NatusAI
Capability pattern
Any knowledge-driven team
Knowledge Graphs for AI answers
AI answers grounded in your facts and their relationships, each traceable to its source.
View use case
Any document-heavy teamCapability pattern
Find the right document by exact term or by meaning
Keyword precision and meaning-based search work together in one search, while your documents and the search index stay in your infrastructure.
- Status
- Capability pattern
- Data
- Documents and the index stay in your deployment
The business problem
Good search needs precision and meaning
Exact terms matter in contracts, regulations and case files, but people also search for ideas in their own words. Most setups bolt separate tools together to get both.
How it works
One engine for both kinds of search
The pattern keeps keyword and meaning-based retrieval in the same engine, next to your documents.
Combine
Hybrid in one engine
Keyword search and meaning-based search combine in a single query.
Compute
Meaning computed on site
The numerical representation of each document’s meaning is computed inside the engine, with no external service.
Contain
Stays in your deployment
Documents, embeddings and the search index stay in your deployment, with no external embedding service.
What leaders get
Better answers, fewer moving parts
For a CIO or head of knowledge management, the value is search people trust, on an architecture you can defend to your data-protection officer.
Precision and recall together. Exact clauses and related concepts appear in the same result list.
No external embedding service. Documents and their embeddings are processed inside your deployment.
A simpler stack. One engine instead of a keyword engine, a vector database and an external API to run and secure.
Products involved
What it is built with
These roles show how the pattern fits the NatusAI architecture. They do not imply that a reference deployment used every product.
- NatusAI CygnusPlanned v1Data foundation for graph, time, location and search data
- NatusAI AquilaRoadmapDocument intelligence: extract and connect information from records
What you can buy today: a delivery engagement led by our team, built on the engine proven in our client projects, with NatusAI Lyra interfaces. Products marked Roadmap show where the platform is going; we share dates under NDA.
Status: a capability pattern, a building block used across projects. It is not a separate client result.
For your technical team
- Hybrid retrieval: BM25 keyword scoring and vector similarity combined in a single query.
- On-device embeddings: computed in the engine, with no external embedding API call.
- Documents, embeddings and the index stay in the deployment, which suits self-hosted and regulated environments.
- A legal-research platform can combine these capabilities in a self-hosted deployment.
- This is a source capability pattern mapped to planned NatusAI product roles. The described search behaviour is not a verified NatusAI Cygnus release claim.
Related use cases
All 22 use cases Related use cases
Capability pattern
Audit, risk & operations
Temporal Analytics
Reconstruct exactly what was true, and what was known, at any past moment.
View use case
Questions
Document & semantic search: questions leaders ask
More answers on deployment, governance and pricing in our FAQ.
Do we need an external embedding API for semantic search?
No. Embeddings are computed inside the engine, so documents, embeddings and the search index stay in your deployment.
Why combine keyword and semantic search in one query?
Because exact terms and ideas both matter. BM25 keyword scoring and vector similarity combine in one query, so exact clauses and related concepts appear in the same result list.
Is hybrid document search a separate client result?
No. It is a capability pattern used across projects and mapped to planned NatusAI product roles. It is not a verified NatusAI Cygnus release claim.
Talk to our team
Where do your people search hardest?
Bring a document collection and the questions people ask of it. We will discuss how combined search could work on it, inside your infrastructure.
- Start with a scoped discovery phase that ends in a clear go / no-go decision.
- Bring one real question; we show where AI helps and how we would measure it.
Or write to contact@natusai.com
