You Don't Own Your AI. The Harness Does.

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

Source video:
- Title: You Don't Own Your AI. The Harness Does.
- URL: https://www.youtube.com/watch?v=k8jYOcQUB_A
- Topic: Interfaces + Open Design
- My current learning frame: Audit an existing agent stack layer by layer, score its harness for control and portability, then sketch one interface change tailored to a task you perform repeatedly.
- Why this matters: New playlist item from Manolo Remiddi; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 1:14 / Evidence 1: "router for example. When you connect the API from that services and then you have access to the different models and then finally the harness. This is what manage the agent loops, the tools, the context, the permissions..."
- 4:10 / Evidence 2: "memory is where you start saving your sessions, your data, project instructions, skills, and so on. This is the long-term memory. We can see this as a database. Some harnesses use more than one memory system depending if..."
- 7:35 / Evidence 3: "the top I have my local model. Of course, I created a series of plugins for this system. For example, this meta folder. This is a folder that I can give color to it where I can move..."
- 10:11 / Evidence 4: "transparency is amazing. I can read the system front of the agent. I can see the context that is being injected. This is extremely powerful. Not everybody needs this. You don't need this all the time, but I'm..."
- 13:20 / Evidence 5: "ability to inject specific prompt that I already created. So all I need to do is slash and for example news. This is one of the prompt get injected inside the input window and then I send it."
- 17:04 / Evidence 6: "your specific use case? What kind of agent interface you need? Design it. Think about how it should work. For me, I use the computer and the browser. So I made a browser version sidecar there. And then..."
- 19:35 / Evidence 7: "will be released the Mac OS and Windows soon. There is this sidebar that is part of the project. All you need to do is give this prompt to your agent and the agent will install it for..."

Video-aware target:
- Prompt lane: AI interface control
- Mechanism to extract: Extract how the interface gives the user control over context, visual quality, generated artifacts, and handoff.
- Artifact to produce: A UI control-surface critique sheet with context inputs, artifact visibility, review criteria, and implementation handoff.
- Artifact must include: context input; visual target; preview/review step; implementation handoff; quality rubric

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 interface gives the user control over context, visual quality, generated artifacts, and handoff. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A UI control-surface critique sheet with context inputs, artifact visibility, review criteria, and implementation handoff.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Intent -> Context -> Generation surface -> Preview -> Critique -> Implementation handoff
   - answers to these source questions: What does the interface let the user control? | What artifact becomes visible? | What critique or handoff step closes the loop?
   - 3 concrete examples that apply the video idea to real agentic work, such as design.md handoff; Figma-to-code review; UI reference library translation
   - 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: generic UI inspiration; visual output with no critique; handoff that lacks implementation criteria
   - a checklist for the next real workflow, focused on: context, preview, artifact visibility, critique, handoff
   - one practical exercise with a clear done signal: Turn one UI demo into a design-review checklist for a real product screen.
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 "You Don't Own Your AI. The Harness Does.", 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 tips; visual hype without inspection; screenshots without implementation criteria.
- 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.