17+ years building enterprise software. I lead AWS Meeting Intelligence AI and help drive AI sales automation across AWS. An idea person who builds in working code, I get the whole team shipping with AI and automate the slow parts of UX and PM, with guardrails built in. On Autonomous Sales: Sales Acceptance nearly doubled, seller prep time down 35–50%.
Active product work at AWS — Meeting Intelligence, Autonomous Selling, and Skill Builder, the AI-Ready Design System and AI enablement underneath them.
A spec-driven, agent-consumable design system and a paved path from idea to working product. Written for two readers — the people building and the AI agents building with them. Adopted org-wide; AFX Hackathon winner.
A governed GenAI product that automates the manual work around every customer meeting for sellers across AWS's global sales org. Metrics set before the first build, the right model for each workflow, and guardrails from day one.
AI runs the repeatable steps of the enterprise sales motion. The recommendation comes first, the reasoning is visible, and the seller approves. Trust drove adoption; adoption drove results.
An AI co-pilot for the design lifecycle — distills multi-stakeholder research into actionable backlogs, generates wireframes with validation loops, and keeps the design org from re-discovering the same insights every quarter. Pilot feedback synthesized in minutes. Insights routed into Asana as tagged roadmap items. Figma components auto-generated for stakeholder comment — one continuous loop instead of three handoffs between research, design, and engineering.
Org-wide work bringing AI tooling to the broader design organization — a
spec-driven workflow that mirrors Kiro's
requirements.md → design.md → tasks.md,
a shared component library every designer can ship from, and the prototypes
that turn into shipped product faster. Less "designers experimenting with AI",
more "designers shipping AI-native products at the same pace as the rest of
the company."
Different problems, same posture. The themes underneath every project — from agent surfaces to design systems to the architecture that holds them together.
Spec files, a design system, an audit loop. The system the agent reads to know what "good" looks like.
Every screen has two readers now — a person and an agent. Both deserve a coherent system.
The driver stays in the chair. The agent accelerates; the system catches what it misses.
requirements.md → design.md → tasks.md. Intent in writing — readable by the team and the agents.
An exceptional ability to think beyond one product to create interconnected experiences. Has established new standards in Autonomous UX.
The ultimate design thinker. Optimism that elevates the team's thinking to designs that change the game.
