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

0:00Markdown became a really popular way of interacting with agents, but the plans are so long, I honestly have stopped reading them. And this is honestly a mistake. I think that you still need to be really in the loop.

0:10Thariq Shihipar:Plans matter. PRDs matter. Spec matters. 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. People ask me all the time, Claire, you said product management is dead. What's next? I'm going to say, you're a compute allocator, babe. That's the job now. HTML is a lot easier to read. And so it's just a richer communication medium between you and Claude. Instead of saying, here's a markdown document. It was like, what's the best way to convey this information?

0:43Thariq Shihipar:So you can actually engage with it and pick something. This is the plan. It's purely in HTML. This is something that I will actually read. This is not even personal software. It's like micro software on top of micro software.

0:59Thariq Shihipar:Welcome back to How I AI. I'm Clara Vaux, 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, Anthropics' first developer conference. And as part of that, I got to spend a little time with Tharik, 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 going to 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 Celigo. Every company today wants AI to improve how work gets done.

1:39Thariq Shihipar:The fastest way is building it directly into everyday business processes, automating employee onboarding, 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. Soligo Aura gives you access to the entire platform through natural language, connecting your systems and turning intent into action.

2:18Thariq Shihipar:All of it under your control. Companies like Databricks, PayPal, and Olipop rely on Celigo to run critical business operations at scale. Ready to operationalize AI? Visit celigo.com slash howiai. That's C-E-L-I-G-O dot com slash howiai. Welcome to How I AI. Thanks for having me. I am so excited to be here at Code with Claude in San Francisco. go. 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. I mean, I think Markdown became a really popular way of interacting with agents, especially like, you know, Opus 4 and Cloud 3.5, where, you know, they have a plan and the plan is like how to do this feature.

3:12And 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. We really need to understand what the agents are doing. But like a thousand line markdown file, you know, I don't even edit them anymore.

3:44just 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 we're using HTML files instead. And so HTML is like, the models are still very good at it. They have a lot more context now, so you can spend the more extra tokens. And it's a lot easier to read. They can have a lot more information. They're a lot 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 like there it can actually draw like things that you can look at and so it's just a richer communication medium between you and Claude.

4:31Thariq Shihipar:And before we go further into HTML specifically I do have to pause because I do have a vested interest in this sure Which is you are saying for the people who are not listening, listen up. Yes. 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. Oh, 100 percent. Yeah. I think that, you know, everyone has different views on how it will go. But I think that this will just forever be the thing. Because when you say, OK, Claude can run for eight hours, what you're really saying is Claude can spend like 500 bucks.

5:04You 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. Yeah. 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. Sometimes you have like unknown unknowns you need to figure out. But yeah, I think this is like the whole thing now is just like really getting in sync with Cloud about what's building.

5:35Thariq Shihipar:I love what you said because people ask me all the time, Claire, you said product management is dead. What's next? I'm going to 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. OK, 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 up levels 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.

6:20Thariq Shihipar: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. Yeah, that's right. OK, so you're building something with the agent so the agent can manage you. 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 Cloud Code have been like that, you know, like how can I get to know you better? So, yeah. OK, great. Well, we have we have Cloud Code up.

6:50Thariq Shihipar:So let's walk through how that how that works. Yeah. So I did like a little bit before we started. And so I like to talk with Cloud 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, once you have a partner. So I was literally like, look, I'm on a Clairvro podcast. 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.

7:27Right. So like PRD to working prototype. Right. Like it searched you up. Right. You saw that with a web search. Right. Whiteboard sketch to working UI, which I thought was really cool. This is such a cute little thing.

7:39Thariq Shihipar:It is 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 mock-ups in chat purity 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 ascii you know wireframe um so this is definitely the dream yes but not even but now you're telling me i'm gonna build it so yeah 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 some descriptions of things you could do.

8:23Thariq Shihipar: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. 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 Cloud Code. You know, so like if I, if you gave me eight ideas, I'm just not going to see all of them. 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?

9:04The 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.

9:15Thariq Shihipar:We love a dashboard. 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. Okay. So you use Cloud Code. You said brainstorm, but brainstorm in HTML. Give me a couple 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 I like the risk. It's like it could go sideways as all good devos can. Yeah. 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 this idea. That's right. Yeah. So I think what I like about HTML is like really Claude really understands this.

9:56And so my next prompt here was really like, okay, I asked it to make some mockups 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 PRD is right, like finding out my unknown unknowns, what do I want it to do? I answered a bunch of questions. and uh now i'm like okay create an html file as a plan that helps me visualize what the implementation plan is include excerpts mock-ups code when whatever is needed to give me like maximum context right um and so then it made me this html file here yeah you can see now this is this is the plan uh 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 file system.

10:48It gave me like an excerpt of the skill.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? Yeah, this is something that like I will actually read. Yeah.

11:15Thariq Shihipar: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 Hawaii AI episodes and they get incredible outputs and everybody's prompts like make the thing. Hopefully it's good. Yeah. 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. I did, yeah. And you're like, excerpts, mockups, code, et cetera, whatever is needed.

11:54Thariq Shihipar:Yeah. And so I do want to encourage people, 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 the model do what it needs to do will do a very high quality job. Yeah, 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. You know, 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.

12:35Right. Like that is usually like outsourcing too much and constraining it. But in this case, for example, like I really did want to make sure it gave me code excerpts. I wasn't sure if I did 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 need it 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 like I trust you here I want to just like be in the loop with you

13:07Thariq Shihipar:yeah 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 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 think leaving that open-ended sort of like, whatever you got to do, I trust your judgment. At least it makes me feel like I get better outcomes. Yeah, yeah. 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.

13:45Thariq Shihipar:We need more happenstance in our life. Okay. So you built this thing. Another thing that I want to walk people through, if you pull up the plan, because I think about this a lot and I get people 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. 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 going to demo it.

14:21Thariq Shihipar:Yeah, yeah, exactly. 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, put the PRD in one tab and put the tech spec in the second tab because maybe separate people would be reviewing that information. And so you can really kind of like craft a ideal spec package to whatever you want with HTML in a way that markdown is a little bit more constrained. It has to either be like one megafile or like separate files. And I think this is just nicer from that perspective.

14:59Yeah, 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? Yep. 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 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. I'm just like, OK, like the types help me understand what we're building.

15:29And then I might edit those. Right. And that's like the boundary I want to interface that. And yeah, like across the problem, right, like from the arc of the podcast to mockups, where do you want to interface?

15:42Thariq Shihipar:Yeah. One other thing on this types is sort of 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.

16:23Thariq Shihipar:And then this is how you would test that you did it correctly. 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. I think that's right. We could have a whole podcast on testing, I think. Let's do it. Okay, round two. We're going to get it scheduled. Yes, yes, yes. Yeah, my tagline there is like verification is not testing. Yeah. And so I think there's a lot of like there used to be like unit tests and things like that. But now, yeah, verification can be like a rubric like with managed agents and outcomes. It can be like have cloud record a video of what it did for you, you know.

16:58So there's a lot of depth there.

16:59Thariq Shihipar:Yeah, I keep a set of like synthetic data and I like run a CLI through this synthetic data because I'm like, these are all the things that have broken in the past. 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 going to 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?

17:32Thariq Shihipar: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. 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 Lithic and Skyfire are pushing the frontier of agentic commerce.

18:12Thariq Shihipar:Learn more at withpersona.com. Okay, so you have built this, but here's the objection I'm going to get, which is Markdown is accessible, right? I can like go into Markdown, type in it, 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 on markdown yes how like i want to fix this how do i how do i touch this how do i edit 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 i because i stopped reading them i had 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 hey, Claude, I didn't like this part of the plan.

19:12Can you edit it? But let's say you want to get really in the loop, right? And like really get in depth with a, 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 edible HTML artifact to help me define the decision rules. So these are the rules that it's defined here on like, okay, how do you take data and turn it into a visualization? And I think some of these are kind of arbitrary. And so I asked it like, you know to create an html artifact i don't like the ones we have right now make this a custom ui that helps me with structure but gives me flexibility design the ideal interface for this problem yeah 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 what cloud like cooks 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 back into the um okay i want to pause because people are going to totally miss

20:25Thariq Shihipar:what you just did so i'm going to repeat it which is you have this html plan yep and there's a section in the HTML plan that is a pretty like specific table of rendering and visualization rules per data type that you could predict would be in a CSV. Yep. And you're like, I don't like it. Yep. And instead of going back into Cloud Code and being like, I don't like it, let's go back and forth and edit it in like the terminal. Yep. 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. for this very, it's like, this is not even personal software.

21:06Thariq Shihipar:This is like sub, it's like micro software on top of micro software, 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 that's going to engage me with the content to get to a higher quality. I also like that it's like kind of gamified. It's like very consumery. Yeah, yeah. 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 data right. And then you're just going to bop it back into the into the file. Yeah, exactly.

21:45Thariq Shihipar:So fun. Is this how you're building now? Actually, it is. 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 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 give input on this. Yeah. Or you want input. Sure. Yeah. I mean, I think on the scale of an implementation plan, it's way better. And I think that this is because you just like can upload it to like, you know, whatever, AWS or something.

22:22And 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. 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, 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 called to read my Slack and just, like, create this message. And, like, she actually gets to read it and I don't have to spend that much time on it, you know?

22:59Thariq Shihipar:Oh, my gosh. 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. But 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. 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 offer software, like, oh, like software gets cheaper.