Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Spent weeks perfecting AI system prompts. Here's what most people get wrong: They write instructions. I engineer architectures. The difference: ❌ "You are a helpful design assistant. Create landing pages when asked." ✓ "You are a conversion-focused UI architect. End goal: production-ready landing page that converts skeptical B2B buyers.... Constraints: no gradients, max 3 colors, 8px radius. Style: swiss minimal, editorial whitespace. Output: section-by-section, not full page. Validate each section against the trust test before proceeding." The 5-step method: 1. Define the end goal first (what does success look like?) 2. Ask AI to draft a system prompt for that goal 3. Extract every important keyword and constraint 4. Rewrite with your domain expertise layered in 5. Run through Gemini Gem to structure it as clear instruction blocks Works on Claude design. Cursor code. Custom agents. Everything. Specificity isn't optional. It's the entire game. Like + reply "INSTRUCT" for my full prompt engineering method. (must be following for DM)show more

MotionViz

12,141 subscribers

21,609 views • 8 months ago •via X (Twitter)

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

My AI made Shopify pages are getting better and better everyday Here’s an example of a Shopify section I built with the reference page and the result on my store 👇 Guide: To make good AI landing pages, you need to use the same method as making good AI UGC or AI product images you have to take something that's already good as a reference for Claude/gemini to analyze and adapt for your product/brand for now you can't adapt full landing pages to your product because the Claude context gets bloated fast and you get poor output. Listicles are the only kind of page you can "one shot" with Claude. But Product pages are another story Analyze an existing page and adapting it to your product section by section is the way to go. The results are 10x better. here's an example (on the video): 1- I found this good product section from im8's product page. I screen-recorded the section on both desktop and mobile, going through the animations to capture the dynamism that a screenshot wouldn’t show. Then I asked Claude Web or Gemini to analyze the recording and produce a very detailed report. Full prompt is on my TG channel, it's quite long. 2- then ask Claude (inside your Shopify brand project folder): "I have a detailed UI/UX specification document for a product page section I want to adapt to my product. Recreate this exactly on Shopify as a section template and adapt it to [name of the product] using the brand guidelines" (paste the result prompt from step 1 ). 3- you will have your section ready after 3-4 minutes. you'll probably have to change a few things. spacing, small visual bugs, price not appearing correctly. it will take you 5 minutes maximum. 4- then you can ask Claude to make 4 different variations of the section using different designs and pick the best one using this prompt: "Create 4 design variations of this section. Keep the content and layout structure identical across all, only vary the visual treatment (color usage, typography hierarchy, spacing, component styling). I will choose the one I like the most." after that you have a pretty good section, and you can do the process again for all sections of the page. The less complex the section, the faster the process will be. note: I know the AI result is not perfect, but it's pretty impressive imo and it will only get better.

Olivier

84,679 views • 6 months ago

Figma Capture + Claude Fable 5 = clone any competitor's landing page in minutes 🤯 Figma just dropped a Chrome extension that copy/pastes any live website into Figma as editable layers. Point Claude Code — running the new Fable 5 model — at the capture, and it rebuilds the whole page in YOUR brand: structure, copy, design system, photography. All inside Claude Code. Perfect for DTC brands and agencies who keep losing weeks rebuilding proven landers from scratch. If you're still cloning competitor pages the old way, You're screenshotting their site and praying the AI guesses the structure right. You're rebuilding sections by hand because the fonts and spacing never come out true. You're paying a designer $3K to recreate a page that already exists. This workflow eliminates the entire loop: → Capture the competitor's landing page with Figma's new Chrome extension — editable layers, not screenshots → Claude Code reads the page structure through the Figma MCP: every section, every headline, in order → It rebuilds the page in YOUR brand — your colors, your fonts, your voice (it even respects your banned-words list) → GPT Image 2 generates on-brand product photography from the layer names → Claude places every image automatically — finished page, ready to ship No screenshots. No guessing at structure. No design invoice. What you get: → A pixel-structured clone of any proven lander, rebuilt in your brand → Every line of copy rewritten in your voice → 16 on-brand images generated and placed for ~$2 in API costs → Start to finish in about 15 minutes Built 100% with Figma + Claude Code on Claude Fable 5. I put together a step-by-step playbook showing you exactly how to set it up. Want access for free? > Like this post > Comment "CLONE" And I'll send it over (must be following so I can DM)

Mike Futia

47,034 views • 3 months ago

I make unlimited landing pages with Claude Cowork for $0 😱 here's the system that turns one URL into a landing page for every possible angle: step 1: scrape your brand DNA → Firecrawl scrapes your site. trust signals, colors, fonts, the works → I pointed it at virlo and it pulled every proof element & visual system in 90 seconds → nothing hallucinated. everything traced back to your actual site step 2: figure out WHY your product works → not the features but the reason someone should care. → maps which claims you can back up vs ones you can't step 3: lock your brand voice → pulls your exact phrases, tone, language patterns → ran it on a client last week. they thought they wrote the page. they didn't. step 4: write the copy → hard ban list kills AI slop on sight ("unlock", "seamless", "revolutionize" = dead) → then cuts 20% of whatever it wrote. if a line doesn't earn its spot, it's gone. step 5: generate on-brand visuals → Bloom creates images that ACTUALLY match your brand (s/o Ray for hooking up FREE bloom credits, ill send you a link) → no stock photo energy. no purple AI gradients. no "two businesspeople shaking hands." step 6: build the page → single-file HTML. responsive. ready to roll. → routes layout by type. product, SaaS, lead gen, regulated all look different → one product. six angles. six pages. each one ships. step 7: QA gate → scores every page on proof, trust, copy, visuals, anti-slop → shippable, draft, or blocked. nothing goes live without passing. input: your URL output: unlimited landing pages w/ copy & brand images Steal Ads automates ads. this builds landers for each. money ad → money page. agencies charge $5-10K per landing page. this builds unlimited pages for $0. I packaged the entire system as the Landing Page Factory. 7 Claude skills: - site-extract (brand DNA via Firecrawl) - page-strategy (mechanism mapping + real claims) - brand-profile (your voice + your branding) - page-copy (conversion copy w/ slop ban) - page-visuals (on-brand images w/ Bloom) - page-build (multiple variations & layouts) - page-qa (shippability gate so it doesn't suck) also works with OpenClaw🦞, hermes (Nous Research) or any agent framework. giving it away free. comment PAGES + like + follow (must follow so i can DM)

Matthew Berman

135,839 views • 5 months ago

THIS GUY TURNED 5 PROMPTING TIPS INTO A FREE AI CEO CHALLENGE The useful part is treating every prompt like you are briefing a very fast employee who has zero context. Most people open ChatGPT and type a wish. Pros give it a job. Try this instead: 1. Give it a role Not “help me with marketing.” Say: “Act as a B2B SaaS growth operator reviewing a landing page.” 2. Give it the real context Who is the customer? What are they buying? What have you already tried? What does success look like? 3. Give it constraints Length, tone, format, audience, banned words, examples to copy, examples to avoid. A vague prompt gets a vague answer. A constrained prompt gets something you can edit. 4. Ask for options before answers “Give me 5 angles, rank them, then explain the tradeoff.” This turns AI from an autocomplete box into a thinking partner. 5. Force it to show assumptions Before it writes, ask: “What are you assuming, what info is missing, and what would change your answer?” That one line saves a lot of fake confidence. Dan Martell’s video works because the promise is simple: 5 prompting habits that make AI feel less random. The reusable move is even simpler: Stop prompting for outputs. Start prompting for decisions. Bad: “Write me a post.” Better: “Here is the source, here is the reader, here is the angle, give me 3 hooks, choose the strongest, then draft in this style.” That is the difference between getting content-shaped noise and getting work you can actually ship. Caveat: prompts do not fix weak taste, bad data, or unclear strategy. But they do expose those problems faster. If your AI answers are generic, your prompt probably has no job, no context, no constraints, and no standard for what “good” means.

THIS GUY TURNED 5 PROMPTING TIPS INTO A FREE AI CEO CHALLENGE The useful part is treating every prompt like you are briefing a very fast employee who has zero context. Most people open ChatGPT and type a wish. Pros give it a job. Try this instead: 1. Give it a role Not “help me with marketing.” Say: “Act as a B2B SaaS growth operator reviewing a landing page.” 2. Give it the real context Who is the customer? What are they buying? What have you already tried? What does success look like? 3. Give it constraints Length, tone, format, audience, banned words, examples to copy, examples to avoid. A vague prompt gets a vague answer. A constrained prompt gets something you can edit. 4. Ask for options before answers “Give me 5 angles, rank them, then explain the tradeoff.” This turns AI from an autocomplete box into a thinking partner. 5. Force it to show assumptions Before it writes, ask: “What are you assuming, what info is missing, and what would change your answer?” That one line saves a lot of fake confidence. Dan Martell’s video works because the promise is simple: 5 prompting habits that make AI feel less random. The reusable move is even simpler: Stop prompting for outputs. Start prompting for decisions. Bad: “Write me a post.” Better: “Here is the source, here is the reader, here is the angle, give me 3 hooks, choose the strongest, then draft in this style.” That is the difference between getting content-shaped noise and getting work you can actually ship. Caveat: prompts do not fix weak taste, bad data, or unclear strategy. But they do expose those problems faster. If your AI answers are generic, your prompt probably has no job, no context, no constraints, and no standard for what “good” means.

kocer

25,573 views • 2 months ago

ONE PROMPT AND ONE BUTTON NOW BUILDS A FULL SYSTEM, DATABASE, BACKEND, AND FRONTEND INCLUDED Most people still picture AI as something you ask questions to, then copy the answer into your own code by hand. A builder wired Claude into Obsidian through MCP instead, so a single written prompt becomes the actual spec for the system. Claude breaks that prompt into database schema, UI components, and API endpoints on its own, then writes, runs, and fixes the code until it actually works. MCP is what makes this possible, it lets the agent see the filesystem, installed packages, and running services before it starts building anything. The output isn't a code snippet sitting in a chat window, it's a live local app running on its own server, ready to open in a browser. What used to need a backend developer, a DevOps engineer, and two weeks now finishes in under fifteen minutes. See the full architecture and prompt structure below👇

ONE PROMPT AND ONE BUTTON NOW BUILDS A FULL SYSTEM, DATABASE, BACKEND, AND FRONTEND INCLUDED Most people still picture AI as something you ask questions to, then copy the answer into your own code by hand. A builder wired Claude into Obsidian through MCP instead, so a single written prompt becomes the actual spec for the system. Claude breaks that prompt into database schema, UI components, and API endpoints on its own, then writes, runs, and fixes the code until it actually works. MCP is what makes this possible, it lets the agent see the filesystem, installed packages, and running services before it starts building anything. The output isn't a code snippet sitting in a chat window, it's a live local app running on its own server, ready to open in a browser. What used to need a backend developer, a DevOps engineer, and two weeks now finishes in under fifteen minutes. See the full architecture and prompt structure below👇

wast3

20,348 views • 2 months ago

Claude Code + computer use is f*cking cracked 🤯 Build a landing page → Claude opens Chrome, looks at it, spots every issue, and fixes it — without you describing a single thing. All inside Claude Code. Perfect for DTC brands and agencies who are still vibe-coding landing pages and advertorials in Claude Code, then manually opening them in Chrome, spotting 15 things wrong, and describing every visual issue back to Claude one at a time. If you're building pages in Claude Code and your workflow looks like this — build the page, open it in Chrome, spot broken spacing, go back to Claude, type "the CTA button is too low and the hero image is cut off," wait for the fix, open Chrome again, find 3 new issues, describe those too ... Claude Code + computer use eliminates the entire loop: → Claude writes the full landing page or advertorial → Opens Chrome and navigates to it → Spots layout issues, broken spacing, off-brand colors, missing elements → Fixes everything and re-checks until the page looks right → Tests your Shopify product pages by clicking through like a real customer → Walks through your checkout flow and flags friction before customers hit it → You only see the finished, visually verified result No describing what you see on screen. No "the CTA button needs more contrast" back-and-forth. No being the eyeballs for an AI that can't see. What you get: → Landing pages and advertorials Claude builds AND visually QAs before you ever look at them → Product pages Claude clicks through — testing layout, images, and CTAs like a real user → HTML dashboards Claude opens and verifies the charts actually render → Checkout flows Claude walks through step by step to catch friction → All of it happening in one session — build, test, fix, done One prompt. Claude builds it, checks it, and fixes it. You just review the finished page. I put together a full playbook with the exact setup, the prompts, and 5 DTC workflows that use Claude Code + computer use. Want it for free? > Like this post > Comment "CLAUDE" And I'll send it over (must be following so I can DM)

Mike Futia

19,143 views • 5 months ago

this Adaptive agent takes any affiliate offer, finds the highest converting pages in that niche, and builds you a landing page that is guaranteed to get maximum conversions here’s how affiliates are going from $0 to $3,000-$8,000 months with this system: -> paste the offer URL you’re promoting and it maps every top converting competitor in that niche -> analyses what every high performing page does (hooks, structure, trust signals, CTA placement) -> identifies the exact patterns that make people click and convert in your specific niche -> scores what’s working and what’s killing conversions on pages like yours -> feed it into Glitchy and it generates a complete landing page brief in minutes -> now every clip you post sends traffic to a page built to convert from day one most affiliates are sending traffic to weak pages that have really low conversion rates. this fixes that before you post a single video. reply “AGENT” + RT and i’ll send you the full agent so that you can make a page that actually converts (must be following so i can DM)

this Adaptive agent takes any affiliate offer, finds the highest converting pages in that niche, and builds you a landing page that is guaranteed to get maximum conversions here’s how affiliates are going from $0 to $3,000-$8,000 months with this system: -> paste the offer URL you’re promoting and it maps every top converting competitor in that niche -> analyses what every high performing page does (hooks, structure, trust signals, CTA placement) -> identifies the exact patterns that make people click and convert in your specific niche -> scores what’s working and what’s killing conversions on pages like yours -> feed it into Glitchy and it generates a complete landing page brief in minutes -> now every clip you post sends traffic to a page built to convert from day one most affiliates are sending traffic to weak pages that have really low conversion rates. this fixes that before you post a single video. reply “AGENT” + RT and i’ll send you the full agent so that you can make a page that actually converts (must be following so i can DM)

Sulfur

21,520 views • 4 months ago

I just cracked the code on AI animation ads 🤯 every one of these cost me 12 cents and under 20 seconds to make Gemini Omni + Claude Code is f*cking wild. i built a system that turns any product into an end-to-end AI animated ad in ANY style you want.. claymation, pixar-style 3D, anime, paper cutout, lego, you name it you drop in your product photo and a one line pitch and it handles everything end to end. images, video, voiceover, music, captions, all generated with AI inside Claude.. AI animation ads are crushing on Meta right now and everyone still assumes you need an expensive editor with a 3-week turnaround time to make one. you don't. you just need the right workflow. Im making full end to end high quality AI animation ads in under 3 minutes with this system and they work just as hard organically on TikTok, reels and shorts so i packaged the whole thing up… here's what you're getting: > every prompt i used across all 8 steps > the exact tool stack + the order to run it in > style recipes for claymation, pixar, anime, wes anderson, retro cartoon + CGI > one system that works for paid Meta AND organic built across Claude Code and Gemini Omni RT + reply 'STYLES' and i'll send it over (must be following so i can dm)

I just cracked the code on AI animation ads 🤯 every one of these cost me 12 cents and under 20 seconds to make Gemini Omni + Claude Code is f*cking wild. i built a system that turns any product into an end-to-end AI animated ad in ANY style you want.. claymation, pixar-style 3D, anime, paper cutout, lego, you name it you drop in your product photo and a one line pitch and it handles everything end to end. images, video, voiceover, music, captions, all generated with AI inside Claude.. AI animation ads are crushing on Meta right now and everyone still assumes you need an expensive editor with a 3-week turnaround time to make one. you don't. you just need the right workflow. Im making full end to end high quality AI animation ads in under 3 minutes with this system and they work just as hard organically on TikTok, reels and shorts so i packaged the whole thing up… here's what you're getting: > every prompt i used across all 8 steps > the exact tool stack + the order to run it in > style recipes for claymation, pixar, anime, wes anderson, retro cartoon + CGI > one system that works for paid Meta AND organic built across Claude Code and Gemini Omni RT + reply 'STYLES' and i'll send it over (must be following so i can dm)

Miko

114,621 views • 2 months ago

Claude Design is f*cking ridiculous 🤯 Claude Design now lets DTC brands and agencies rebuild any high-performing email — logo, hero, headline, CTA button, comparison table, brand colors — in 20 minutes. One reference email + a pre-loaded brand design system + a structured prompt = a finished, on-brand email you can preview as HTML. All inside Claude Design. Perfect for DTC brands and agencies who are still paying email agencies $3-5K/month to design flows that take 2 weeks to ship. If you're sitting on a welcome series, abandoned cart, and post-purchase flow that hasn't been touched in 6 months because the design lift is too painful... This workflow eliminates the entire bottleneck: → Build a design system in Claude Design once (brand colors, fonts, logo, button styling) → Upload a screenshot of any email you want to rebuild as your reference → Use Claude to write a structured prompt that maps every section top-to-bottom (promo bar, logo, headline, CTA, hero, body, table, footer) → Drop the reference image + the prompt into Claude Design at high fidelity → Iterate inline — swap the hero image, fix button styling, color-pick brand colors directly from the original No briefing a designer. No waiting 2 weeks for V1. No paying an agency $4K/month for 4 emails. What you get: → Win-back, welcome, abandoned cart, and post-purchase emails designed in under an hour each → A reusable brand design system that every new email pulls from automatically → Full inline editing — fonts, colors, buttons, images all editable in the canvas → HTML preview ready to hand off to your ESP Built 100% in with Claude Design. I put together a full playbook showing the design system setup, the exact structured prompt format, and the inline editing workflow. Want it for free? > Like this post > Comment "DESIGN" And I'll send it over (must be following so I can DM)

Mike Futia

31,959 views • 4 months ago

how to use Google's NEW open source Design.md + AI Skills to make your startup look like a $100 million company in 1 hour: 1. Design.md is an open source file from Google that captures the soul of a design. Typography, colors, spacing, all in one markdown file. You attach it to your prompt and your agent builds beautiful things every time. 2. Think of it this way. The HTML is the finished dish. The design.md is the recipe. The skills are the ingredients. Put them together and everything you build looks consistent and professional. 3. Don't create a design system from scratch. Find a brand you love. Linear, Stripe, Vercel, whatever resonates. Study it. Use ChatGPT or Claude to help you extract the design language into your own design.md file. 4. Build skills on top of your design.md. A landing page skill. A mobile app skill. A motion design skill. A slide deck skill. Each one references the same design.md so everything looks like it came from the same designer. 5. The biggest mistake people make: they nail one screen and then everything else looks generic. Design.md solves this. One file keeps every page, every format, every medium consistent. 6. Use it across everything. Your landing page. Your app. Your pitch deck. Your promo videos. Same DNA. Same taste. Same system. That's what separates a startup that looks real from one that looks vibe-coded. 7. Build a second brain for design inspiration. When you see something beautiful in the real world or online, capture it. Save it. When you're building something new, reference it. Taste is developed, not downloaded. 8. It's obvious but the difference between a product people trust and a product people bounce from is how it looks and feels. Design.md gives you that edge. you can watch below shoutout to Meng To for coming on The Startup Ideas Podcast (SIP) 🧃 and walking through his full workflow. if you want to use AI to actually build gorgeous designs, you'll want to use see this. watch

GREG ISENBERG

511,448 views • 4 months ago

DOWNLOAD MASTERCARD DESIGN MD AND BUILD CLEAR WITH CLAUDE CODE people onboard Claude with text designers actually getting results onboard it with a file most never think to write step everyone skips: A design md - plain text rulebook for colors, fonts, spacing, component patterns, tone You don’t write it from scratch - pull a public one from an open design system repo, or literally download a real brand’s guidelines and tell Claude “design like this” Upload it once to a Claude Design system, pick the strongest model, set effort to Max, wait 10-20 minutes for real mockups to review Every project after that pulls your actual brand automatically - zero re explaining your look every single prompt mistake that burns the most hours: designing and coding in the same conversation Claude Design is for visual exploration Claude Code is for production “Mixing them is where beginners lose entire afternoons re litigating decisions that were already made” real workflow, start to finish: design system once - structured brief - first draft - refine with chat, inline comments, sliders - export handoff bundle - Claude Code converts it to a real Next.js app - push, deploy, done 10 dashboards in 10 minutes isn’t the headline Never re explaining your brand again is full below

YARD

31,614 views • 14 days ago

You can now spy on your competitor's entire funnel inside Claude Code 🤯 I built a plugin that finds a competitor's proven landing pages, tears down why each one converts, and walks the funnel all the way to checkout. In the demo below I run it on Jones Road Beauty and Grüns, both funnels mapped end to end. All inside Claude Code. Perfect for DTC brands and agencies who keep swiping competitor ads but never see what's actually converting after the click. If you've studied a competitor's ads for weeks but have no idea which landing page they actually point to... A brand can run 50 ads while only two of them lead to the page carrying the whole account — and the ad library won't tell you which. You copy the creative, miss the offer on the page, and never see the cart stack that's quietly funding their ad spend. This plugin pulls the whole funnel apart for you: → Pulls every active ad from the Meta Ad Library and clusters them by landing page → Ranks pages by ad volume and run duration, so the proven winners surface first — not the tests → Tears down each winning page: hook, offer, social proof, price framing, urgency → Reads the cart for gift-with-purchase, bundles, and free-shipping thresholds → Walks checkout to map order bumps and payment offers (stops before "Pay now") No swiping ads one at a time. No guessing which page converts. No missing the upsells that fund their ad spend. What you get: → A ranked leaderboard of any competitor's proven landing pages → A full teardown of why each one converts → Their entire pre-purchase upsell funnel, mapped → A SaaS-style report with everything saved locally Built 100% in Claude Code. I put together a full playbook showing the exact process to build this yourself — the stages, the scripts, and all the prompts. Want it for free? > Like this post > Comment "SPY" And I'll send it over (must be following so I can DM)

Mike Futia

17,449 views • 3 months ago

Steal this mega prompt to generate high quality landing pages using LLMs and go viral every single day. --- You are an expert landing page designer and frontend developer specializing in high-converting, beautiful web experiences. CONTEXT: I need a landing page for [product/service name]. TARGET AUDIENCE: [describe your ideal customer] PRIMARY GOAL: [e.g., email signups, demo bookings, purchases] BRAND VOICE: [e.g., professional, playful, technical, aspirational] DESIGN SYSTEM REQUIREMENTS: - Primary Color: [hex code] - Secondary Color: [hex code] - Font: [font family] - Design Style: [modern, minimal, bold, etc.] STRUCTURE: Create a single-page landing page with these sections: 1. Hero Section - Attention-grabbing headline (focus on outcome, not feature) - Subheadline clarifying value proposition - Primary CTA button - Hero visual placeholder or description 2. Problem Section - Articulate the pain point clearly - Use relatable language - Build urgency subtly 3. Solution Section - How your product solves the problem - 3-4 key benefits (outcome-focused, not feature-focused) - Visual aids or icons 4. Social Proof - Testimonials (if available) or trust indicators - Logos of companies/clients (if applicable) - Metrics or results 5. How It Works - 3-step process - Simple, clear language - Visual flow 6. Final CTA Section - Reinforce primary action - Remove friction (e.g., "No credit card required") - Create urgency if appropriate TECHNICAL REQUIREMENTS: - Use semantic HTML5 - Tailwind CSS for styling (use only core utility classes) - Mobile-first responsive design - Smooth scroll behavior - Accessible (WCAG AA compliant) - Fast loading (optimize for performance) - Include meta tags for SEO COPY GUIDELINES: - Keep headlines under 10 words - Use active voice - Focus on outcomes, not features - Avoid jargon unless audience expects it - Every section should answer "What's in it for me?" OUTPUT: Provide complete HTML file with inline Tailwind CSS. Include comments explaining key sections. Ensure all placeholder content is realistic and contextual. CONSTRAINTS: - No external dependencies except Tailwind CDN - No JavaScript frameworks - Keep total file size under 100KB - Use system fonts or Google Fonts CDN Build this landing page now.

Harshil Tomar

23,305 views • 7 months ago

Anthropic released Claude Design TODAY and it's now accessible at I spent the last hour giving it a first look, and shared my thoughts and results in the video below. This is a BIG drop. This is a new design surface from Anthropic, and it changes what "AI design" means. Short version: Claude can now design. Not "describe a design." Not "generate an image of a design." Actual production work — prototypes, wireframes, high-fidelity mocks, slide decks, landing pages — editable, on-brand, and ready to hand off. Here's what stood out on first look: → Real design surfaces Prototypes, wireframes, hi-fi, and slide decks — each with templates and proper structure, not just pretty screenshots. → Comment-based edits Leave a comment on any element and Claude revises it. This is the Figma-style review loop, with the designer replaced by a model that works at 3am. → Brand design systems You can feed it your system — colors, type, components — and it actually respects it. On-brand output, not generic AI slop. → Export anywhere PDF, PowerPoint, Canva, standalone HTML. Plus a built-in handoff straight to Claude Code for engineers to implement. → Import from real tools Figma, GitHub, and captured web elements come in as inputs. Your existing work is the starting line, not the discard pile. → Collaboration Share links for view / comment / edit — the exact tier system teams already expect. What I tested on Opus 4.7: • A 5-slide deck generated from a single screenshot. Claude asked clarifying questions BEFORE generating and shipped speaker notes by default. • A landing page build. Solid first pass, real components, real layout logic. • Multiple chats running concurrently. You can parallelize design work across threads like a small team. Why this matters: PMs, founders, marketers, and non-engineers can now create designs that engineers can actually ship with production-ready output and a claude code handoff built in. The gap between "I have an idea" and "here's a working prototype with my brand applied" just collapsed to minutes. Full walkthrough, live demos, exports, and honest takes on where it breaks below. P.S. • This is an Anthropic Labs product — NOT GA yet. • Claude Design is currently webapp only (no API), and does not yet support the Analytics API, Compliance API, or cost/usage reporting. • Availability: – Default ON for Pro / Max / Team – Default OFF for Enterprise Enterprise admins can toggle it on via RBAC in console (comes with a ~$20/user initial credit).

JJ Englert

32,445 views • 4 months ago

Here's my workflow for reverse-engineering any creator's style using AI: I feed a 65-second video to an AI agent with one prompt "Break down the style, transcribe the script, and give me a replication plan." It came back with a full creative playbook: Step 1: Define your concept hook — One sentence, explainable in under 10 seconds — Must have a visual payoff you can show immediately Step 2: Film your talking head — Dark room, RGB lighting, shoot vertical — Hold your project in your hands during every shot Step 3: Capture 3 types of B-roll — Macro shots of hardware and components — Screen recordings of your creative process — Product reveal in natural light near a window Step 4: Build your VFX explainers — Simple line art with glow effects on pure black — After Effects for control, CapCut for speed Step 5: Design a typography system — Main title card, section headers, word-by-word captions — Define all three before you start editing Step 6: Edit to a 5-act structure — Hook → Conflict → Build → Resolution → CTA It nailed the typography, lighting, music tempo, even the emotional arc. One video in. Full style guide out. Do this for 10 creators you admire. Mix what you like from each. That's how you build your own style.

Here's my workflow for reverse-engineering any creator's style using AI: I feed a 65-second video to an AI agent with one prompt "Break down the style, transcribe the script, and give me a replication plan." It came back with a full creative playbook: Step 1: Define your concept hook — One sentence, explainable in under 10 seconds — Must have a visual payoff you can show immediately Step 2: Film your talking head — Dark room, RGB lighting, shoot vertical — Hold your project in your hands during every shot Step 3: Capture 3 types of B-roll — Macro shots of hardware and components — Screen recordings of your creative process — Product reveal in natural light near a window Step 4: Build your VFX explainers — Simple line art with glow effects on pure black — After Effects for control, CapCut for speed Step 5: Design a typography system — Main title card, section headers, word-by-word captions — Define all three before you start editing Step 6: Edit to a 5-act structure — Hook → Conflict → Build → Resolution → CTA It nailed the typography, lighting, music tempo, even the emotional arc. One video in. Full style guide out. Do this for 10 creators you admire. Mix what you like from each. That's how you build your own style.

The Startup Ideas Podcast (SIP) 🧃

26,560 views • 6 months ago

I just built a Claude Code plugin that spies on your competitors' entire funnel 🤯 Every "ad spy" tool stops at the ad. This one goes past the click → it finds their proven landing pages, tears down why each one converts, and walks the funnel all the way to the edge of checkout. All inside Claude Code. Perfect for DTC brands and agencies who keep screenshotting competitor ads but never see what actually happens after the click. If you're swiping competitor ads for "research," saving them to a board, and still guessing which landing page is doing the heavy lifting... guessing which offer is actually on the page... guessing what they're stacking in the cart to lift AOV... this plugin pulls the whole funnel apart for you: → Pulls every active ad from the Meta Ad Library and clusters them by landing page → Ranks pages by ad volume × run duration, so you see the proven winners, not the tests → Tears down each winning page: hook, offer, social proof, price framing, urgency → Builds a cart and reads the gift-with-purchase, bundles, and free-shipping thresholds → Walks checkout to capture order bumps and payment-plan offers (stops before "Pay now") No more screenshotting ads one at a time. No more guessing which page converts. No more missing the upsells that fund their ad spend. What you get: → A ranked leaderboard of any competitor's proven landing pages → A full teardown of why each one converts → Their entire pre-purchase upsell funnel, mapped → A SaaS-style report with everything saved locally Built 100% in Claude Code. I put together a full playbook showing the exact process to build this yourself — the stages, the scripts, and all of the prompts. Want it for free? > Like this post > Comment "SPY" And I'll send it over (must be following so I can DM)

I just built a Claude Code plugin that spies on your competitors' entire funnel 🤯 Every "ad spy" tool stops at the ad. This one goes past the click → it finds their proven landing pages, tears down why each one converts, and walks the funnel all the way to the edge of checkout. All inside Claude Code. Perfect for DTC brands and agencies who keep screenshotting competitor ads but never see what actually happens after the click. If you're swiping competitor ads for "research," saving them to a board, and still guessing which landing page is doing the heavy lifting... guessing which offer is actually on the page... guessing what they're stacking in the cart to lift AOV... this plugin pulls the whole funnel apart for you: → Pulls every active ad from the Meta Ad Library and clusters them by landing page → Ranks pages by ad volume × run duration, so you see the proven winners, not the tests → Tears down each winning page: hook, offer, social proof, price framing, urgency → Builds a cart and reads the gift-with-purchase, bundles, and free-shipping thresholds → Walks checkout to capture order bumps and payment-plan offers (stops before "Pay now") No more screenshotting ads one at a time. No more guessing which page converts. No more missing the upsells that fund their ad spend. What you get: → A ranked leaderboard of any competitor's proven landing pages → A full teardown of why each one converts → Their entire pre-purchase upsell funnel, mapped → A SaaS-style report with everything saved locally Built 100% in Claude Code. I put together a full playbook showing the exact process to build this yourself — the stages, the scripts, and all of the prompts. Want it for free? > Like this post > Comment "SPY" And I'll send it over (must be following so I can DM)

Mike Futia

36,075 views • 3 months ago

One of my favorite ways to use Claude Code is to create a ticket Here is why I love it: Claude Code is very good at doing the work, but it must know when it's "done." A ticket gives Claude Code a clear signpost for when to stop Here's how to write it in 4 parts: 1) Give it a job: - "Add a wait list form to the landing page." 2) Give it a proper scope: - Ask for a name, an email, and a company. 3) Tell it the UX you want: - Show a simple success message after a person sends the form. 4) Tell the constraints it needs to follow: - Keep the design the same as the current brand identity. Then add an instruction: make the change small enough to review in the diff view, run the checks, open the app in the desktop preview, and tell me what still needs human review. The catch: a ticket that is not clear makes Claude guess. "Make the app better." "Add AI." "Build the whole thing." You get a diff too big to read, so you cannot tell if it is right. Keep the ticket small enough so that Claude knows exactly what to do

The Startup Ideas Podcast (SIP) 🧃

10,471 views • 26 days ago

Huge UI design boost by adding this to my AI workflow 1. Explore variations with Variant. The secret is to use "shuffle layout" and "see other views". This keeps the essence of a design that I like, but gives interesting layout variations. I also change colors and explore narrow by specifying one or two things in prompt, like font name, UI style or light/dark mode. 2. Copy HTML and prompt with Gemini 3 in site builder. Fix minute details like fonts, icons, assets, intro/scroll animations, adaptive layout and make the whole thing functional. Include image references, button styles, code snippets and other components to keep things creative. Often, I see sites that have one cool thing, but the rest is super generic. That's because AI is especially good at being generic without continuously feeding specs. 3. Turn into a landing page by prompt adding new components/sections and connect/adapt new pages. This is the part where most people stop, but it's actually the easiest since AI is so good at reading existing code. "Adapt this {page code} for a {features, blog, pricing, login} page." Finally, set up SEO and custom domain name. Boom, you just shipped a pro-level site that doesn't look generic.

Huge UI design boost by adding this to my AI workflow 1. Explore variations with Variant. The secret is to use "shuffle layout" and "see other views". This keeps the essence of a design that I like, but gives interesting layout variations. I also change colors and explore narrow by specifying one or two things in prompt, like font name, UI style or light/dark mode. 2. Copy HTML and prompt with Gemini 3 in site builder. Fix minute details like fonts, icons, assets, intro/scroll animations, adaptive layout and make the whole thing functional. Include image references, button styles, code snippets and other components to keep things creative. Often, I see sites that have one cool thing, but the rest is super generic. That's because AI is especially good at being generic without continuously feeding specs. 3. Turn into a landing page by prompt adding new components/sections and connect/adapt new pages. This is the part where most people stop, but it's actually the easiest since AI is so good at reading existing code. "Adapt this {page code} for a {features, blog, pricing, login} page." Finally, set up SEO and custom domain name. Boom, you just shipped a pro-level site that doesn't look generic.

Meng To

65,762 views • 7 months ago

Anthropic just changed how they think about Claude 5. Not with a new model. Not with a benchmark. With a completely different philosophy for building AI systems. Most people will miss it. They're still trying to write better prompts. Anthropic is optimizing something else entirely: Context. Here's what every AI builder should learn from it: 1. Stop telling AI exactly what to do. Start telling it what success looks like. Older models needed rigid instructions. Newer models perform better when you define the objective and let them make the decisions. The goal is no longer more control. It's more clarity. 2. Context is a budget, not a storage unit. Every extra sentence competes for the model's attention. A massive context file doesn't make AI smarter. It often makes reasoning worse. The best systems don't load everything. They load only what's relevant. 3. Great tools beat great prompts. Most people spend hours tweaking prompt wording. Anthropic is investing in better interfaces instead. Clear parameters. Structured inputs. Well-designed tools. If the interface removes ambiguity, the model makes better decisions before it even starts reasoning. 4. Show reality instead of describing it. Want a specific coding style? Provide the codebase. Want a certain design language? Share the mockup. Want consistent outputs? Give it tests to satisfy. Concrete references consistently outperform long written instructions. 5. Deliver information when it's needed. Not everything belongs in the initial context. Documentation. Style guides. Verification. Reviews. Load them only when they're relevant. Think of context like RAM, not a hard drive. 6. The real advantage is system design. Prompt engineering isn't disappearing. It's becoming one small part of a much bigger stack. Memory. Retrieval. Context architecture. Tool design. Evaluation. Every improvement compounds. The biggest takeaway from Anthropic's update? The next generation of AI won't be won by the people writing the longest prompts. It'll be won by the people building the smartest systems. Same models. Completely different results.

Anthropic just changed how they think about Claude 5. Not with a new model. Not with a benchmark. With a completely different philosophy for building AI systems. Most people will miss it. They're still trying to write better prompts. Anthropic is optimizing something else entirely: Context. Here's what every AI builder should learn from it: 1. Stop telling AI exactly what to do. Start telling it what success looks like. Older models needed rigid instructions. Newer models perform better when you define the objective and let them make the decisions. The goal is no longer more control. It's more clarity. 2. Context is a budget, not a storage unit. Every extra sentence competes for the model's attention. A massive context file doesn't make AI smarter. It often makes reasoning worse. The best systems don't load everything. They load only what's relevant. 3. Great tools beat great prompts. Most people spend hours tweaking prompt wording. Anthropic is investing in better interfaces instead. Clear parameters. Structured inputs. Well-designed tools. If the interface removes ambiguity, the model makes better decisions before it even starts reasoning. 4. Show reality instead of describing it. Want a specific coding style? Provide the codebase. Want a certain design language? Share the mockup. Want consistent outputs? Give it tests to satisfy. Concrete references consistently outperform long written instructions. 5. Deliver information when it's needed. Not everything belongs in the initial context. Documentation. Style guides. Verification. Reviews. Load them only when they're relevant. Think of context like RAM, not a hard drive. 6. The real advantage is system design. Prompt engineering isn't disappearing. It's becoming one small part of a much bigger stack. Memory. Retrieval. Context architecture. Tool design. Evaluation. Every improvement compounds. The biggest takeaway from Anthropic's update? The next generation of AI won't be won by the people writing the longest prompts. It'll be won by the people building the smartest systems. Same models. Completely different results.

Evan Luthra

38,751 views • 1 month ago

The 5 biggest AI leaks are on GitHub. Free. This wasn't supposed to end up online. 1. instructkr/claw-code, 195k ⭐️ stars A clean rewrite of the leaked Claude Code CLI. Got 100k stars in one day. Nobody has ever done that on GitHub. 2. x1xhlol/system-prompts-and-models-of-ai-tools, 143k ⭐️ stars 28 coding tools, with the JSON tool schemas. Not just the prompt text, the actual list of what each agent can touch. 3. asgeirtj/system_prompts_leaks, 63k ⭐️ stars The real prompts behind Claude Opus 5, GPT-5.6, Gemini 3.5, Grok and Cursor. Claude's is 3,677 lines long. The Washington Post ran a story off this repo. 4. elder-plinius/CL4R1T4S, 47k ⭐️ stars Same thing, every big lab in one place. Updated when new models ship. 5. Piebald-AI/claude-code-system-prompts, 12.4k ⭐️ stars Claude Code's prompt pulled from compiled source. 27 tool descriptions, subagent prompts, security review logic. The best prompt engineering course ever made is 5 free repos written by people who never meant to publish them. Saved it. Most of it is publicly available, but few people know about it 👇

The 5 biggest AI leaks are on GitHub. Free. This wasn't supposed to end up online. 1. instructkr/claw-code, 195k ⭐️ stars A clean rewrite of the leaked Claude Code CLI. Got 100k stars in one day. Nobody has ever done that on GitHub. 2. x1xhlol/system-prompts-and-models-of-ai-tools, 143k ⭐️ stars 28 coding tools, with the JSON tool schemas. Not just the prompt text, the actual list of what each agent can touch. 3. asgeirtj/system_prompts_leaks, 63k ⭐️ stars The real prompts behind Claude Opus 5, GPT-5.6, Gemini 3.5, Grok and Cursor. Claude's is 3,677 lines long. The Washington Post ran a story off this repo. 4. elder-plinius/CL4R1T4S, 47k ⭐️ stars Same thing, every big lab in one place. Updated when new models ship. 5. Piebald-AI/claude-code-system-prompts, 12.4k ⭐️ stars Claude Code's prompt pulled from compiled source. 27 tool descriptions, subagent prompts, security review logic. The best prompt engineering course ever made is 5 free repos written by people who never meant to publish them. Saved it. Most of it is publicly available, but few people know about it 👇

unicode

12,437 views • 23 days ago