AI WORKFLOW: Claude, Seedance, Kling & Grok

You are helping me turn one specific YouTube video into real, durable learning.

Source video:
- Title: AI WORKFLOW: Claude, Seedance, Kling & Grok
- URL: https://www.youtube.com/watch?v=weR6CyBMCBI
- Topic: Interfaces + Open Design
- My current learning frame: Connect Claude to a generation platform via MCP as a project with instructions and assets, then run one shot through multiple video models and record which model wins on which criteria to start your own model stack.
- Why this matters: New playlist item from Matt Oz; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:46 / Evidence 1: "here called an MCP. So all of the deep research documentation that I put together to be able to prime a Google gem to become my prompt master is evolving into yet again, another workflow and changing the..."
- 5:56 / Evidence 2: "where a video writes a thousand prompts, as opposed to a picture writing a thousand words. It's told me to organize my project into roughly a shot list that I have in an edit that I've constructed from..."
- 21:24 / Evidence 3: "to talking about, I'm testing the different video models in a Claude project space. One of the issues that I'm experiencing with Claude, just up, just to be upfront about it is I got the pro subscription, which..."
- 23:03 / Evidence 4: "usage, I've got this warning message here that says you've hit your limit for Claude messages limits will reset at 4am. That was last night view your usage details. And I believe that what happens here is you..."
- 25:53 / Evidence 5: "I basically gave Claude my criticisms and top picks and explained why I'm picking those kinds of things because it's also producing something called a production Bible for me, like a almanac of information. As I'm developing this..."
- 56:44 / Evidence 6: "four hours before my usage resets. This here saying all models reset at 1am. I don't know what that means. But that doesn't seem to be an issue. It's the session time, the session limits that I'm hitting."
- 64:49 / Evidence 7: "And maybe maybe And maybe that's the key to unlocking the speed that I need to be able to work out instead of getting one or two shots per session, four shots in a day if I'm lucky."

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 UI critique sheet for judging whether an AI interface improves control.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Intent -> Canvas -> Artifact -> Preview -> Feedback -> Iteration
   - 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 "AI WORKFLOW: Claude, Seedance, Kling & Grok", not a generic Interfaces + Open Design 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.