Stop Making AI Slop Landing Pages

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

Source video:
- Title: Stop Making AI Slop Landing Pages
- URL: https://www.youtube.com/watch?v=M4DNgmI7MIM
- Topic: Agent Architecture
- My current learning frame: Build a landing page for a made-up brand starting from a URL or screenshot reference plus a design.md, then do three polish passes: swap the font away from Inter, replace gradients and lights with generated images, and adapt one Mobin section into your design.
- Why this matters: New playlist item from DesignCode; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 1:57 / Evidence 1: "file and you can include that in your next prompt. Especially if you're starting from scratch. Then if you want this as part of a workflow, you put these rules into your agents.md file. The agents.mmd file is..."
- 6:41 / Evidence 2: "you want and it's going to do a far better job. Looking at this one, like I said, if the goal is to avoid the AI slop, this is a good starting point. There are other mistakes. For..."
- 11:12 / Evidence 3: "that are already packed with this information that you can use for your designs. every time that you prompt or every time that you feel that the AI is steering away from something that looks good into something..."
- 13:36 / Evidence 4: "inspiration and that's your goal. It's also adapting to the page using the font that is the design system of the page and it's also setting it in dark mode. Now again coming back to point number three,..."
- 16:09 / Evidence 5: "the model, their strength, and their weaknesses. We have to use screenshots and references and URLs of your favorite websites. We want to use skills and design. MD that are highly available across many many websites. And if..."
- 19:01 / Evidence 6: "and then you want to describe your product. So for example, you know, AI gave Verra. So for my uh yoga studio called Verra and then you add this all to the prom which includes the design. MD..."
- 20:43 / Evidence 7: "going to do at. And by the way, you can do also this in codeex or whatever tool that you want to use. But in this case, you can reference a skill like this. And you can search..."

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 one-page agent harness map with tool boundaries and proof signals.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Intent -> Model -> Harness -> Tools -> Verifier -> Artifact
   - 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 "Stop Making AI Slop Landing Pages", not a generic Agent Architecture 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.