The Future of Photo Editing? (Claude AI + Affinity First Test)

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

Source video:
- Title: The Future of Photo Editing? (Claude AI + Affinity First Test)
- URL: https://www.youtube.com/watch?v=b27XG3UFrOM
- Topic: Creative Automation
- My current learning frame: Set up Claude desktop with the Affinity connector and MCP enabled, ask Claude to crop a photo to its subject and add a border, save it as a script, then run that script on two differently-composed photos and document exactly where the saved script succeeds versus where its baked-in logic fails.
- Why this matters: A practical bridge from agentic coding to visual work.

Transcript anchors from this exact video:
- 0:27 / Evidence 1: "Claude. If we look at the bullet points for this item, we see it says no coding knowledge required. Describe reproductive production tasks in plain language to Claude desktop. Work with existing documents as well as new ones."
- 2:35 / Evidence 2: "point because it does say the free plan can integrate through connectors with the remote MCP, which is how this Claude Affinity connection works. And in the Affinity help document, it also says that this AI automation connection..."
- 4:18 / Evidence 3: "we have our model context protocol turned on so that it's ready to communicate as well. So, for me on Windows in Affinity, I'm just going to come to under the edit menu and choose settings. For you,..."
- 5:54 / Evidence 4: "allow Claude permission to perform certain tasks in Affinity. So, you can expect this if this is the first time you're trying to use this. So, it's doing things like checking documentation, checking commands. Now, it says that..."
- 11:02 / Evidence 5: "is there and we're going to talk about that, but let's talk about really how this connection is working and the pros and cons that exist within this Claude and Affinity workflow. So here's what's actually happening behind..."
- 13:51 / Evidence 6: "you mean, doesn't actually know what you mean. So you have to be very specific, you have to be ready to correct Claude or the AI when it makes mistakes. And again, this is not deterministic, you could..."
- 20:25 / Evidence 7: "ways to speed up the workflow and to amplify their own creativity and individuality. So, that's really going to be the challenge with AI. You might be able to find some easy wins with it, but there also..."

Video-aware target:
- Prompt lane: Creative automation
- Mechanism to extract: Extract the creative production loop, especially where the human keeps taste, selection, and final judgment.
- Artifact to produce: A creative production board with source inputs, prompt recipe, selection criteria, edit pass, and taste-review checkpoints.
- Artifact must include: brief; source inputs; generation recipe; selection criteria; edit/review checkpoint

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 the creative production loop, especially where the human keeps taste, selection, and final judgment. Do not invent claims that are not supported by the title, lesson frame, or transcript anchors.
4. Build a reusable learning artifact: A creative production board with source inputs, prompt recipe, selection criteria, edit pass, and taste-review checkpoints.
5. Include:
   - a plain-English definition of the core idea
   - a diagram or structured model using this sequence: Brief -> Source material -> Generation -> Selection -> Edit -> Taste review -> Reusable recipe
   - answers to these source questions: What asset is being produced? | What inputs and tools drive it? | Where does human taste intervene?
   - 3 concrete examples that apply the video idea to real agentic work, such as Claude-generated video campaign; image-to-site workflow; voice or video editing loop
   - 2 failure modes the video helps prevent, chosen from the transcript evidence and these likely risks: mistaking novelty for quality; no source/brief discipline; shipping generated media without taste review
   - a checklist for the next real workflow, focused on: brief, inputs, generation, selection, critique
   - one practical exercise with a clear done signal: Build one reusable creative recipe and define what would make the result rejectable.
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 "The Future of Photo Editing? (Claude AI + Affinity First Test)", not a generic Creative Automation essay.
- Anchor each creative step to transcript evidence about inputs, model/tool choices, iteration, editing, or critique.
- 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 content advice; tool hype; creative output without selection 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.