I love the concept behind HCB and the amount of effort everyone at Contra Labs is putting into testing and comparing models through pure taste and creative direction.
So I decided to give it a shot myself and create these two clips using the exact same prompt, but with different models.
Curious to know which one works better as a hook according to you?
5
21
3.5K
Built an immersive fantasy portfolio where every section becomes part of a living world instead of another webpage.
Designed the entire experience in @flowstep_ai using Flowstep + MCP (Antigravity).
Connected Flowstep MCP with Antigravity, then iterated directly on the canvas using promptsβrefining layouts, components, navigation, interactions, and the design system without rebuilding screens from scratch.
Created reusable design tokens, cinematic UI, glass navigation, parchment components, handcrafted cards, and a consistent visual language across every scene.
Once the prototype was finalized, I replicated the entire Flowstep canvas into a Next.js application and polished interactions with modern animation libraries before deploying.
The workflow:
πΏ Idea β Prompt Flowstep
π¨ Refine with MCP (Antigravity)
𧩠Build reusable design system
πΌ Iterate every screen on the canvas
β Replicate to Next.js
β² Deploy on Vercel
π‘ 9 connected fantasy scenes
β¨ 1 immersive portfolio
Project link : https://portfolio-6asf.vercel.app/
flowstep link : https://app.flowstep.ai/file?activeFileId=dd5c563d-33a1-4b37-8b24-3669efac9652
1
199
"We pay for ChatGPT and nobody uses it": a 2-week AI adoption sprint.
The problem: a company buys ChatGPT Team or Gemini licences, runs one demo, and three months later only two people log in. Staff don't know what to use it for in their actual job.
The fix: short interviews to find the 5 tasks each role repeats every week, copy-ready prompts for exactly those tasks, and two hands-on sessions where people use them on real work.
Includes: a use-case library by role, a one-page "what not to paste into AI" guide, and a 30-day usage check-in. (Sample build to show the approach.)
0
7
The Forecast is a 40-second psychological thriller short film built entirely on Renoise. The story follows a South Asian data analyst working late in a dark room, intensely focused on completing a critical forecast. Shot by shot, we see him type, analyze, and finally lean back with a satisfied smile as the screen flashes "FORECAST COMPLETE" β he believes he's done something meaningful. Then comes the twist: the camera pulls back to reveal he was never in an office. He's been sitting inside a glowing glass simulation pod the entire time, surrounded by scientists in white lab coats quietly taking notes on tablets β observing him like a lab subject. The final black screen delivers the gut punch: "Every forecast you trust... was made by someone who never knew they were being watched." Built using Renoise Canvas with Seedance 2.0 and FacePass for consistent character identity across all scenes.
Tool used: Renoise AI β renoise.ai
(http://renoise.ai)#RenoiseChallenge
3
1
312
Sorted by Shae: booking for a solo home organizer
Shae runs a one-woman organizing business in Indiranagar, Bengaluru. Every enquiry used to start with "how much?", and the real answer depends on what the space looks like. That meant back-and-forth over WhatsApp, an evening spent quoting, and slots held for people who never confirmed.
What I built:
Photo-based estimate: The client picks a room, sets how full it is and how much they want to declutter, and uploads a photo. AI flags what will slow the job down and pins each item on the photo with its hour adjustment. The client sees an hours range and a βΉ range before they book.
Booking by blocks: The estimate maps to a half day, full day or multi-day block. Clients can only pick dates where that block fits Shae's calendar.
Owner approval: Shae reviews each request with the photo, the AI notes and suggested follow-up questions. She can approve it, adjust the quote or ask for more information.
25% deposit to confirm: The slot is held for 24 hours, with a reminder at 12 hours and an automatic release if the deposit isn't paid.
Itemised quote and invoice: Labour, products, cleaning supplies and add-ons are listed separately.
Statuses on both sides: Requested β Quote sent β Booked β In progress β Fulfilled. Clients and Shae can both cancel or reschedule under a 72-hour policy.
Private client links: Each client gets a tokenised link checked against the last 4 digits of their phone. The links are not indexed by search engines and they expire.
Owner dashboard behind login: /owner sits behind sign-in, and access is checked against an owner role in Supabase. Booking data is locked down with row-level security, so a client can only reach their own booking through their link.
The result: a client goes from "can I book?" to a confirmed, deposit-backed slot without waiting on a quote by message. Shae approves jobs instead of calculating them.
Built with: Lovable (TanStack Start), Supabase (auth, RLS, storage, cron automations) and the Lovable AI gateway for photo analysis.
1
130
AI-Powered Multi-Channel Content Creation Workflow
-Developed an end-to-end workflow using LLMs (GPT-4/Claude) and automation tools (Make/Zapier) to generate SEO-optimized blogs, social media posts, and video scripts from a single prompt.
-Reduced content production time by 80% while maintaining 100% brand consistency and high engagement scores.
0
130
This self-initiated AI commercial was created to explore emotional storytelling through a 3D Pixar-inspired visual style. The concept blends cinematic animation, character-driven storytelling, and premium product placement to create an advertisement that feels both heartwarming and memorable. By combining stylized 3D environments, expressive animation, and seamless AI-generated visuals, the project demonstrates how brands can move beyond traditional product ads and build deeper emotional connections with their audience through narrative-driven marketing.:
0
69
