Security & sovereignty
Air-gap-safe by construction, not by configuration
Cortessa is built to the constraints of a controlled environment: sovereign, offline-first and provenance-gated by design. It runs disconnected inside an accreditation boundary — the same bar defence sets, cleared for everyone else.
No external calls at runtime
In its default mode nothing leaves the machine to answer a question. There is no corpus upload, no query sent to a third party, no telemetry that phones home. Cortessa is a self-contained console: no web fonts, no CDNs, no external services — OFFICIAL-tier by construction.
This site is built the same way. It has no third-party CDNs, no external web fonts and no analytics or trackers that phone home; every asset is self-hosted. It loads inside an accreditation boundary, disconnected — the same constraint the product is built to.
On-device and in-region options, always opt-in
When a deployment chooses to bring an AI model into the loop, it does so explicitly and within a stated boundary. The classification ribbon shows the active mode at all times.
- Offline (default) — pure local retrieval; nothing leaves the machine to answer.
- In-region cloud — optional AI kept in-region (UK, London / eu-west-2); opt-in and logged.
- On-device — optional AI fully on-device; the same gate applies, and nothing leaves the machine.
Offline cryptographic licensing
Cortessa activates with offline cryptographic activation — no account, no phone-home. Licences are issued per seat or per site. A 30-day evaluation converts to activation without the machine ever needing to reach a licensing server on the internet.
The commercial model matches the security model: near-zero infrastructure to stand up, nothing to expose, nothing to leak. One file, activated cryptographically, on a dedicated workstation inside your boundary.
Auditability you can inspect
Because the product is a single self-contained executable with no external calls, its behaviour is inspectable within your boundary. The provenance gate is deterministic: the same input yields the same Verified / Draft / Refused decision, and a value not present in the source cannot pass as Verified.
- Deterministic gate. Never-false-positive by design — the guarantee is enforced in code, not left to a prompt.
- In-region option logged. When in-region AI is used, it is opt-in and logged, so the boundary crossing is visible.
- Self-contained footprint. No server to harden, no CDN to trust, no tracker to review.
- The engineer signs off. Cortessa hands over cited evidence; it never certifies on your behalf.
Measured, with context. In a 480-question blind evaluation, retrieval was ~97% with 0 provenance breaches and all 16 fabrication baits gated. In an independent, oracle-authored blind exam on a real physics corpus, 12 of 12 out-of-corpus questions were refused with 0 fabrications, fully offline. Figures were measured blind on real, public corpora; raw run artifacts are hash-manifested.
Evaluate it inside your own boundary
A scoped, paid pilot runs on your hardware, behind your firewall, disconnected if you need it to be.