This is my submission for the Flowstep Challenge. I built a multi-page digital archive that treats painting styles as a practical design reference rather than just art history. The project is organized as a cohesive system with multiple screens and clear entry points through Gallery, Movements, Palettes, About, Artists, and Search. It is still a working draft that will continue to evolve, but even at this stage it already shows how artistic movements can be turned into a useful design tool. I used Flowstep not as a random prompt generator, but as part of a more complete design-engineering workflow. From the start, I worked with a defined structure across four input files — icp.md, sitemap.md, content-plan.md, and design.md (pinned as the design guidelines) — so the system, not a single mockup, was the starting point. To speed up the process, I also connected Claude via MCP. This is where I made a mistake: Flowstep gives clear recommendations on when to generate a single screen versus a full multi-screen flow (6 screens), and I didn't pass those recommendations to the agent. As a result, it generated 45 pages, with several duplicating each other because the multi-page guidelines weren't included from the start. It was a useful lesson: even with a defined structure, the agent still needs the platform's own generation rules spelled out explicitly, or the output drifts. The next challenge was the imagery. On some pages, placeholder images still needed to be replaced with real visuals, and it became clear that this was better handled in code rather than through another round of generation. I took the code from the already-built version, swapped the placeholders for the selected real images directly in the code, redeployed, cleaned up anything unnecessary, and brought the finished pages back into Flowstep for comparison. The result is a live archive site, not static mockups — a multi-page system with a complex structure, but all within one consistent style and one coherent language. It is not yet a 100% finished final solution, but it is a strong and fast starting point for further work. What mattered most to me in this process was testing not only the visual side, but the full product-thinking approach: structure, logic, error correction, and final assembly.

Flowstep file: https://app.flowstep.ai/file?activeFileId=974ab7cc-bbee-445d-a38c-a93c6eb4eb57

Final prototype: https://painting-movements-archive.pages.dev

Walkthrough video:

https://www.instagram.com/reel/DbeUuRctN_7/?igsh=MTh2NXQ0a2F0d2k5OA==

Social post: https://www.instagram.com/reel/DbeZPtgNbX4/?igsh=amo3emVmN3U4cGk2

fascinating 😍 Incredible work and best of luck in the challenge! 🚀

Being a designer feels like a superpower. Build a prototype? Nope. A fully working app? Yes! Here’s what I made:

Leela is a 2,000-year-old Indian board game with 72 squares, one question, and one die. You roll to enter, move through named inner states, and write a reflection at each square.

Existing versions are either flat, digitised boards or feature-heavy wellness suites. I wanted to make a quieter one.

How I built it:

→ Flowstep MCP wired into Claude Code, Created Flowstep screens directly on canvas and implemented changes from the canvas and using Figma, Design MD file inside of Flowstep is a gem, helps to create cohesive design fast

→ Three complete design iterations before the visual language felt right: a night-sky version, a minimal one, and finally the aura direction that shipped.

→ A playable build deployed on Vercel with the real rules: roll a six to enter, three sixes burn, land exactly on square 68 to complete the game, and landing on square 72 sends you back to 51, music on/off, record or type settings.

→ An optional AI guide running behind a serverless function, so the API key never reaches the browser. The game is fully playable without it.

🎉 Link: Flowstep

🎮 Play: https://leelagame.vercel.app

Linkedin Post: link

Built with Flowstep, Claude Code via MCP, and Vercel.

#FlowstepChallenge

can't wait to try out this game, a 2000 year old game with 72 squares seems like a real challenge, I don't know but my mind is telling me "SUDOKU STRATEGY" 😂. I love also how many screens you have and the consistency that you respected.