How I AI

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

· Summarized

Share this episode
Anyone with this link can open it.
Share Link
Start at 0:00

Key takeaways

  • HTML is replacing Markdown for AI planning and communication because it supports richer visuals, interactivity, and engagement, leading to higher quality collaboration and documentation.
  • Using HTML enables the creation of dynamic, interactive artifacts like mockups, design systems, and plans, which can be easily shared, edited, and maintained across projects.
  • Prompt engineering should focus on trust and clarity, giving AI models enough constraints to produce high-value outputs without over-restricting them.
  • The approach of just-in-time, lightweight, or throwaway software and documentation reduces costs and increases relevance, making processes more efficient.
  • Interactive HTML artifacts facilitate better collaboration within teams and with external stakeholders, supporting real-time feedback, annotations, and versioning.
  • The future of product management, design, and engineering involves higher levels of visual, interactive, and AI-integrated documentation that travel with the code and evolve continuously.

Summary

Introduction to the Shift from Markdown to HTML in AI Workflows

The host, Claire Vo, introduces the topic of how Markdown, traditionally used for AI planning and communication, is being replaced by richer formats like HTML. Thariq Shihipar from Anthropic discusses how the increasing complexity and length of AI plans make Markdown less practical, advocating for HTML as a more effective, engaging medium. HTML allows for detailed, scrollable, and visual specifications that are easier to engage with, improving communication and understanding between humans and AI agents.

HTML as the New Standard for AI Communication and Planning

Thariq explores why HTML is superior to Markdown for AI workflows. He explains that as AI models generate longer and more complex plans, a format that supports richer visuals, mockups, and interactivity—like HTML—is essential. HTML enables more engaging and comprehensible documentation, which improves collaboration and decision-making in product development. He emphasizes that HTML improves engagement and clarity without increasing the cognitive load, thus fostering better human-AI collaboration.

Practical Applications and Workflow Innovations with HTML and Claude Code

The podcast details practical ways to leverage HTML in AI-driven workflows. Thariq demonstrates how to brainstorm ideas in HTML, generate visual mockups, build 'throwaway' micro-UIs for editing specific plan segments, and maintain living design systems within code repositories. These practices allow for more dynamic, interactive, and up-to-date documentation and planning tools. He also discusses prompt engineering strategies, advocating for trust in AI outputs while constraining it enough to produce high-quality, useful artifacts.

Advantages of Using HTML for Documentation and Collaboration

Using HTML enables teams to create more engaging, interactive, and easily shareable documentation artifacts like specs, PRDs, and design systems. Thariq describes how HTML documents can serve as single sources of truth, accessible and modifiable by multiple team members, and how they support better collaboration, versioning, and transparency. He emphasizes that this approach encourages a mindset of 'just-in-time' documentation, reducing costs and increasing relevance.

Transforming Product and Design Workflows with Interactive HTML Artifacts

Thariq showcases examples such as living design systems, component style guides, and interactive plans that stay synchronized with codebases. These tools allow for real-time updates, annotations, comments, and visual comparisons, making design and development more iterative and human-centered. He also mentions how companies like Stripe are customizing review and approval processes through embedded interactive tools built with HTML, highlighting the flexibility of this approach.

Key Lessons and Future Outlook

The discussion concludes with reflections on how HTML and AI can democratize and elevate product management, design, and engineering workflows. Thariq believes that the reduction in content costs enables a shift toward higher-quality, purpose-driven documentation. He advocates for experimenting with interactive, modifiable artifacts to enhance team alignment and product quality, and imagines future developments like even more integrated, visual, and interactive AI-assisted workflows.

Sponsors

  • Celigo · Celigo makes this possible, and now, with Celigo 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 Alipop rely on Celigo to run critical business operations at scale.
  • 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. For those of you building in the AI agent space, Persona helps you verify the identities of people, businesses, and developers behind agents.

Show notes

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:

  1. Why HTML has replaced Markdown as the ideal format for AI agent communication and planning
  2. How to brainstorm in HTML to get visual mockups and interactive demos instead of text lists
  3. The technique for building throwaway micro-UIs to edit specific parts of your plan
  4. How to create a living design system in HTML that lives in your repo and travels with every project
  5. Why “complexity has to earn its keep” and how HTML helps you stay in the loop without over-constraining Claude
  6. The prompting technique that gives Claude flexibility while ensuring that you get what you need
  7. Why 99% of your AI-generated tokens should go to planning, interfaces, and communication—not production code

—

Brought to you by:

Celigo—Intelligent automation built for AI

Persona—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

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 jordan@penname.co.

Follow this show on AudioBrevity and new episodes get summarized for you. Create a free account

Couldn't load the audio. A blocker may be stopping the show's tracking links. Open the file