Fix-to-100: correct cluster labels, self-contained notebook embedding, honest clustering framing, consistency, PCA plot, business/ethics, build scripts as resources

Bonus depth: t-SNE, DBSCAN, per-cluster grids, query montage, FAISS benchmark, business/ethics; app stays on numpy

Deepen EDA: image grid, dimensions, colour/background, brands + richer README and notebook

README: absolute plot URLs + accurate sample size

Polish: remove em-dashes from README, app, notebook

Visual Product Recommender: app, catalog embeddings, notebook, plots