Architecture, drawn.
Two diagrams matter most to a buyer: the enterprise AI attack path we defend against, and the trust boundary. The pipeline and response detail comes with the demo and technical pack.
What we test and defend against.
Modern AI systems chain an app, a retrieval layer, a vector store, an agent, and MCP tool servers — each hop is an attack surface. The red callouts are the failure modes our Full AI Red Team and continuous testing target.
User → AI app → RAG → vector DB → agent → MCP → enterprise system, with the AI-specific failure modes
What stays, what leaves, what’s encrypted.
Raw files and secret values never leave the endpoint. Only masked metadata crosses the wire over TLS. Console data is encrypted at rest — or, with the in-VPC option, never leaves your AWS account at all.
On endpoint (raw stays) → in transit (metadata only) → console (encrypted; in-VPC option keeps data in your account)
The pipeline and response detail.
Pipeline detail
How findings travel from the endpoint to your SIEM and ticketing, and how they are classified, scored and attributed.
Response detail
How observation, decisions and opt-in, audited action are kept separate.
Want the deployment topology?
Shared SaaS, a dedicated managed tenant and fully in-VPC options, with resilience and recovery, are covered in the demo and technical pack. See also the Trust Center.
Planned, not available today: Roadmap a multi-zone application tier, Roadmap published recovery objectives, Roadmap regional data planes and Roadmap a published large-fleet load test.
See the AI on your fleet in about a week.
Run the sensor across your estate and receive an AI risk report and an AI Bill of Materials. The assessment is free and carries no commitment.