What are the primary use cases for Shaped?
Shaped is used for building AI-powered search and recommendation systems. Key use cases include search agents, personalized recommendations, e-commerce search, image search, lexical search, semantic search, and hybrid search. It allows retrieval by text, user ID, or item ID.
What are the key features and capabilities of Shaped?
Shaped offers a unified query language called ShapedQL that combines semantic search, keyword search, filtering, scoring, and reordering in one call. It provides personalized hybrid search, a built-in feedback loop for continuous improvement, and replaces legacy RAG stacks. It is available via API, Python SDK, TypeScript SDK, or MCP.
How is Shaped priced or packaged?
Shaped offers $100 in free credits to start, with no credit card required. A comparison on the homepage states it is 50x cheaper than traditional agent stacks, costing $0.03 per answer versus $1.50 per answer.
What is Shaped and what problem does it solve?
Shaped is a vector database designed to power personalized search and recommendations, simplifying AI tool selection. It unifies retrieval, ranking, and learning in a single query to replace complex, duct-taped retrieval stacks. The platform handles embeddings, models, and data freshness, aiming to deliver relevant results in milliseconds.
Who is Shaped designed for?
Shaped is designed for developers and teams building AI-powered applications. It serves as infrastructure for building retrieval systems, offering a developer-focused platform with APIs, SDKs (Python, TypeScript), and an MCP interface.
5 of 6 research questions are answered for this product. The rest need source evidence we have not collected yet, so they are left unanswered rather than guessed.