Concept·Workflow Infrastructure·Augmentation·Emerging·CON-026

Custom Plugins

Value hypothesis

Designers automate workflows without engineering support, creating custom tooling for tasks not covered by existing plugins.

Efficiency · Innovation

Teams identify repetitive or specialised tasks that would be suitable for automation. The desired functionality is specified in natural language, then produced by an AI coding agent. The designer tests the output, identifies gaps or errors, and re-prompts to refine. Success creates a persistent workflow tool, reusable beyond a single project.

Risks in application

Black Box Rationale

Plugins are built from code the designer cannot read, so when they break or behave unexpectedly they cannot be manually debugged; maintenance depends on re-prompting rather than understanding.

Constraint Blindness

AI-generated plugin code may operate correctly in testing but fail under Figma API updates, edge-case file structures, or team-scale deployment conditions the designer could not anticipate.

Expertise that differentiates

Design System Logic

Specifying plugin functionality addresses real workflow bottlenecks, integrates correctly with design system infrastructure, and is scoped to scale across different use cases within the team's tooling environment.

Technical Feasibility

Assessing whether AI-generated plugin code will behave correctly within API constraints, and recognising implementation approaches likely to be brittle or difficult to maintain across tool versions.