MOCKLY · search interfaces by intent

Designers needed references from real product flows, not isolated concept shots. Keyword tags could not express layout intent, interaction patterns, or the difference between two visually similar screens serving different jobs.

• An agentic capture layer navigates products, detects state changes, and records meaningful interface states.
• An LLM pipeline generates normalized descriptions for hierarchy, components, flow purpose, tone, and interaction patterns.
• Azure AI Search combines vector retrieval, keywords, and semantic ranking.
• De-duplication, resolution checks, safety screening, relevance tuning, and analytics protect catalogue quality.

Acquisition and interpretation stay separate. The crawler captures clean evidence; later systems decide what it means.

Normalize language before scale. A growing library becomes less useful if equivalent patterns drift into incompatible labels.

Search the job, not the decoration. Queries such as “card-based checkout” should match interface purpose and structure.

The product architecture and Hashaam's design/front-end role are documented on his public case study. Source code, ingestion scale, latency, and search-quality metrics are not public, so this case focuses on product thinking and system shape rather than invented results.