AI tools & skills I've been using in my design process β thoughts from a product design leader
This video surveys a product designer's practical AI toolkit, from voice-first prompting and plan pressure-testing to visual exploration, agent-readable component foundations, precise annotations, targeted design skills, and live UI tuning. The central lesson is to choose a focused tool for each stage instead of applying every AI tool to every project.
femke.design12 minTranscript 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 femke.design; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to assemble an AI-assisted product design workflow that preserves intentional decisions, precise feedback, and visual craft from initial idea through implementation polish.
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.
2,489 cleaned transcript words reviewed across 714 timed caption segments.
Thesis
AI tools & skills I've been using in my design process β thoughts from a product design leader teaches a practical design system move: This video surveys a product designer's practical AI toolkit, from voice-first prompting and plan pressure-testing to visual exploration, agent-readable component foundations, precise annotations, targeted design skills, and live UI tuning. The central lesson is to choose a focused tool for each stage instead of applying every AI tool to every project.
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.
0:35
Speak Richer Prompts
βbuild side of AI assisted design. The skills and systems that are shaping how AI generated work turns out, not just the flashy tools. Are you ready? Buckle in cuz we've got a lot of tools to get...β
A handheld microphone creates an intentional capture ritual, while Monolog transcribes, organizes, and summarizes spoken thoughts into usable text. Dictation helps the speaker give longer, more detailed prompts than typing, which leads to better AI output. Dictate one product idea into a transcription tool, then compare the detail and structure of the resulting prompt with a version you type from scratch.
6:24
Annotate Exact Elements
βnot just a sealed package. And it's basically like a design system out of the box that your AI agent can work with. Another one that I've heard about, but I've yet to explore is Astrix, which I...β
Agentation turns clicks on a running app into structured feedback that includes the CSS selector, source path, component tree, and computed styles. Passing those annotations directly to a coding agent replaces vague descriptions with exact implementation context and reduces back-and-forth. Annotate three specific UI problems in a running page and write agent requests that reference each numbered annotation instead of describing element locations manually.
8:36
Tune Values Live
β{slash} polish or {slash} distill to kind of steer the output, and it also includes a design.md file that keeps the system consistent across sessions. So, I kind of like to run it as a pass after the...β
Dial Kit exposes real values from a running app through sliders and toggles, letting a designer tune easing, spacing, blur, and spring physics in real time. This closes the gap between judging how an interaction feels and repeatedly guessing numeric values through prompts and rebuilds. Connect one animated element to live controls and adjust its spring or easing until you can describe which values produce the intended feel.
01
Reference
Start with this video's job: This video surveys a product designer's practical AI toolkit, from voice-first prompting and plan pressure-testing to visual exploration, agent-readable component foundations, precise annotations, targeted design skills, and live UI tuning. The central lesson is to choose a focused tool for each stage instead of applying every AI tool to every project. Treat "Reference" as the outcome you are trying to make visible, not a topic label. Anchor it to 0:35, where the video says: βbuild side of AI assisted design. The skills and systems that are shaping how AI generated work turns out, not just the flashy tools. Are you ready? Buckle in cuz we've got a lot of tools to get...β
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 6:24, where the video says: βnot just a sealed package. And it's basically like a design system out of the box that your AI agent can work with. Another one that I've heard about, but I've yet to explore is Astrix, which I...β
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 AI tools & skills I've been using in my design process β thoughts from a product design leader 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: This video surveys a product designer's practical AI toolkit, from voice-first prompting and plan pressure-testing to visual exploration, agent-readable component foundations, precise annotations, targeted design skills, and live UI tuning. The central lesson is to choose a focused tool for each stage instead of applying every AI tool to every project.
02
Explain the practical stakes without hype: New playlist item from femke.design; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Intent -> Context -> Generation surface -> Preview -> Critique -> Implementation handoff sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A UI control-surface critique sheet with context inputs, artifact visibility, review criteria, and implementation handoff.
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: AI tools & skills I've been using in my design process β thoughts from a product design leader
- URL: https://www.youtube.com/watch?v=Zq8tstsPRjE
- Topic: Interfaces + Open Design
- My current learning frame: Take one small interface from rough idea to polished interaction by dictating its brief, annotating three implementation fixes, and live-tuning one motion or spacing value.
- Why this matters: New playlist item from femke.design; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 0:35 / Evidence 1: "build side of AI assisted design. The skills and systems that are shaping how AI generated work turns out, not just the flashy tools. Are you ready? Buckle in cuz we've got a lot of tools to get..."
- 2:44 / Evidence 2: "product, and digital designers who want more structure when they're building new skills. Instead of piecing everything together from tutorials, you get a clear learning path, live sessions with working designers, access to mentors, and a community working..."
- 4:27 / Evidence 3: "like that's the point because you don't just run it when you want to move fast, you run it when you want to be intentional, when you want to make sure you're covering everything you need to consider..."
- 6:24 / Evidence 4: "not just a sealed package. And it's basically like a design system out of the box that your AI agent can work with. Another one that I've heard about, but I've yet to explore is Astrix, which I..."
- 8:36 / Evidence 5: "{slash} polish or {slash} distill to kind of steer the output, and it also includes a design.md file that keeps the system consistent across sessions. So, I kind of like to run it as a pass after the..."
- 11:24 / Evidence 6: "well on its own. This is probably the smallest thing on the list and maybe the best argument for why design taste still matters when the building is automated. So, that's it. That's kind of a high-level rundown..."
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 "AI tools & skills I've been using in my design process β thoughts from a product design leader", not a generic Interfaces + Open Design 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.
A beautiful page is automatically a good learning tool.
Learning requires sequence, active recall, feedback, and application.
Generated UI should be accepted as-is.
Generated UI needs critique, revision, and browser verification.
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 β without rewatching.
What roles do the microphone and Monolog play in the voice-first capture workflow?
How does Agentation make feedback to a coding agent more precise?
What problem does Dial Kit solve when refining a working interface?
Source shelf
Use the video as a doorway, then verify with primary sources.