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
Audit, risk & operationsCapability pattern
Temporal analytics: see exactly what was true at any moment
Reconstruct what was true, and what was known, at any past moment. Analyse large event streams where the data lives, with no separate extraction pipeline.
- Status
- Capability pattern
- For
- Audit, risk, compliance and operations
- Data
- Analysed in place, nothing extracted first
The business problem
“What did this look like then?” is a hard question
Regulators, auditors and incident reviews ask about the past. Answering usually means heavy extraction work before anyone can start the analysis.
How it works
Take the question to the data
History is kept in the engine, so past states and statistics are computed where the events already live.
Rewind
Point-in-time view
Set a moment in time and read the exact state of anything at that instant.
Measure
Statistics in the engine
Sampling and streaming statistics run where the data lives.
Scale
Computation goes to the data
Very large networks of events are queried in place, with nothing to extract first.
What leaders get
Defensible answers about the past
For a CRO, head of compliance or COO, the value is a reconstruction you can stand behind, produced in less time.
Defensible reconstructions. Show what was true, and what was known, on the date that matters to an auditor or regulator.
Faster answers on history. Questions about past states are answered interactively instead of after an extraction project.
A leaner architecture. No separate analytics cluster to feed and secure.
Products involved
What it is built with
These roles show how the use case fits the NatusAI architecture. They do not imply that a reference deployment used every current product.
- NatusAI CygnusPlanned v1The planned data foundation for graph, time, location and search data
- NatusAI LyraAvailableAccessible operational views, maps and dashboards
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 mapped to planned NatusAI product roles. It is not a separate client result, and the event scale described is not a NatusAI Cygnus benchmark.
For your technical team
- As-of queries: set a cursor in time and read the exact state of any entity at that instant (valid time and knowledge time).
- Server-side sampling, streaming statistics and FFT run in the engine, where the data lives.
- “Query billions of nodes in place”: a claim of the underlying source platform. The event scale is not a NatusAI Cygnus benchmark.
- Interactive temporal analytics with no separate analytics cluster to feed.
Related use cases
All 22 use cases Related use cases
Delivered · client result
Banking · Fraud detection & compliance
A large European bank
Fraud detection and analytics moved from a 3-day query process to real-time intelligence.
View use case
Delivered · client result
Energy distribution · Grid management
A national electricity distribution operator
One of Europe’s first country-wide AI grid digital twins, with a near-real-time view of the national network.
View use case
Questions
Temporal analytics: questions leaders ask
More answers on deployment, governance and pricing in our FAQ.
What is an as-of query?
A query that reads the exact state of any entity at a chosen moment. It covers both valid time (what was true) and knowledge time (what was known).
Do we need a separate analytics cluster for temporal analysis?
No. Sampling, streaming statistics and FFT run in the engine, where the data lives, with no extraction pipeline to feed.
Is the event scale a NatusAI benchmark?
No. Querying very large event networks in place is a claim of the underlying source platform, not a NatusAI Cygnus benchmark.
Talk to our team
Which past moment do you need to reconstruct?
Bring one audit, incident or reporting question. We will show how a history-aware view could answer it.
- 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
