AI
Design Systems

Towards an Agentic Design System

Live
30 MIN + Q&A

About this Session

Design systems codify decisions and contracts, but they've always depended on human governance to stay honest. Documentation drifts from implementation. Tokens diverge from code. The "source of truth" depends on who you ask.

The fix isn't more process. It's choosing the source of truth that can't lie: code.

This session introduces a layered architecture for agentic design systems, where AI agents don't just consume components the way developers do, but actively enforce the contracts your system already defines. The architecture separates concerns across three primitives: skills (reusable executable capabilities), rules (project-specific constraints and decisions), and instructions (the methodology that orchestrates both).

The result: governance becomes an automated output, not an expensive special project. Weekly audits at cents per report. Drift detection without dedicated headcount. Design decisions that are explicit in the system rules and enforced by the agents that read them.

This isn't a better-indexed component library. It's a design system that governs itself.

From this session, you will learn:

  • The three structural layers of an agentic design system: tokenization, indexing, and strategies, with live code examples of the skills and artifacts each layer produces
  • How structured component metadata enables agents to select, compose, and enforce design decisions without human interpretation
  • Why indexing and relationship mapping are the missing infrastructure that turns a component library into an agent-ready system
  • What governance looks like as an automated output: on-demand audit reports, generated dashboards, and documentation sites built from the system itself

Who is this for?

This session is for design system maintainers, design engineers, and front-end developers who care about component architecture and are frustrated with governance being a manual, expensive process. If you've felt the pain of documentation drifting from implementation, tokens diverging from code, and "source of truth" meaning something different to every team member, this talk offers a structural answer. You don't need AI experience, but you should care about systems, contracts, and how design decisions survive contact with a real codebase. If you're skeptical about what "agentic" actually means beyond the buzzword, even better.

Presented by:

Cristian Morales Achiardi, Design Engineer at Enara Health

Cristian Morales Achiardi

(he/him)

Design Engineer

Enara Health

Exploring how AI reshapes design systems, design to code workflows, and trust between humans and machines. Currently creating pipelines that make design data machine-readable and ready for AI agents.

Secure your ticket now

Get access to all conference sessions, files, Q&As and networking.

25% OFF
Most popular
INDIVIDUAL

Solo Pass

Full access for one attendee

1 login per ticket

$599
$749 · Save 25%

Prices in US Dollars

Secure your spot
Access to live conference
Access to networking board
Networking & live Q&A
Slides & files included
All conference recordings included
Certificate of attendance
120 minutes of pre recorded AI sessions
TEAM

Team Pass

Live access to the conference for up to 3 team members

$1,795
3 seats / $599 per ticket

Prices in US Dollars

Learn with your team
Access to live conference
Access to networking board
Networking & live Q&A
Slides & files included
All conference recordings included
Certificate of attendance
120 minutes of pre recorded AI sessions

Waiting for budget approval? Get a 14-day price lock → Email us

Bonus

AI Bonus content included

120 minutes total of on-demand AI sessions (multiple sessions combined) pre-recorded during our events. Available instantly to all conference ticket holders. Access immediately after purchase.

Spotify MCP

How their Design System team built their MCP

Cursor Prompting

Best practices so AI generates the design you expect

Context-based DS

How to work with helpful plugins and workflows