WebAI StudioCluster & Label
EmbeddingsGroup raw user feedback into themes with k-means over embeddings, then let the Prompt API name each cluster.
Why On-Device?
Topic discovery over private feedback, notes, or tickets happens entirely locally — the embeddings power the math, the Prompt API writes the labels.
Interactive Demo
Each item becomes a point in embedding space, projected to 2D. Similar feedback lands close together.
Implementation Code
Keep exploring
56 demos, all running on-device.
Moderation Cascade
The production pattern for cheap moderation: embeddings clear the obvious 90% in microseconds, the LLM judges only the borderline.
Chat With Your Document
Fully local RAG: retrieve the relevant passages with embeddings, then answer with the Prompt API — citations included.
The Omnibox
One input, every API: whatever you paste is intent-routed to the right tool — translate, summarize, proofread, rewrite, or answer.