Skip to content
LocumView

Clinical AI

Agents that show their work.

LocumView agents are designed to run locally inside your environment, read data through governed FHIR access, and send clinicians concise summaries with the evidence attached. They support decisions. They never make them. Not built yet: this page describes the design.

Walkthrough

Antimicrobial stewardship, step by step.

The lead example shows how every LocumView agent is designed to work.

  1. Trigger

    A new culture result posts to the EHR.

  2. Retrieve

    The agent pulls current therapy, allergies, renal function, and recent labs via FHIR.

  3. Summarize

    It builds a short clinical picture from the data it retrieved, and shows that data.

  4. Reason

    It compares therapy to the current guideline and local antibiogram, citing the exact versions used.

  5. Check

    Safety checks run for allergies, renal dosing, and interactions before anything is sent.

  6. Deliver

    A draft summary lands in the clinician’s inbox, marked for review.

  7. Log

    The data used, the reasoning, and the clinician’s response are all recorded.

Principles

Decision support, not decision making.

  • Shows the data, cites the exact guideline version used, and shows its reasoning
  • Drafts, summarizes, and flags. Never signs, orders, or prescribes. The clinician decides.
  • Every action is logged and auditable
  • Built around transparent clinical decision support principles
LocumView agents are clinical decision support tools. They do not diagnose, sign, order, or prescribe. Final clinical judgment always rests with the licensed clinician.
Stewardship review
Draft · awaiting clinician review

Synthetic patient · Bed 12 · Med/Surg

New result: blood culture

Organism
E. coli
Susceptible
Ceftriaxone, cefazolin
Current therapy
Meropenem 1 g IV q8h
Renal function
CrCl 68 mL/min

Consider de-escalation to a narrower agent based on susceptibilities.

Local stewardship guideline v2026.1, §4.2 · Antibiogram 2025

Illustrative example. Synthetic data.

Governed knowledge

How the knowledge base stays current.

Planned: agents will only reason over sources that have passed through this process.

  1. Versioned sources

    Guidelines, local antibiograms, and protocols live in a curated library. Every document is dated and versioned.

  2. Scheduled review

    Each source has an owner and a review date. Nothing ages out of date silently.

  3. Clinician sign-off

    A qualified clinician reviews and signs off every update before it reaches an agent.

  4. Regression testing

    Updates are tested against validated scenario cases. Any change in output is reviewed before release.

  5. Feedback loop

    Clinician overrides are logged and reviewed, and every update can be rolled back.

Roadmap

Planned agents.

Each new agent follows the same pattern: governed data, cited sources, clinician in control.
  • Planned

    Renal and weight-based dosing checks

    Recalculates doses against current renal function and weight, and shows every step of the math.

  • Planned

    Pharmacovigilance intake

    Helps assemble adverse event reports from chart data for pharmacist review.

  • Planned

    Therapy review

    Surfaces duration, duplication, and interaction questions for scheduled medication review.