Edit Pending
This Use Case has not been finalized.
Explore·Domain Probing·Augmentation·Emerging·DEF-103
Design Codebase Discovery
Value hypothesis
Breaks down the translation barrier between design and engineering by giving designers direct, AI-mediated access to codebase reality, reducing redesign cycles caused by incorrect assumptions about current implementation.
Insight · Velocity
The designer uses an AI coding assistant to query the production codebase before beginning visual work — asking about component properties, usage locations, legacy naming conventions, and behavioral states — to build understanding of the existing product without changing anything. AI generates structured outputs (file names, properties, usage locations, ASCII property trees) that inform design decisions by revealing the actual state of the implementation. The designer treats the codebase as a primary research source rather than an implementation target, discovering constraints and usage patterns that are invisible in design tools: legacy naming conventions, conditional behaviors, edge-case states, and dependency relationships. The output is design-informing knowledge, not a system artifact.
Risks in application
Shallow Solutions
AI may return incomplete or misleading query results — missing usage locations, reporting deprecated code as current, or surfacing file structure without capturing the runtime behavior that actually matters for design decisions.
Deskilling
Designers may reduce direct communication with engineers when AI-mediated codebase access provides sufficient implementation context, eroding the collaborative relationship that surfaces nuance no query can capture.
Expertise that differentiates
Research and Insight
Using codebase auditing to discover constraints and usage patterns invisible in design tools — legacy naming conventions, conditional behaviors, edge-case states — treating the codebase as a primary research source for design decisions.
Technical Feasibility
Formulating queries that surface design-relevant information from code (component properties, usage contexts, state machines) rather than implementation details that do not inform visual or interaction decisions.
AI Fluency that assures
Platform Awareness
Formulating queries that surface design-relevant information from code (component properties, usage contexts, state machines) rather than implementation details that do not inform visual or interaction decisions.
Product Discernment
AI generates structured outputs (file names, properties, usage locations, ASCII property trees) that inform design decisions by revealing the actual state of the implementation.
Using codebase auditing to discover constraints and usage patterns invisible in design tools — legacy naming conventions, conditional behaviors, edge-case states — treating the codebase as a primary research source for design decisions.
Creation Diligence
AI generates structured outputs (file names, properties, usage locations, ASCII property trees) that inform design decisions by revealing the actual state of the implementation.
Possible Indicators
Implementation awareness
number of implementation constraints or states discovered through codebase auditing that would not have been surfaced by design tool inspection alone
Redesign avoidance
reduction in design revision cycles attributable to incorrect assumptions about current implementation state