How it works
Live signals, a living knowledge graph, and human validation.
The model reasons. The graph holds relationships. Live tools report current state. Confirmed learning is preserved — without retraining a model on your data.
Architecture
How evidence flows through Provenant.
Live signals
What is happening now — logs, metrics, queues, deployments.
Knowledge graph
How services, code, owners and incidents relate.
Semantic memory
Runbooks and confirmed past incidents, retrieved by meaning.
Reasoning
A language model that explains verified results — it never invents numbers.
Onboarding
Up and running without handing over the keys.
Connect
Grant read-only access to telemetry, deployment metadata and repositories. Secrets stay in your vault.
Discover
Provenant maps services, dependencies, repositories and business use cases.
Confirm
Your engineers review and correct the map before anything is trusted.
Investigate
Run investigations on demand or from alerts, in advisory mode first.
Deployment and model options
Deploy your way
Managed SaaS or self-hosted in your environment.
Your model
Local models or an approved provider — switchable without changing workflows.
Full provenance
Every AI response records provider, model and configuration.