Claude Plans, Gemini Designs: One Workflow for Beautiful Frontends (LIVE)
This live stream builds an Archon workflow that mixes three models across providers to produce a beautiful, accurate frontend: Opus plans the content and integrations, Gemini 3.5 Flash builds the UI, and Sonnet handles cheaper validation, with Clerk authentication bolted on via its Claude Code skill and Gemini accessed through OpenRouter via Pi.
Cole Medin140 minTranscript found
Quick learning frame
Read this before watching.
Coding-agent workflow is the loop of inspect, route, plan, edit, verify, summarize, and decide what should be automated next.
New playlist item from Cole Medin; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Skill you build: The ability to design a mixed-provider, multi-model coding workflow that routes each stage (planning, UI generation, integration, validation) to the model that is strongest and cheapest for it, rather than using one model end to end.
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.
01Inspect context
02Route tool
03Plan work
04Edit safely
05Verify behavior
06Report next step
Deep lesson
Turn this video into working knowledge.
23,323 cleaned transcript words reviewed across 6,621 timed caption segments.
Thesis
Claude Plans, Gemini Designs: One Workflow for Beautiful Frontends (LIVE) teaches a practical coding-agent workflow move: This live stream builds an Archon workflow that mixes three models across providers to produce a beautiful, accurate frontend: Opus plans the content and integrations, Gemini 3.5 Flash builds the UI, and Sonnet handles cheaper validation, with Clerk authentication bolted on via its Claude Code skill and Gemini accessed through OpenRouter via Pi.
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.
1:35
Route models to strengths
“Opus decide here's the information to put on the front end and then we have Gemini 3.5 flash build the UI and then any kind of integrations that we need with our application uh like authentication for example...”
Gemini 3.5 Flash builds crazy good-looking frontends but hallucinates a lot of on-page content and falls flat on integrations, so the plan is to have Opus decide the actual information, Gemini build the UI, and Opus again handle integrations like Clerk authentication, all orchestrated as one Archon workflow. For a landing page you'd build, write down which single model you'd assign to content/planning, to UI, and to integrations, and justify each choice from that model's known weakness.
55:05
Why Gemini alone fails
“implementation you run the tests or before you do your planning you load in some context deterministically like that there's none of that in here as well so you're you're really still just like shoving your entire system...”
The build-UI step run by Gemini 3.5 Flash skipped a huge part of the prompt: it never wrote the required UI summary into the artifact directory listing every file and integration stub that the Opus integrate step needed, which is exactly why the workflow doesn't rely on Gemini for the whole task. Take a multi-step prompt you've used and add an explicit checkable artifact each step must output, so a downstream step can verify the previous one actually did its job.
85:31
Spec to deployed app
“obviously I'm doing a lot more like AI coding content now, but as far as like building production grade AI agents and orchestrating them with Langraph, like this is still the stack in my mind. But yeah, this...”
Every node ran across providers and finished; the Opus integrate step alone ran about 31 minutes while everything else was fast, producing a real full-stack Next.js app with working Clerk OAuth, passing tech checks, and a Vercel deploy, though clerk deploy's interactive wizard couldn't be driven by Claude Code and needed the human to run it. List which steps of an end-to-end deploy (build, auth setup, tech checks, deploy) an agent can fully automate versus where an interactive wizard forces a human step, using this Clerk-deploy example as your model.
01
Inspect context
Start with this video's job: This live stream builds an Archon workflow that mixes three models across providers to produce a beautiful, accurate frontend: Opus plans the content and integrations, Gemini 3.5 Flash builds the UI, and Sonnet handles cheaper validation, with Clerk authentication bolted on via its Claude Code skill and Gemini accessed through OpenRouter via Pi. Treat "Inspect context" as the outcome you are trying to make visible, not a topic label. Anchor it to 1:35, where the video says: “Opus decide here's the information to put on the front end and then we have Gemini 3.5 flash build the UI and then any kind of integrations that we need with our application uh like authentication for example...”
02
Route tool
Use "Route tool" to locate the part of the coding-agent workflow mechanism the video is demonstrating. Ask what changes in your real setup if this claim is true. Anchor it to 55:05, where the video says: “implementation you run the tests or before you do your planning you load in some context deterministically like that there's none of that in here as well so you're you're really still just like shoving your entire system...”
03
Plan work
Turn "Plan work" into the reusable artifact for this lesson: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal. This is where watching becomes something you can inspect and reuse.
04
Edit safely
Use "Edit safely" 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
Verify behavior
Use "Verify behavior" 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
Report next step
Use "Report next step" to carry the idea forward: save the prompt, checklist, diagram, or operating rule that would make the next agent run better.
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 coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
Example
Coding-agent workflow proof brief
Separate what the speaker claims, what the demo actually proves, and what still needs outside verification before you adopt the coding-agent workflow pattern.
Example
Teach-back module
Transform the lesson into a definition, a Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step 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.
choosing tools by hype
losing context across agents
letting parallel sessions become invisible
Letting the lesson drift into generic Codex vs Claude comparison.
Letting the lesson drift into feature lists without task routing.
Letting the lesson drift into claims that ignore limits or recovery.
Do not count this as learned until these are true.
01
State the transcript-backed claim in your own words: This live stream builds an Archon workflow that mixes three models across providers to produce a beautiful, accurate frontend: Opus plans the content and integrations, Gemini 3.5 Flash builds the UI, and Sonnet handles cheaper validation, with Clerk authentication bolted on via its Claude Code skill and Gemini accessed through OpenRouter via Pi.
02
Explain the practical stakes without hype: New playlist item from Cole Medin; queued for transcript-backed review, topic mapping, and a practical learning artifact.
03
Map the idea onto the Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step sequence and name the weakest link.
04
Produce the artifact and include the evidence that proves it: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
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: Claude Plans, Gemini Designs: One Workflow for Beautiful Frontends (LIVE)
- URL: https://www.youtube.com/watch?v=Xh1z23uBZo0
- Topic: Interfaces + Open Design
- My current learning frame: Take a simple app spec and build a small multi-step pipeline that has a strong model plan the content, a UI-focused model build the frontend, and a third step validate, checking that each stage writes the artifact the next stage needs.
- Why this matters: New playlist item from Cole Medin; queued for transcript-backed review, topic mapping, and a practical learning artifact.
Transcript anchors from this exact video:
- 1:35 / Evidence 1: "Opus decide here's the information to put on the front end and then we have Gemini 3.5 flash build the UI and then any kind of integrations that we need with our application uh like authentication for example..."
- 51:42 / Evidence 2: "over Claude Code's dynamic workflow? So that's a good question. Um, Claude Code's dynamic workflow though is is not really the same thing as Archon at all because it's more about just orchestrating sub agents. It's not really..."
- 55:05 / Evidence 3: "implementation you run the tests or before you do your planning you load in some context deterministically like that there's none of that in here as well so you're you're really still just like shoving your entire system..."
- 85:31 / Evidence 4: "obviously I'm doing a lot more like AI coding content now, but as far as like building production grade AI agents and orchestrating them with Langraph, like this is still the stack in my mind. But yeah, this..."
- 94:06 / Evidence 5: "because I didn't really give it any skills like agent browser for browser automation. I mean there's so many ways that I could have made this workflow better. I could have split up the plan more like I..."
- 131:02 / Evidence 6: "always use sub agents for either web research or codebased exploration because that's where just having some summary returned to your main agent is all the information you really need. So not not sub aents for implementation but..."
- 132:41 / Evidence 7: "usage limits like crazy. Are you talking about the new dynamic workflows in Claude? Because that might be true, but also for any kind of sub agent, you can choose to use a different model like Haiku or..."
Video-aware target:
- Prompt lane: Coding-agent workflow
- Mechanism to extract: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review.
- Artifact to produce: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
- Artifact must include: task class; agent/tool choice; context packet; verification step; handoff/recovery rule
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: Find the workflow rule that explains when and how to use Codex, Claude Code, browser control, dashboards, or manual review. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal.
5. Include:
- a plain-English definition of the core idea
- a diagram or structured model using this sequence: Inspect context -> Route tool -> Plan work -> Edit safely -> Verify behavior -> Report next step
- answers to these source questions: What workflow pain is being solved? | What exact coordination mechanism is shown? | What evidence proves it changes the work?
- 3 concrete examples that apply the video idea to real agentic work, such as rate-limit routing; browser verification after a UI edit; long-running /goal session review
- 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: choosing tools by hype; losing context across agents; letting parallel sessions become invisible
- a checklist for the next real workflow, focused on: routing decision, context portability, verification, handoff summary
- one practical exercise with a clear done signal: Route three recent tasks across Codex, Claude, browser checks, and manual review with a reason for each.
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 "Claude Plans, Gemini Designs: One Workflow for Beautiful Frontends (LIVE)", not a generic Interfaces + Open Design essay.
- Each workflow rule must point to a timestamped claim or demo moment, then state what remains unproven.
- 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 Codex vs Claude comparison; feature lists without task routing; claims that ignore limits or recovery.
- 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 coding-agent routing and execution matrix with context needed, tool choice, verification, and done signal..
A reusable artifact with a done signal and one verification step.03
Coding-agent workflow teach-back card
Explain the coding-agent workflow 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.
Which model does each stage of the workflow use, and why is the work split this way?
What critical step did Gemini's build-UI run skip, and why did it matter?
In the final deploy, what could the agent not do on its own?
Source shelf
Use the video as a doorway, then verify with primary sources.
