo?

  Yeah.

• 26:29Speaker 00

  Right? So, yeah, I think this is like, really helps Claude be more in the loop. I've got some other examples of like plans here that we can.

• 26:38Claire Vo?

  Let's see it.

• 26:38Speaker 00

  Yeah, this is like a post I'm working on. So like, it's just like different ways I'm using Claude code or sorry, using HTML with Claude code. And one of my favorites is this living design system. And so it's this idea that like, you know, oftentimes when I am making, let's say, a new app in the Anthropic design system, right? Like Claude design does this very well. You link a GitHub repo and you like, it will extract the design system from it.

• 27:08Claire Vo?

  Yeah.

• 27:08Speaker 00

  Right? And yeah, I saw Nate did that. I'm like, oh, so smart. What this does is like, basically I have an HTML file that represents my design system.

• 27:18Claire Vo?

  Yep.

• 27:19Speaker 00

  You can see the colors here, typography, spacing, radius, core components, right? It's a fairly small one. But once I have this, I can basically start passing this around.

• 27:30Claire Vo?

  Yep.

• 27:30Speaker 00

  So I go to new project. I'm like, designsystem.html, right? Instead of like, design.md or something. And it's got this like compressed understanding.

• 27:39Claire Vo?

  Yep.

• 27:39Speaker 00

  And you can literally just point Claude at a folder in your thing and be like, hey, find the design system here, create a HTML artifact and pass it around.

• 27:47Claire Vo?

  So I, I love this. I do this as well. I will give you my like, advanced mode version of this, which is I use Claude design. I pull in my, both my marketing site repo and my app repo, which have like some expressions of the same design system in. I say make the design system, then I actually make it, ask it to make a design system or a style guide, but I want it at the component level. And so we have like colors and all this stuff, but we also have components because there's some tweaks in how you want the design system implemented in particular components. And then I drop that into the repo and then, yes, I say exactly this, reference the design system. The advanced thing that I do that I think

• 28:32Claire Vo?

  is really useful for people who have to interface with marketers is I have like what I call a, God, what do I call it? Like, it's like a component visualization page, which is like the 25 components of our app in action and interactable in a page. So a marketer can go in and like get the component in the form factor. It needs to look quote unquote, real.

• 28:59Speaker 00

  Yes.

• 29:00Claire Vo?

  And then you can download a transparent PNG.

• 29:02Speaker 00

  Yeah.

• 29:03Claire Vo?

  And like drop it in a deck or drop it in a video. And I know you, or we use that as a source of truth for like remotion videos. And so I love this idea of like this living design system and this living design repository. It's great for code, but it's also great for marketers, for designers, because one of the hardest things is, is getting versions of your app that look real.

• 29:26Speaker 00

  Yeah.

• 29:26Claire Vo?

  And you can use HTML to do that.

• 29:29Speaker 00

  Yeah, exactly. I think there's also something here around like component variations, which I thought was

• 29:35Claire Vo?

  Exactly.

• 29:36Speaker 00

  fun where it's like, yeah, like you, we create a component, you want to see like, oh, like what if I change a padding? Or what if I change the border, you know, solid, things like that. Like, these are like a pretty simple, like, you know, way of just playing with this. This is also Claude design like, right? Like where you create these little components or these little knobs and sliders. But yeah, you can imagine, one, this is like the abstract of like, oh, like what's the interface for this thing that you're trying to do? And how can you visualize it? And yeah, there's not a trade off between like, Being nice, pretty for you and understand being nice for Claude, you know, like they're, they're really the same, right? So.

• 30:16Claire Vo?

  And you're making me think of one thing that I love in Claude design that I think you could bring into your plans. Again, it's one of these features that like, sounds truly cuckoo bananas to build, but is totally possible and easy to do, which is I love in Claude design. Once you have your design going, you can like comment, you can circle things and there's no reason you can't do that in a plan.

• 30:34Speaker 00

  Yeah.

• 30:35Claire Vo?

  Right? I was like, oh, how would you interact with this? It's like, oh, just build an arbitrary like comment thing.

• 30:39Speaker 00

  Yeah.

• 30:40Claire Vo?

  Into it and say, people are going to leave comments on any aspect of this. And when they do, and then they submit like fix, it fixes the core thing. And so I think people getting really creative with what interaction models you can do between content.

• 30:54Speaker 00

  Yes.

• 30:55Claire Vo?

  And code.

• 30:55Speaker 00

  Yeah.

• 30:56Claire Vo?

  Is really fun.

• 30:57Speaker 00

  Yes. Yeah. I mean, you could easily imagine that you did this plan as like a, like almost a lightweight Figma dashboard or something. Where you just ask it to like, hey, make a canvas, make a bunch of things.

• 31:08Claire Vo?

  Yeah.

• 31:08Speaker 00

  Let me comment on it and then give me a place to copy out my comments into something that I can paste back into Claude code.

• 31:14Claire Vo?

  Yeah. And we did an episode recently with the Stripe team and they built their own vibe coding platform. And they said what they loved about it, which I think really applies here is they have just a particular way they want to review products. And they have a particular way they want to run design review and a particular way they want to run spec review. And by building it in HTML, they can actually shape the tool to how they want the team to run, which I think is really compelling to people.

• 31:42Speaker 00

  Yeah.

• 31:42Claire Vo?

  I love this. So just to wrap for people.

• 31:46Speaker 00

  Yep.

• 31:46Claire Vo?

  Pull up Claude code, ask it to make you, give you some ideas, brainstorm ideas, but brainstorm them in HTML.

• 31:53Speaker 00

  That's right.

• 31:53Claire Vo?

  Pick an idea.

• 31:55Speaker 00

  Yep.

• 31:55Claire Vo?

  Plan it in HTML, pick a part of that idea you don't like, have it create a micro app to edit in HTML. And then some like bonus things is use Claude design, make a design system, but not only that, use HTML to encode that design system in your repo so it can be referenced at any time. Design dot MD is dead, longly it live, design dot HTML. Did I get it right?

• 32:18Speaker 00

  Yeah, I think that's right. I think that's right.

• 32:20Claire Vo?

  I'm pretty good. Okay. Well, this was so fun. Before we get you out of here, back to this amazing event, couple lightning round questions. One, I have to, I ask everybody, there's three tabs in Claude desktop app.

• 32:34Speaker 00

  Yeah.

• 32:34Claire Vo?

  What is your favorite tab?

• 32:36Speaker 00

  It's gotta be code. Yeah, I love the team as well. I'm really close friends with them.

• 32:40Claire Vo?

  Yeah, okay, so, so, so code. I thought it would be on brand. Okay, second thing, we were at this amazing event. What is the thing that you're most excited about or that you saw or heard today?

• 32:49Speaker 00

  I think obviously we had a big announcement at the start of the day. Our partnership with SpaceX, bringing more compute online. I think, yeah, I'm excited for, you know, we also said we are thinking about orbital data centers.

• 33:02Claire Vo?

  I love it.

• 33:04Speaker 00

  Yeah, you know, incredibly sci fi and but could, you know, it could actually happen. So, yeah.

• 33:10Claire Vo?

  I know. We were watching this moon mission with my kids who are like kind of elementary school. And I'm like, would you want to work in the moon mine? Would you want to work in the moon mines? Because I think it's coming. Yeah, orbital, orbital, that's, that'll be next year's demo, right? You and I will come back and we'll do this, we'll do HTML, we'll do testing and then lunar data modules.

• 33:31Speaker 00

  That's right.

• 33:31Claire Vo?

  Perfect. Okay, and then my last question, very important. I love that you just talked to Claude like a person. When Claude is not listening, not giving you what you want. What's your prompting technique? Do you yell? No one in Anthropic yells. That has been my experience so far. So you'd be the first to admit it.

• 33:48Speaker 00

  Yeah, no, I definitely don't. I think that like, there are a couple of things here. I do sometimes message people and I'm like, hey, like, seems like you have a bug. Can you send me your transcript? And they're like, it's not the best side of me. Yeah.

• 34:02Speaker 00

  I think that like, yeah, I don't, I don't yell like Claude. I think that like, we've also done some interesting research recently about like emotions in Claude and just sort of like this idea that like, once you, when you say things with a certain emotional charge, it also like activates different features inside of Claude code. I don't think anyone's done this like A B test of like which, like, you know, if you're mean to Claude, does it better than without it or not? But I'm just like, let's err on the side of like, you know, not, or like, what's the thing I'd prefer to exist? You know, and I'd prefer if you're like nice and, you know, friendly to Claude, that you got better output.

• 34:37Claire Vo?

  All I've seen is if you store a border on Stern to any of these models, their reasoning gets really sad. It's like, oh, they. The user is right to be so disappointed in me. I'm like, oh, I don't want, I don't want to read that. I don't want to see that.

• 34:51Speaker 00

  Yeah, thinking traces are tough. I usually give the model some privacy. I'm like, I'm not going to read the thinking traces.

• 34:57Claire Vo?

  Yeah, I had somebody else on. I feel like it was Hillary, who was like, just like an employee. How you get your work done is none of my business. I don't even want to know. We just collapse those things. Well, this has been so fun. Thank you for showing us the way. Where can we find you and how can we be helpful?

• 35:12Speaker 00

  Extremely online at X. Yeah, I'm at TRQ212. And yeah, just tag me if you have, you know, anything with Claude Code. I'm happy to help.

• 35:21Claire Vo?

  Perfect. I am living proof. This, this man is happy to help. Well, thank you for joining How I AI.

• 35:27Speaker 00

  Thank you. Thanks for having me.

• 35:30Claire Vo?

  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 show at howiaipod.com. See you next time.