Built around the endpoint. Verified at every hop.
Vedric is an agent, a cloud, and an operator surface - connected by signed messages and tenant-isolated at every layer. Nothing collected is content. Nothing executed goes unlogged. Nothing written can be quietly undone.
Three layers. One signed channel between them.
The agent
Runs as a managed service under OS-sealed credentials. Collects primarily behavioural metadata from the host, identity, and network layers, plus a documented bounded PowerShell script preview where host logging is enabled.
The correlator
Baselines behavior per user and per peer group, correlates deviations into storylines, and runs triage against a strict budget. Every query is tenant-scoped. If the AI layer is unavailable, baseline detection keeps running.
The surface
Your analyst can correlate related activity into storylines. Remote response commands are admin-gated, reason-required, signed, and audited, but remain default-off pending deployment-specific safety drills.
The agent
Runs as a managed service under OS-sealed credentials. Collects primarily behavioural metadata from the host, identity, and network layers, plus a documented bounded PowerShell script preview where host logging is enabled.
The correlator
Baselines behavior per user and per peer group, correlates deviations into storylines, and runs triage against a strict budget. Every query is tenant-scoped. If the AI layer is unavailable, baseline detection keeps running.
The surface
Your analyst can correlate related activity into storylines. Remote response commands are admin-gated, reason-required, signed, and audited, but remain default-off pending deployment-specific safety drills.
How a deviation becomes a signed verdict.
- 01 /CollectEndpoint behavior is collected across several surfaces by default. Deeper visibility modes can be enabled per tenant. What is never collected is documented and refused in code.
- 02 /NormalizeUser identity is anonymized on the endpoint. The backend stores a per-machine one-way token, not the raw identity. Your team can label that token after an independent local investigation; Vedric cannot reverse it.
- 03 /DetectTwo layers run in parallel. Behavioral baselines (per user, per peer cohort, per endpoint) surface drift from the user's own pattern. Rule-based detection catches well-known-bad patterns that fire from day one. A quiet warm-up prevents the baseline layer from generating noise while it settles; the rule layer is active immediately.
- 04 /CorrelateDeviations and rule hits on the same endpoint and user within a short window become a single correlated storyline.
- 05 /TriageTriage runs inside a fail-closed budget and circuit. It reads tenant-scoped data only and never reaches the endpoint. If it is unavailable for any reason, baseline detection continues.
- 06 /RespondRemote response is a default-off preview. Its command paths are admin-gated, reason-required, signed, and audited, but they remain unavailable until the deployment passes endpoint safety and recovery drills.
- 07 /ArchiveEvery decision lands in an append-only audit. Edits and deletes are refused at the storage layer. Your forensic trail is preserved without depending on operator discipline.
Six constraints the product is built around.
Content-minimizing collection
The refusal list lives in the agent source. PowerShell script previews are the one bounded exception: they require host logging, are truncated and scrubbed, and machine-policy management is opt-in.
Tenant isolation by default
Every tenant-scoped query is automatically filtered. The guarantee is tested on every build - if a new table would create a cross-tenant path, the build fails.
Offline-signed updates
Agent binaries are signed with a key that never lives on the server. A cloud compromise alone cannot produce a valid update; the attacker would need offline key custody too.
Append-only audit
The application database role is refused edits and deletes on audit rows. Customers with a database-owner or infrastructure-admin threat model should also retain exports in an independently controlled system.
Fail-closed AI
Triage runs behind a fail-closed control layer: if the check that decides whether AI may be used cannot be completed, it resolves to no. An admin can disable AI triage for their whole organization, and an operator kill-switch propagates across the platform quickly. Baseline behavioral detection continues regardless - the AI layer is useful, not load-bearing.
Default-off response preview
Remote commands require an admin role and written reason and use a signed channel, but remain disabled until deployment-specific endpoint and recovery drills are complete.