AI slop is real: here's how you avoid it when building apps in WeWeb

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

Source video:
- Title: AI slop is real: here's how you avoid it when building apps in WeWeb
- URL: https://www.youtube.com/watch?v=BjGF0asnqmc
- Topic: Agent Architecture
- My current learning frame: Grab a favorite brand's design.md from getdesign.md, generate a small expense-tracker interface in WeWeb with it, verify the colors and typography in the library guidelines, add one custom hover color, and lock AI editing of the library to none.
- Why this matters: New playlist item from WeWeb; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:31 / Evidence 1: "their design.md file. And I'll show you a few examples of prompts that I tried in WeWeb. I used always the same prompt and then just pasted a different design MD. So, here for example, I want to..."
- 2:52 / Evidence 2: "right here in our library, we see the design system guidelines that should be taken from the prompt that we shared, has some hierarchy and we can find uh some of the colors here. So, let's see to..."
- 6:08 / Evidence 3: "whenever you ask AI to do something, it will follow the design the guidelines of the project's design system. And you can you do also have some settings. You can allow AI to edit your library or on..."

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 "AI slop is real: here's how you avoid it when building apps in WeWeb", 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.