How Salus's AI personas actually work

"AI-native" does not mean AI making clinical calls. Inside Salus, intelligence is Conrad: one governed persona with a least-privilege permission scope, supervised by a human. AI assists people; it never replaces scientists or makes final clinical or financial determinations.

Conrad is a real worker with a defined job, not a chatbot layered on top of the software. He drafts, flags, extracts, and monitors. He never releases a result, issues an invoice, or submits a claim on his own.

Conrad is the live Salus Agentic voice, in the product and on salusagentic.com. He guides accessioning, results, QC, ELR, surveillance, operations, and first-week LIMS practice.

Westgard pass/fail is computed by rules, not by a model. He explains a flag and drafts CAP/CLIA notes. He validates HL7/FHIR coding. He never transmits, never releases a result, and never declares an outbreak.

A human can pause or disable Conrad from the AI Personas screen.

Every persona sits at one of four levels: Suggest, Acts with approval, Autonomous in scope, or Supervisor. Most personas operate as "Acts with approval," meaning they draft the work and a person approves it in one click, nothing is auto-committed.

A floating assistant orb appears on every screen and is always Conrad, with a proactive tip, a live operational pulse, and a one-click action, so help is one click away without anyone hunting for a menu.

Disabling a persona is a human-only action; the kill switch always stays in a person's hands. Personas hold scoped permissions that mirror staff roles, so a persona structurally cannot do something its human counterpart could not do. Every status, autonomy, and scope change is written to an append-only control log recording who changed what, and when, the same audit discipline applied to clinical actions applies to the AI layer itself.