Skip to content

By playing, you agree to uListen's Terms and Privacy Policy and YouTube's Terms of Service.

How I AIHow I AI

Why this Claude Code engineer uses HTML files as AI specs | Thariq Shihipar (Anthropic)

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…

Thariq ShihiparguestClaire Vohost
May 18, 202635mWatch on YouTube

Summaries, chapters, transcripts, and FAQs on this page are made by uListen, not YouTube.

Great conversations run long. Their best ideas don't have to.

uListen is free on iPhone, iPad, Android, Chrome, and Claude.

See how

At a glance

WHAT IT’S REALLY ABOUT

Using HTML specs to stay aligned with long-running AI agents

  1. As agent runs get longer and more expensive, planning and specs become a core “compute allocation” decision point rather than optional documentation.
  2. HTML is presented as a richer, more readable medium than Markdown for long plans, enabling visuals, mockups, and structure that humans will actually review.
  3. A workflow is demonstrated: brainstorm in HTML, interview the user to surface unknown unknowns, then generate an HTML implementation plan containing code excerpts, file structure, mockups, and logic.
  4. When a plan section is hard to edit in raw text, Claude can generate a micro-UI (a throwaway HTML app) to interactively edit decisions and then paste structured output back into the plan.
  5. The approach extends beyond one-off plans to reusable artifacts like “living design systems” encoded as HTML files that can be dropped into repos and referenced across projects and teams.

IDEAS WORTH REMEMBERING

5 ideas

Treat specs as the control surface for spend and risk.

Running an agent for hours maps directly to real cost, so the PRD/plan phase is where you decide what’s worth spending compute on and what success should look like.

Switch formats when the bottleneck is human attention, not model capability.

Models can parse Markdown fine, but humans stop reading 1,000-line plans; HTML increases engagement through layout, visuals, and scannability, keeping you “in the loop.”

Ask for “maximum context” while still leaving the model room to help.

Their prompting philosophy is a balance: specify key constraints (e.g., include code excerpts) but add an escape hatch (“whatever is needed”) so Claude can contribute structure you didn’t anticipate.

Use an interview step to surface unknown unknowns before locking a plan.

After picking an idea, Thariq has Claude ask targeted questions; this mimics good product discovery and produces a plan that matches real intent rather than assumptions.

Turn plan friction into a tailored interface, then paste results back.

Instead of editing dense tables or rules manually, generate a small HTML UI to edit fields, add/remove items, and export structured markdown/text back into the canonical plan.

WORDS WORTH SAVING

5 quotes

When you say, "Okay, Claude can run for eight hours," what you're really saying is, "Claude can spend, like, 500 bucks."

— Thariq Shihipar

All of us are becoming these compute allocators now.

— Thariq Shihipar

You're a compute allocator, babe. Like, that's, that's the job now.

— Claire Vo

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

— Thariq Shihipar

This is not even personal software. This is, like, sub... It's like micro-software... on top of micro-software.

— Claire Vo

Read the available transcript
HTML as the new Markdown for agent plansCompute allocator mindset and cost of long agent runsSpec/PRD importance in agentic workflowsBrainstorming with visual HTML artifactsFrom brainstorm to implementation plan (code, mockups, structure)Editable micro-apps for refining parts of a planLiving design systems as portable HTML references

Ask ChatGPT about this episode

Get its key ideas, plus a summary of each chapter linked to that point in the video, right in your chat.

  1. Add uListen AI to ChatGPT.

  2. Paste this prompt into a new chat.

    Use uListen AI to give me this episode's key ideas and a chapter-by-chapter summary, with timestamps: https://www.youtube.com/watch?v=Qrpm7E80wQ0

SPEAKERS

  • Thariq Shihipar

    guest

    Engineer on Anthropic’s Claude Code team who shares workflows for using HTML files as richer AI specs.

  • Claire Vo

    host

    Product leader and AI-focused podcast host of How I AI who interviews builders about practical AI workflows.

High quality AI-generated summary created from speaker-labeled transcript.

Get more out of YouTube videos.

Read along on your phone, search it beside the video, or ask your favorite AI app what was said.