A designer who has worked with booking.com, Slack, and Mailchimp shows how to build a reusable design system with just two tools — shadcn's 'build your own' component styles and Paper (an HTML-based design tool with a Chrome extension) — driven by Claude Code one layer at a time: tokens, then building blocks, then components, then a dark mode variant.
Charles Postiaux7 minTranscript found
Quick learning frame
Read this before watching.
Creative automation uses agents to accelerate production while keeping human taste in story, pacing, selection, and critique.
New playlist item from Charles Postiaux; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to direct an AI coding agent to build a design system incrementally from a captured HTML reference — tokens first, blocks second, components third — while verifying every AI output against the reference instead of prompting for everything at once.
Watch for the shift from claim to mechanism. The learning value is the point where the transcript reveals a repeatable action, tool boundary, context move, review habit, or artifact.
Concept diagram
Where this video fits.
01Brief
02Source
03Generation
04Selection
05Edit
06Taste Review
Deep lesson
Turn this video into working knowledge.
1,561 cleaned transcript words reviewed across 420 timed caption segments.
Thesis
How To Build Design Systems with AI teaches a practical creative automation move: A designer who has worked with booking.com, Slack, and Mailchimp shows how to build a reusable design system with just two tools — shadcn's 'build your own' component styles and Paper (an HTML-based design tool with a Chrome extension) — driven by Claude Code one layer at a time: tokens, then building blocks, then components, then a dark mode variant.
The goal is not to remember the video. The goal is to extract the operating principle, tie it to timestamped evidence, test how far the claim transfers, and make something reusable.
0:20
Two-tool capture setup
“pretty much use any style that they already have preset or you can customize with whatever you need for your project. The other thing that we're going to use is Paper. It's a HTML-based design software and they...”
Start on shadcn's build-your-own page to preset or customize a component style, then use Paper's Chrome extension to select the rendered components and grab their HTML — which works on technically any website — pasting them into Paper as an editable, live-prototypable reference library for the AI. Pick a shadcn style, capture its component page with the Paper extension, and paste it into Paper so you have a concrete HTML reference before writing any AI prompt.
2:47
One layer at a time
“you need really to build a design system that comes from the tokens we added. Once that's done, we can move on to the components. The components is kind of like the pressure test of the whole design...”
Asking the AI to build the whole design system at once causes mistakes, shortcuts, and wasted tokens — instead connect Claude Code to Paper via the MCP server and go stepwise: tokens (colors, typography, spacing, border radius) first, then building blocks like buttons and inputs, then components such as cards and tables as the 'pressure test' — and double-check everything, because even with full context the AI still gets reds, greens, and spacing wrong. Prompt your agent with only 'based on the reference, build the color and typography tokens', verify each value against the reference, and refuse to advance a layer until the current one checks out.
4:49
Dark mode is tokens
“>> >> And so once you have those two down, the sky is the limit. And so for example, I did a little exploration here. I liked this design element, but I thought that, you know, maybe we...”
For dark mode you recapture the dark reference with the extension, duplicate the system, and change only the tokens — building blocks and components inherit the update — while deliberately keeping per-mode color assignments (this color in light, that color in dark) so switching modes produces no discrepancies. Duplicate your light-mode system, update only the token layer from a dark reference, then toggle between modes and list any component whose colors didn't follow the tokens.
01
Brief
Start with this video's job: A designer who has worked with booking.com, Slack, and Mailchimp shows how to build a reusable design system with just two tools — shadcn's 'build your own' component styles and Paper (an HTML-based design tool with a Chrome extension) — driven by Claude Code one layer at a time: tokens, then building blocks, then components, then a dark mode variant. Treat "Brief" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:20, where the video says: “pretty much use any style that they already have preset or you can customize with whatever you need for your project. The other thing that we're going to use is Paper. It's a HTML-based design software and they...”
02
Source
Use "Source" to locate the part of the creative automation workflow the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 2:47, where the video says: “you need really to build a design system that comes from the tokens we added. Once that's done, we can move on to the components. The components is kind of like the pressure test of the whole design...”
03
Generation
Turn "Generation" into the reusable artifact for this lesson: A creative workflow board with critique criteria and review checkpoints. This is where watching becomes something you can inspect and reuse.
04
Selection
Use "Selection" as the application surface. Decide whether the idea touches a browser flow, a local file, a model choice, a source document, a UI, or a review step.
05
Edit
Use "Edit" to prove the lesson. The evidence should connect back to the video title, transcript anchors, and a concrete output, not a generic best-practice claim.
06
Taste Review
Use "Taste Review" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
Example
Source-backed work packet
Convert the video into a scoped task that includes the transcript claim, target workflow, acceptance criteria, and proof. The output should be a creative workflow board with critique criteria and review checkpoints..
Example
Claim vs. demo brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the workflow.
Example
Teach-back module
Transform the lesson into a definition, a mechanism diagram, one misconception, one practice exercise, and a check-for-understanding question.
Do not learn it wrong
Treating the title as the lesson without checking what the transcript actually says.
Letting the prompt drift into generic advice that could apply to any video in the playlist.
Copying the tool setup without identifying the operating principle that transfers to your own stack.
Skipping the artifact, which means the learning never becomes operational or inspectable.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: A designer who has worked with booking.com, Slack, and Mailchimp shows how to build a reusable design system with just two tools — shadcn's 'build your own' component styles and Paper (an HTML-based design tool with a Chrome extension) — driven by Claude Code one layer at a time: tokens, then building blocks, then components, then a dark mode variant.
02
Explain the practical stakes without hype: New playlist item from Charles Postiaux; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Brief -> Source -> Generation -> Selection -> Edit -> Taste Review sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A creative workflow board with critique criteria and review checkpoints.
Put it into practice
Give this grounded prompt to Codex or Claude after watching.
You are helping me turn one specific YouTube video into real, durable learning.
Source video:
- Title: How To Build Design Systems with AI
- URL: https://www.youtube.com/watch?v=U_qhzWyD0FY
- Topic: Creative Automation
- My current learning frame: Capture a shadcn style with Paper's Chrome extension and use Claude Code to build a mini design system in three verified passes — tokens, building blocks, one card component — then derive a dark mode by swapping only the tokens and generate three AI variations of a sidebar to practice iterating on strategy instead of pixel work.
- Why this matters: New playlist item from Charles Postiaux; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:20 / Evidence 1: "pretty much use any style that they already have preset or you can customize with whatever you need for your project. The other thing that we're going to use is Paper. It's a HTML-based design software and they..."
- 2:47 / Evidence 2: "you need really to build a design system that comes from the tokens we added. Once that's done, we can move on to the components. The components is kind of like the pressure test of the whole design..."
- 4:49 / Evidence 3: ">> >> And so once you have those two down, the sky is the limit. And so for example, I did a little exploration here. I liked this design element, but I thought that, you know, maybe we..."
- 6:34 / Evidence 4: "code from the the design element. I can ask the AI to give me the code, paste the code into the plugin on Figma, and I get the design. Or I can just literally just copy the image..."
Your task:
1. Use the transcript anchors above as the primary source packet. If you add outside context, label it clearly as outside context and keep it secondary.
2. Create a source-check table with columns: timestamp, claim, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable claims from the video. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A creative workflow board with critique criteria and review checkpoints.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Brief -> Source -> Generation -> Selection -> Edit -> Taste Review
- 3 concrete examples that apply the video idea to real agentic work
- 2 failure modes the video helps prevent
- a checklist I can use the next time I run Codex or Claude
- one practical exercise with a clear done signal
6. Add a "learning transfer" section: what changes in my workflow tomorrow if I actually learned this?
7. Add a "source check" section that cites which transcript anchor supports each major takeaway.
Quality bar:
- Make this specific to "How To Build Design Systems with AI", not a generic Creative Automation essay.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- If evidence is weak, say what transcript segment or timestamp needs review instead of guessing.
- Finish with a concise artifact I could paste into my learning app.
Misconceptions
What to stop believing.
Creative AI removes the need for taste.
It increases the need for taste because output volume explodes.
The best prompt is enough.
References, critique, iteration, and post-production matter just as much.
Practice studio
Learning only counts when you make something.
01
Transcript evidence map
Separate what the video actually says from what you already believe about the topic.
3 source-backed takeaways with timestamps, confidence, and a transfer note.02
One useful artifact
Apply the video to a real workflow and produce a creative workflow board with critique criteria and review checkpoints..
A reusable artifact with a done signal and one verification step.03
Teach-back card
Explain the lesson to someone who has not watched the video yet.
A 90-second explanation, one diagram, one example, and one misconception to avoid.
Recall check
Answer first, then reveal — without rewatching.
What two tools does the video use to build a design system with AI, and what role does each play?
Why shouldn't you ask the AI to build the whole design system in one prompt, and what order should you follow instead?
What is the only layer that needs to change when creating a dark mode version of the system?
Source shelf
Use the video as a doorway, then verify with primary sources.
