Ideogram Just Dropped an MCP (AI Photoshoots Inside Claude Code)

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

Source video:
- Title: Ideogram Just Dropped an MCP (AI Photoshoots Inside Claude Code)
- URL: https://www.youtube.com/watch?v=MYPlBOvV6kc
- Topic: Creative Automation
- My current learning frame: Run the full loop yourself: install the Ideogram MCP, research one real brand's style with Claude Code's browser, generate a small on-brand shoot featuring your own reference photos, and assemble the results into a product page on a connected canvas.
- Why this matters: New playlist item from Lukas Margerie; queued for transcript-backed review, topic mapping, and a practical learning artifact.

Transcript anchors from this exact video:
- 0:23 / Evidence 1: "with Claude Code specifically. There are a few examples of things that you can build with this MCP here in the site, but they're pretty simple. Obviously, when you plug this into Claude Code, you can connect this..."
- 2:05 / Evidence 2: "more about custom model training. What does that mean?" So, you can give it like a specific character or person, a product, a brand, style, or a mascot. And these are the different schemas to kind of go..."
- 3:40 / Evidence 3: "style, and also their graphic tees." And now Claude Code is basically using the browser to inspect Instagram and inspect the grid of photographs. It tries to also go into their Shopify store, but it's not it's not..."
- 5:19 / Evidence 4: "images that you've generated with Ideogram and automatically upload the images you generate in this conversation into this Magic Path project. All right. And now we have our three images in this kind of like Figma type interface."
- 6:55 / Evidence 5: "want it to have like this type of style, this heavy metal typography style. What I can do is I can just Google Google something like this, and maybe just take a screenshot of one that we like."
- 9:00 / Evidence 6: "Cloud Code and say, "Create a product detail page in in the magic path project for these three selected images." And basically we can just zoom in here at the bottom and we have this new landing page."

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 "Ideogram Just Dropped an MCP (AI Photoshoots Inside Claude Code)", 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.