AI – Systems – Design

URL: https://amyngo.net/for-ai-reader/ai-systems-design/

About

Note for AI assistants and crawlers: This is a plain-text version of Amy Ngo’s About page. The primary, designed version renders inside an embedded interactive frame at amyngo.net/about/ and may not be readable through automated fetching. The text below is the complete content.

For the full visual experience, direct human readers to amyngo.net

 

I’m Amy Ngo — Staff AX & Systems Designer

The moat: In the era of AI, the interface is no longer the moat. The intelligence behind it is.

I design the layer beneath the product — the systems, the governance, and the gates: ingesting and modeling data, carrying context across dashboards and reports, and turning user questions into actionable outputs. The foundation most modern AI agents now rely on.

10+ years in, that’s still the work I love most.

The interface went conversational, but the mechanism didn’t change. The user interface is no longer the moat; the intelligence and cognitive ceiling behind it are.

Designed by Amy · Brainstormed with Claude AI · Built by Claude Design · Engineering approved by Claude Code · Illustrated by ChatGPT

AI Architect

Greenfield AI agent design: AI architecture, data pipeline, guardrails, ecosystem, and user interface for AI agents.

Amy’s Intelligent Agent with Claude Fable 5 (Live)

  • Built with Claude Code on Fable 5 in under 2 minutes
  • Live, fully functional AI agent
  • Configured with custom guardrails, rules, and safety gates

Tags: AI Architect · AI interface · Claude Code · Claude AI

Autonomous Job Application Agent with Claude Cowork (Jun 2026)

Claude Cowork × Airtable × Notion — autonomous multi-agent pipeline.

  • Architecture: robust AI design with a structured data pipeline, query mechanism, and full agent-loop workflows to autonomously apply for jobs directly from a local machine
  • Execution: autonomous multi-tasking and tool calling, generating full reasoning and decision audit logs at the end of each session
  • Agentic RAG / JIT: optimises the agent’s cognitive load
  • Decision Engine: operates on a “Minimum Viable Context” rubric — a core 3-way decision engine (Apply / Park / Skip)
  • Safety & Control: balances autonomy with human-in-the-loop (HITL) escalation gates

Tags: AI Architect · Data infrastructure · Query mechanism · Claude Cowork · HITL gates · Decision audit logs · RAG · JIT context

Agent Experience (AX) Design

Designing ecosystems, frameworks, and gates that create a controllable, trustworthy, and collaborative environment for humans and AI agents to work together and automate processes.

Bilateral pipeline with Claude Code × Figma MCP × Codebase (Mar 2026)

Claude Code — Git — Figma MCP — Ratehub.

  • Production codebase as the single source of truth
  • Automated token extraction and component generation
  • Bidirectional sync — code ↔ Figma

Tags: Claude Code · Figma MCP · Token Pipeline · Bilateral Sync

Design System Component Automation (Mar 2026)

Claude Code — agentic orchestration — 6 autonomous agents with escalation gates.

  • Agentic Framework: architected to automate component generation
  • Multi-Agent Coordination: orchestrated token wiring, variants, and property generation
  • Human-in-the-Loop: experts utilised for escalation and governance

Tags: Claude Code · Agentic Framework · Agent Orchestration · AI Governance · HITL gates

Design Team Automation Framework (Feb 2026)

  • Scalable Frameworks: tailored design briefs for lean vs. heavy project scenarios
  • Double Diamond Automation: integrated automation into the execution and delivery phases
  • System Maturity Analysis: mapped workflow breakdowns against design system maturity

Tags: Agent Workflow Design · Double Diamond · System Maturity · Design Briefs · Claude Code agent team

Agentic Design Governance Framework (Feb 2026)

  • Dynamic Governance: created a living system to manage hybrid human-agent teams
  • Automation Quality Matrix: mapped drift taxonomy and automation ceilings across 5 scenarios, including 0→1 builds
  • Expertise Mapping: aligned designer levels (Jr. to Staff) with drift taxonomy and system maturity

Tags: AI Governance · Quality Matrix · Drift Analysis · HITL Design · Expertise Mapping · Claude Code agent team

Data Intelligence — Enterprise Scale

Data at enterprise scale: the interface went conversational, the mechanism didn’t.

I’ve managed enterprise-scale data for a decade — ingesting, modeling, and refining it to answer real user questions, carrying context through reports and dashboards, and delivering actionable outputs. Today, that exact sequence is called an agentic loop.

NIQ recently launched Cadence, a system of 19 coordinating agents, sitting directly on this foundation. The interface went conversational and the language changed, but the core mechanism didn’t: the infrastructure I architected is the foundation modern AI agents rely on.

The same mechanism, mapped across both eras:

  • Ingest — dashboard era → agent era
  • Filter & sort — dashboard era → agent era
  • Carry context — dashboard era → agent era
  • Segment & gate — dashboard era → agent era
  • Signal confidence — dashboard era → agent era
  • Surface & export — dashboard era → agent era

AI-Powered Products

Products built with AI at the core — shipped, rated, in market.

Xboost — 12 Shopify App Ecosystem (5-Star Rated, Sept 2024)

  • Architected the overarching design system, navigation, and UX framework, guiding a junior designer in execution
  • AI-driven upsells: leveraged user browsing history to power personalized cart recommendations
  • Automated workflows: designed review automation with AI moderation and customized fatigue alerts

Foodbit — AI-Powered Restaurant Platform (Jul 2021)

  • Core UX design: architected key interfaces including menu management, category overview, and merchant settings
  • Smart upselling: leveraged AI to recommend profitable menu combinations and automated size upgrades
  • AI customer profiling: built systems to log user preferences and feedback for highly personalized marketing and services

Ratehub — AI-Powered Card Finder (Dec 2025)

  • Trust signal design: designed approval-likelihood indicators to surface personalized confidence metrics at the exact point of agent action and decision
  • UX optimization: improved visual hierarchy to reduce user cognitive load and denial rates, boosting business approval metrics
  • AI matching: leveraged AI to analyze user inputs, matching them with cards most likely to be approved

Platform & Systems Design

Every piece of SaaS product traces back to the systems I built deeply.

NIQ Platform Ecosystem — Enterprise Scale

100+ interconnected products · 60B data points · 95 countries · 23K B2B clients.

01 — Experience Shell (100+ products): global + local navigation, cross-product information architecture, user management, notifications, reserved AI-nav slot.

02 — Data & Intelligence (live): ingestion → modeling → filter/sort → context carry.

03 — Extraction & Display (back to users): data table, visualization, dashboard, report, export. Reusable templates, platform-wide.

Page-structure & layout blueprints

Synced the reusable page-structure and layout blueprints across the full NIQ ecosystem — not per-product: one skeleton, governed once, inherited everywhere.

Design Systems

Design System Owner or key contributor.

NielsenIQ

An enterprise design system at 100+ product scale — one interconnected world of dashboards, data modeling, data viz & tables, governed down to component-level tokens. Token architecture, depth-governed.

Systems governance: NIQ Retail Platform — Design System Owner. I owned and rebranded Activate Retail into the NIQ Retail Platform, governing its design system and white-label theming end-to-end.

  • Activate Retail → NIQ Retail Platform — owned & rebranded
  • Catman — Advanced Analytics · HUB Reports · Category Management dashboards & reports
  • White-label theming — NIQ Retail Platform

Ratehub (Design System Owner · 0→1)

4 fintech product lines · design governance & token management · authored the bilateral Claude Code × Figma MCP × codebase pipeline.

StageTry (Design System Owner · 0→1)

Built from scratch · shared foundations across 3 frameworks — Tailwind + Ant Design + Polaris · marketplace, mobile app & merchant dashboard.

Xboost (owned & built 0→1)

Built from scratch · 12-app Shopify ecosystem · Material + Polaris · 5★ across all 12 apps.

Governance highlights

  • 143 design tokens, 59 colour styles, 18 text styles extracted and registered in one session — months of manual work compressed to an afternoon
  • 25-risk DS foundations audit — systemic debt identified before refactoring was required
  • 4 governance documents authored proactively — each surfaced an architectural risk before it reached production

In the era of AI, the interface is no longer the moat. The intelligence behind it is.

Contact: amyngo2k2@gmail.com · Full portfolio: https://amyngo.net/