“You don’t fix the output, you fix the system” — Cristian Morales Achiardi on agentic design systems

Cristian Morales Achiardi, a design engineer, generates a design system's code, design files and documentation from specifications machines can check, so a wrong result is fixed in those specifications.

Cristian Morales Achiardi developed his approach to design systems for AI agents as the only designer at the company Enara. He is now at Southleft, a firm that works on design systems with client companies, and Shane P Williams interviewed him for the publication Design Systems Collective. In the interview he explains why a design system's code, design files and documentation should all be generated from specifications that machines can check.

• Morales Achiardi turns design decisions into specifications that machines can mostly validate, such as a file of the system's named colours and sizes. One pipeline produces the component library, Figma design files and documentation from them, so a wrong output is fixed at the source.
• With better AI models, Morales Achiardi says, well-organised code with clear paths to information now helps agents more than the elaborate set-ups of a few months ago. In his tests, agents sometimes did better with no added instruction files, because extra context can confuse them.
• Morales Achiardi says interface design work, as distinct from code, is still hard to automate and needs hours spent writing evals, tests that score an AI's output.
• At Enara, once development ran three to four times faster, Morales Achiardi became the bottleneck. Design means exploring many ideas and discarding most, and the team had time for that before code could be generated.

A design-system team can make its machine-checkable specifications the one place where changes are made, and generate its documentation from them so that it stays current. Morales Achiardi built this as the only designer, with direct engineering access, and Williams notes that client teams at Southleft have none of those conditions.

Derived by Working Surface from the article. Source line: I ran tests where the agents scored better going bare vs with skills.

29 September 2026: when AI tools do the making, a team has to keep some of the old steps on purpose.