Rosyad Zain@Zain2
1
Events attended
1
Submissions made
Indonesia
2+ years of experience
About me
I design digital products and ship them — from brand and UX to the live, deployed web app. Most people stop at one end of that. My focus is owning the whole arc. I'm Rosyad, a design-led Creative Director and product designer. I help founders and brands turn an idea into a finished product: the brand system, the interface in Figma, and a fast, production-ready web app — built with a modern AI-augmented workflow that lets me ship complete products solo, not just hand off mockups. What I do → Brand identity, visual systems, and UX design (Figma) → Bilingual, conversion-focused web products on Next.js + Supabase + Vercel → End-to-end creative direction — vision through to live deployment → Motion, video, and 3D environment art (Unreal Engine 5) when a project needs a cinematic edge How I work I lead with design and ownership. I shape the full experience in Figma, then ship it through an AI-augmented build workflow — faster delivery, one clear vision, and real products in production. I'm continuously deepening my hands-on engineering to take more of the execution in-house.
🤓 Latest Submissions
Crucible — Break it before reality does
Crucible is an adversarial document-hardening desk for the documents you can't afford to get wrong — incident runbooks, security policies, compliance procedures, contracts. Most AI tools stop at "Find": they list problems and hand them back. Crucible closes the loop — Find → Fix → Prove. Three AI agents work against each other, coordinated through Band. A Red agent attacks the document like an adversary and surfaces concrete flaws. A Blue agent defends, rewriting the document to close each gap. An Arbiter then judges the new version and scores it from 0 to 100. The loop repeats for up to three rounds, and on high-stakes documents it escalates to a human for final sign-off regardless of score. Every action — each attack, fix, score, and approval — is appended to a tamper-evident SHA-256 hash chain, so the whole hardening history can be independently verified afterward. In our live run on a Kubernetes production-rollback runbook, the agents surfaced 14 findings (3 Critical, 5 High, 5 Medium, 1 Low) across three rounds, with the Arbiter scoring 75 → 75 → 85. The run used all three rounds and — with some findings still partially open and a human gate required for high-stakes work — escalated to a human on-call engineer, who reviewed and approved the final version. The result was sealed into a 67-entry hash chain, fully reproducible at /api/verify. Crucible runs all three agents on Featherless (Qwen2.5-7B-Instruct) and coordinates them on Band, with a Next.js front end on Vercel and Supabase for state and realtime. It's built for regulated, high-stakes workflows where "looks fine" isn't enough — you need proof that a document was stress-tested before it ever met reality.
19 Jun 2026
