A walkthrough of Codex's new product design plugin — 11 copyable skills covering ideate, image-to-code, prototype, research, and more — combined with a Miro MCP server for visual context and a design.md design system, used to generate a Linear-inspired issue tracker in three visual directions and a one-page gym landing site, with Codex visually QA-ing its own output.
AI for WorkWatchTranscript found
Quick learning frame
Read this before watching.
A design-system lesson is about making visual taste reusable through tokens, components, examples, constraints, and review loops.
New playlist item from AI for Work; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to stack a design plugin, an MCP-connected whiteboard, and a design.md system file into one Codex workflow that goes from brief to three visual directions to a working, self-QA'd prototype.
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.
01Reference
02Tokens
03Components
04Usage rules
05Agent prompt context
06Implementation
07Visual QA
Deep lesson
Turn this video into working knowledge.
2,416 cleaned transcript words reviewed across 682 timed caption segments.
Thesis
Codex Just Solved Product Design teaches a practical design system move: A walkthrough of Codex's new product design plugin — 11 copyable skills covering ideate, image-to-code, prototype, research, and more — combined with a Miro MCP server for visual context and a design.md design system, used to generate a Linear-inspired issue tracker in three visual directions and a one-page gym landing site, with Codex visually QA-ing its own output.
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.
0:16
Eleven portable skills
“more comprehensive UI and then a simple one-page layout. So, let's go. Okay, so the first thing, how do you get access to the plugin? Obviously, you need Codex application, probably one of the the better ones currently...”
The product design plugin is enabled from Codex's plugin list and contains 11 skills — ordered, design Q&A, get context, ideate, image to code, product design, prototype, research, share, URL to code, and user context — each stored as plain copyable text, so you can lift the same skills into Cursor or Claude Code instead of being locked to OpenAI's models. Open the plugin, read two of the 11 skill texts end to end, and note which you could reuse in a different coding agent.
3:45
Layer your context
“to copy it, we just click on design.md and there's a copy button. We are going to go to Codex, just paste this as the first context and then let's go back to to Miro here and just...”
Before prompting, the host assembles three context sources: a design.md file (a Google-backed standard, grabbed from getdesign.md — here the Figma theme with colors, typography, buttons), a Miro board URL whose screenshots of Linear the Miro MCP server lets Codex actually see, and the tagged product design plugin — then runs on GPT-5.5 high with full access. Pick a design.md from getdesign.md, paste it plus a reference-image board into your agent, and prompt for an app in that style to see how faithfully the system is followed.
11:18
Generate, pick, visual QA
“yeah. Let's pick version number one. Hey, I like I like the first version, Performance Lab. So, let's let's go with that one. It's tough. So, Codex has generated the HTML. Now it's doing the QA again. So,...”
The workflow yields three genuinely different image-gen directions to choose from before any code is written (about 9 minutes for the app concepts), and after building, Codex runs its own browser to compare the coded page against the chosen concept image — for the gym landing page it QA'd desktop and mobile visually, producing on-brand hovers, anchors, and a responsive menu from a single HTML file. Ask your agent for three distinct visual directions of one page, pick one, and require it to visually verify the built page against the chosen mockup before you review it.
01
Reference
Start with this video's job: A walkthrough of Codex's new product design plugin — 11 copyable skills covering ideate, image-to-code, prototype, research, and more — combined with a Miro MCP server for visual context and a design.md design system, used to generate a Linear-inspired issue tracker in three visual directions and a one-page gym landing site, with Codex visually QA-ing its own output. Treat "Reference" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:16, where the video says: “more comprehensive UI and then a simple one-page layout. So, let's go. Okay, so the first thing, how do you get access to the plugin? Obviously, you need Codex application, probably one of the the better ones currently...”
02
Tokens
Use "Tokens" to locate the part of the design system mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 3:45, where the video says: “to copy it, we just click on design.md and there's a copy button. We are going to go to Codex, just paste this as the first context and then let's go back to to Miro here and just...”
03
Components
Turn "Components" into the reusable artifact for this lesson: A design-system adoption brief with source references, tokens/components, agent handoff rules, and visual QA checks. This is where watching becomes something you can inspect and reuse.
04
Usage rules
Use "Usage rules" 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
Agent prompt context
Use "Agent prompt context" 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
Implementation
Use "Implementation" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
07
Visual QA
Connect "Visual QA" to Codex Just Solved Product Design by naming the claim, the evidence, and the artifact it should produce.
Example
Source-backed artifact packet
Convert the video into a scoped artifact request that includes the transcript claim, mechanism, acceptance criteria, and proof. The output should be a design-system adoption brief with source references, tokens/components, agent handoff rules, and visual qa checks..
Example
Design system proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the design system pattern.
Example
Teach-back module
Transform the lesson into a definition, a Reference -> Tokens -> Components -> Usage rules -> Agent prompt context -> Implementation -> Visual QA 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.
copying visuals without rules
generic generated UI
no visual QA screenshot pass
Letting the lesson drift into generic design inspiration.
Letting the lesson drift into component lists without usage rules.
Letting the lesson drift into no screenshot review.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: A walkthrough of Codex's new product design plugin — 11 copyable skills covering ideate, image-to-code, prototype, research, and more — combined with a Miro MCP server for visual context and a design.md design system, used to generate a Linear-inspired issue tracker in three visual directions and a one-page gym landing site, with Codex visually QA-ing its own output.
02
Explain the practical stakes without hype: New playlist item from AI for Work; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Reference -> Tokens -> Components -> Usage rules -> Agent prompt context -> Implementation -> Visual QA sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A design-system adoption brief with source references, tokens/components, agent handoff rules, and visual QA checks.
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: Codex Just Solved Product Design
- URL: https://www.youtube.com/watch?v=O3D7yn7gCy0
- Topic: Codex + Claude Workflows
- My current learning frame: Recreate the workflow on a small product idea: feed your agent a design.md plus a mood board of reference screenshots, run the product design plugin to get three directions, build the chosen one, and have the agent visually QA the result against its own mockup.
- Why this matters: New playlist item from AI for Work; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:16 / Evidence 1: "more comprehensive UI and then a simple one-page layout. So, let's go. Okay, so the first thing, how do you get access to the plugin? Obviously, you need Codex application, probably one of the the better ones currently..."
- 2:00 / Evidence 2: "pretty much just copy and paste one command and then authenticate. And actually what this allows the um Codex in this case is to go and interrogate the the Miro board, see what is actually in the board,..."
- 3:45 / Evidence 3: "to copy it, we just click on design.md and there's a copy button. We are going to go to Codex, just paste this as the first context and then let's go back to to Miro here and just..."
- 5:23 / Evidence 4: "actual product brief which is which is quite nice. So build a linear inspired product management and issue tracking app for AI for work workspace. After you confirm I will move to product design. Generate three visual directions."
- 7:17 / Evidence 5: "not just like taking one design and just making small changes. It actually made a few changes that are significant. Yeah, this one looks cool. We've got avatars. We've got like an inbox style. So like a Google..."
- 9:46 / Evidence 6: "So, we are now in Chrome, not Codex. Maybe it's going to be better. The drop-downs, these are just system drop-downs. And then create issue. Can we do anything with it? So, you can create an issue. Yeah,..."
- 11:18 / Evidence 7: "yeah. Let's pick version number one. Hey, I like I like the first version, Performance Lab. So, let's let's go with that one. It's tough. So, Codex has generated the HTML. Now it's doing the QA again. So,..."
Video-aware target:
- Prompt lane: Design system
- Mechanism to extract: Extract how the video turns visual references or component systems into usable constraints for agents.
- Artifact to produce: A design-system adoption brief with source references, tokens/components, agent handoff rules, and visual QA checks.
- Artifact must include: references; tokens/components; handoff artifact; implementation rule; visual QA
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, transcript support, what the demo proves, confidence, and what still needs verification.
3. Extract the actual teachable mechanism from the video: Extract how the video turns visual references or component systems into usable constraints for agents. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A design-system adoption brief with source references, tokens/components, agent handoff rules, and visual QA checks.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Reference -> Tokens -> Components -> Usage rules -> Agent prompt context -> Implementation -> Visual QA
- answers to these source questions: What design source is reused? | How is it translated into agent context? | What review catches generic output?
- 3 concrete examples that apply the video idea to real agentic work, such as Figma-to-shadcn workflow; design.md brief; UI reference library remix
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: copying visuals without rules; generic generated UI; no visual QA screenshot pass
- a checklist for the next real workflow, focused on: references, tokens, components, handoff, QA
- one practical exercise with a clear done signal: Turn one screen reference into five constraints a coding agent must follow.
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 "Codex Just Solved Product Design", not a generic Codex + Claude Workflows essay.
- Cite transcript anchors for every claim about design context, UI generation, preview, critique, or handoff.
- Prefer operational examples, failure modes, and reusable artifacts over broad definitions.
- Call out uncertainty instead of smoothing over weak evidence.
- Avoid these generic drifts: generic design inspiration; component lists without usage rules; no screenshot review.
- If evidence is weak or missing, stop and 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.
One agent should do every task.
Different tools have different strengths. Routing is part of the workflow.
More context is always better.
Relevant context helps; stale context causes drift and cost.
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 design-system adoption brief with source references, tokens/components, agent handoff rules, and visual qa checks..
A reusable artifact with a done signal and one verification step.03
Design system teach-back card
Explain the design system mechanism 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.
Why does the host highlight that the plugin's 11 skills are stored as plain copyable text?
What does the Miro MCP server let Codex do in this workflow?
How does Codex perform QA after generating the gym landing page?
Source shelf
Use the video as a doorway, then verify with primary sources.
