The argument in one line.
Because Claude generates code instead of images, it produces on-brand carousels with accurate fonts and consistent design tokens that image generators routinely hallucinate away.
Read if. Skip if.
- A solo creator or marketer who posts regularly to Instagram and wants carousel posts without hiring a designer or subscribing to another tool.
- Anyone who has a working brand palette and wants every new post to inherit it automatically from a single Claude Project.
- Someone comfortable copying and pasting prompts but not interested in writing code.
- You already have a Canva template system — the creator explicitly recommends using the Canva connector inside Claude instead.
- You need image-generation effects (photos, illustrations, AI art) rather than typographic and layout-driven slides.
The full version, fast.
Claude has no image model, but it can write HTML — and that turns out to be better for branded carousel posts than image generation. The workflow: upload reference carousels, prompt Claude to extract the design system as JSON (colors, fonts, layout), paste that JSON into a Claude Project's instructions, then drop any content into the project and get a fully styled, downloadable carousel in one prompt. Because Claude generates actual font names rather than rendering them, slides look exactly on-brand. If download fails, ask Claude to convert to PNG. If you already have Canva templates, use the Canva connector instead.
Chat with this breakdown — free.
Sign in and you get 23 free chat messages on us — ask for the hook, quote a framework, find the exact transcript moment, generate a markdown action plan. Bring your own key when you want unlimited.
Create a free account →Where the time goes.

01 · Cold open — the inverted question
Host flips the usual AI framing: the interesting question in 2026 is what Claude cannot do. Introduces the carousel workflow as the example.

02 · Inspiration — existing carousels that perform
Shows his Practically AI Instagram page and infographic carousels that have been getting traction, which became the design reference for this workflow.

03 · Step 1 — Extract design system to JSON
Upload reference carousel images to Claude, run the style-extraction prompt (ignore content, capture colors/fonts/layout as JSON). The output is structured design data, not training.

04 · Step 2 — Set up a Claude Project
Create a new Claude Project, paste the JSON design system into project instructions, and add the carousel generation system prompt with brand-gating logic.

05 · Why code, not images
Explains the core mechanism: Claude writes HTML with real font names rather than rendering an image, producing accurate typography. The slides are code, exported as images.

06 · Step 3 — Generate carousels from content
Demo: paste a newsletter article, Claude asks for brand/account, confirms color palette, generates seven slides with progress bar. Looks clean, no errors.

07 · Step 4 — Download as PNG
Download each slide individually. Troubleshoot tip: if download fails, ask Claude to convert to PNG first.

08 · When to use Canva connector instead
If you already have a Canva template system, connect Canva inside Claude and use that. Do not rebuild what already works.

09 · Closing — do not overengineer with AI
The final lesson: capability does not equal obligation. Ask whether you should use AI for something, not just whether you can.
Lines worth screenshotting.
- Claude generates HTML carousels using real font names, which means slides look exactly on-brand — image generators hallucinate fonts into blurry approximations.
- Extracting your design system once as JSON and storing it in a Claude Project eliminates almost all prompting for every future carousel.
- The style-extraction prompt works by telling Claude to ignore written content entirely and capture only visual DNA: colors, fonts, layout, aesthetic.
- A Claude Project's persistent instructions function as a brand style guide that runs silently on every conversation in that project.
- Asking Claude to identify which account a carousel is for before generating lets a single project serve multiple brands without confusion.
- If a carousel slide will not download, asking Claude to convert it to PNG first fixes the issue every time.
- Just because you can do something with AI does not mean you should — the workflow is worth building only when you lack an existing template system.
- The better path for creators who already have Canva templates is the Canva connector inside Claude, not rebuilding a design system from scratch.
Claude writes carousels better than image generators do.
Because Claude generates code with real font references instead of rendering pixels, its carousels are more accurate and more repeatable than anything an image model produces.
- Storing a brand's design system as a JSON token set in Claude's project instructions eliminates manual styling on every future generation — the brand travels with the prompt.
- Style extraction works by instructing Claude to ignore all written content and return only visual properties: color values, font families, layout approach, and spacing conventions.
- HTML-generated slides use actual font names from Google Fonts or system stacks, which means typography is crisp and legible — image generators approximate fonts and often distort them.
- A brand-gating step (asking which account before generating) lets one Claude Project serve multiple brands without cross-contamination.
- Downloading a generated slide as PNG is a two-step fallback: if the direct download fails, ask Claude to convert the slide to PNG.
- The Canva connector inside Claude is the better path when a template already exists — building a new code-based system from scratch only makes sense when no template does.
- Capability does not equal obligation: the most durable lesson in the video is to ask whether a task should use AI before asking how it could.
Terms worth knowing.
- Design token
- A named variable that stores a single design value — a hex color, a font family, a spacing unit — so every element that references it updates consistently when the value changes.
- Claude Project
- A persistent workspace inside Claude where custom instructions, uploaded files, and conversation history are shared across every chat in that project, functioning like a standing brief.
- Swipeable HTML carousel
- A single HTML file containing multiple slides with navigation controls, designed so each slide can be screenshotted or exported as an individual image for social media posting.
- Canva connector
- A native integration inside Claude that lets you read, edit, and create Canva designs directly from a Claude conversation without leaving the chat interface.
Things they pointed at.
Lines you could clip.
“If there is something you could do with AI, does it mean you should?”
“The question we should be asking is not what things you can do with Claude, but what is something Claude cannot do?”
Word for word.
Don't just watch it. Burn it in.
See every word as it's spoken — crank it to 2× and still catch all of it. The same dual-channel trick behind Amazon's Kindle + Audible.
The bait, then the rug-pull.
The hook inverts the expected question — not what Claude can do, but what it cannot — and then immediately answers it by showing a capability most people assume is off-limits: generating polished, brand-consistent Instagram carousels without any image model at all.
Named ideas worth stealing.
Design System Extraction to Project Injection
- Extract visual DNA from reference images as JSON
- Store JSON in Claude Project instructions
- Generate brand-consistent output on every prompt
A two-step setup that front-loads all branding work so ongoing generation requires no design prompting.
How they asked for the click.
“Give a thumbs up if this video was useful, you learned something new, you feel inspired on things you can do with Claude.”
Soft and conversational. Bundled with newsletter link in description. No aggressive pitch.







































































