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.

DREAM-O — The global registry of dreams.

I almost never remember my dreams. I wanted an app that would tell me what I dreamed last night — and the moment I imagined it working, I knew what the company behind it would actually be. So I built that company instead.

A pillow unit records every session. Twelve minutes after you wake, the company issues a record. It never explains how.

What you're allowed to see of your own dream depends on which plan you pay for. ORIGIN opens one scene a month. The rest stay in custody — described in full, never opened. Their time, their length, their size, their state. Everything except what happened. After fourteen days they're destroyed. Not for the company. For you. And the company doesn't say destroyed. It says released.

Every screen is written in that voice: procedural, patient, institutional. The product never winks. Nothing on any sheet tells you this is wrong — you work that out yourself, somewhere around the retention page.

One prompt in Flowstep produced six screens. From there it was iteration — prompt, look, correct, look again. Text overflowing, blocks colliding, things that looked fine until I zoomed in. Every screen sits on a percentage grid with four x-values and a single hairline spine at 68.4% height. No border radius, no shadows, no serifs, no accent colour anywhere in the system.

Then I connected Claude Code to Flowstep's MCP server, handed it my design guide, and asked it to audit all fourteen screens against it, one by one. A second prompt to fix what the audit found. It worked inside the Flowstep file over MCP. I went off to cook. I came back and it was ready — I just wired a few links by hand, three clicks each. Fourteen screens for twelve sheets — the record sheet exists three times, one per plan. A path you can walk end to end.

Prototype: https://app.flowstep.ai/file?activeFileId=0a82e6e8-edfa-4dfb-ace8-dfb2e8122859 Social: https://x.com/JosIgnacio17989/status/2083406318304481732 Built with Flowstep · Claude Code over MCP @flowstep_ai #FlowstepChallenge

Love this