// demos
Every demo is a real app built on Layer that reimplements nothing. Each composes shipped gateway features over a different corpus and makes the gateway's decisions visible in the UI — the fastest way to see what Layer does without standing up a cluster.
Amazon product catalog
Everything together — an end-to-end storefront.
An indexing pipeline, image-native semantic search (CLIP), recommendations, facets, and observability in one app. KEDA scales workers from pipeline metrics; Karpenter scales the nodes underneath. The demo that exercises the most of Layer at once.
// Pipelines · write path · nearest_to_id · snapshots · autoscaling
PMC-Patients case reports
Clinical search, with a number.
Clinicians search by exact token (metformin 500mg) and by clinical picture (elderly woman with progressive dyspnea). chart routes both — and scores it against real relevance judgments, so the claims are measured, not asserted. A GPU Gemma cascade extracts clinical events per note.
// Query routing · qrels-scored hybrid fusion · function runtime · pipelines
BEIR/SciFact abstracts
Hybrid text fusion, proven with qrels.
Purely lexical — no embeddings, no GPU. One query fans out into a BM25 leg plus a fuzzy leg per token, fused by reciprocal rank fusion. SciFact ships qrels, so every search scores nDCG@10 and shows a fusion inspector.
// Hybrid text fusion · fuzzy matching
Goodreads books
Book search that shows its routing.
One search box, three routes. Type an author, a title, or a vibe; the gateway picks keyword, semantic, or a fused blend from the shape of the query, and shelf renders that decision as a badge with the reason.
// Query routing · hybrid text fusion · fuzzy matching
Want the implementation detail behind each one? Read the demos page in the docs.