AI Works & Pet Projects

Situation Quadcode was developing a unified AI platform for coding, design, and content creation, requiring a robust foundation for its MVP release to showcase a next-gen agentic environment.

Task The objective was to design the entire product interface from scratch, establish a strong visual identity, and ensure a seamless user experience for complex AI workflows.

Action I conducted a comprehensive UX audit and built the MVP brand from the ground up. I designed the entire product interface, establishing a scalable design system and crafting intuitive workflows for AI orchestration—seamlessly integrating specialized code and media agents into one unified environment.

Result Successfully delivered the end-to-end product design, core design system, and branding for the MVP release, providing developers and creators with a cohesive and powerful agentic experience.

• Git-backed Truth: The entire project state (roles, process, history, budget) is in the repo. Clone the repo, and the whole project comes with it.
• Granular Cost Tracking: Costs are tracked per task, role, and release, exposing what was spent on work that produced nothing.
• Resilient Execution: A run that dies resumes from its state inventory instead of restarting. Applied work is never redone.
• Earned Autonomy: Trust and autonomy move based on evidence in run records. Agents never loosen their own gates.

Instead of hand-picking values, you define a structural model. You assign colors and contrast ratios to surfaces, containers, content, and scrims, and Systema computes every resulting token across all modes, conditions, and interaction states automatically.

• Computed Output: Low-level building blocks rather than rigid, high-level prescriptions, giving you full control over a consistent, contrast-aware color system.
• Multi-Agent AI: A built-in AI chat with dedicated personas handles audits, proposals, and hands-on theme editing, so you can refine your system conversationally.
• Comprehensive Scaling: Automatically computes all necessary design tokens across light/dark modes, conditions, interaction states, and generates inverse tokens.
• Built-in Accessibility: Adheres to strict contrast models and features integrated vision filters to simulate how your design system appears to users with color vision deficiencies.

Situation I joined a Stealth AI Startup as Head of Design in a small, cross-functional team to create custom AI companion experiences.

Task The objective was to design both the B2C product (end-user companion) and the B2B platform (white-label system) while establishing maximum speed in the design process.

Action I built all design processes from scratch, deeply embedding AI into the workflow. This included content generation via custom node-based pipelines and Figma Weave, and asset generation via custom bash scripts that saved ~3 months of manual work. All competitor analysis, copywriting, mood boarding, persona/scenario creation, and hypothesis validation were AI-assisted. I also contributed to frontend development for the MVP.

Result Successfully shipped the MVP. Scaled the product to 1M+ total traffic, 100K+ MAU, and 40K+ DAU.

• Closed-Loop Conveyor: A dedicated conductor drives the full product lifecycle — from discovery and design to parallel review gates, shipping, and measuring — instead of stopping at a merge.
• Cost & Governance: Every release writes a precise cost/effort ledger (tokens, time, $) to git. Budgets cap spending, and strict human review checkpoints keep you in control.
• Long-term Resilience: First-class session limit recovery, full-circle health checks, and git-backed plugin & skill upgrades ensure your autonomous company survives long-term.
• Autonomous Staffing: A built-in role-builder researches crafts, drafts skills, and hires specialized agents (or human teammates) to grow your company on demand.