Voyage
Pet parentsFor vetsDispatchJoinGet free access
◆Free for verified vets, techs & students

Your veterinary AI copilot.Every citation. One click to the source.

Work through cases, interpret labs and images, and open each citation to examine the source for yourself.

Choose a task, or let Voyage decide. Add files in the workspace.

Explore example questions
  • Photos
  • ·Lab reports
  • ·Radiographs
  • ·PDFs

Here for your own pet? Explore Voyage for Pet Parents →

◆How it works

From scattered signals to a usable clinical record.

Illustrative case · no patient diagnosis or treatment protocol

  1. 1

    Frame

    Question + record

    11y cat · weight loss + PU/PD · reconcile serial labs, urine and history

    Mara · feline · 11y FS

    Timeline
    4.8 → 4.1 kg over 6 months
    Today
    PU/PD; appetite preserved; no vomiting
    Blood
    Creatinine 2.3 → 2.8 · SDMA 16 → 21
    Urine
    USG 1.018 · inactive sediment
    Still missing: blood pressure, UPC and hydration assessment.
  2. 2

    Synthesize

    Evidence + uncertainty

    Pattern synthesisConditional

    The pattern is more informative than any result alone.

    Signals that align

    K1 · K2

    Persistent renal-marker rise + inadequately concentrated urine + weight loss and PU/PD.

    Alternatives kept open

    K2

    Hydration, pre-renal contribution and post-renal causes still need clinical exclusion.

    Stage cannot be finalized

    K1 · K3

    Stable, hydrated measurements plus blood pressure and proteinuria assessment are not yet available.

    Working synthesis: CKD is a concern; confirm stability and characterize complications before staging or planning treatment.

  3. 3

    Act

    Assessment + handoff

    Assessment draftSources attached

    Prioritized problem

    Progressive azotemia with inappropriate urine concentration, weight loss and PU/PD; renal disease suspected, stage not yet confirmed.

    1. 01Reassess hydration and repeat renal values when clinically stable.
    2. 02Measure blood pressure and UPC; complete urinalysis ± culture as indicated.
    3. 03Trend weight, appetite, water intake, creatinine, SDMA and phosphorus.

    Client handoff

    A plain-language explanation of what changed, what remains uncertain, and why the next measurements matter.

Evidence you can examine

Open the source.
Examine the support.

Inspect the cited evidence, then request a source check to examine whether it supports the clinical statement—including its species, drug and route. Where gaps are identified, Voyage can revise the wording and citations.

Run a check when needed, or enable Auto-check sources for subsequent answers. Auto-check is off by default.

A closer look at the evidenceAnonymized clinical conversation · condensed

The clinical question

Brighter today. But getting better?

A cat with jaundice, prolonged poor appetite and weight loss is brighter at follow-up. Two laboratory reports tell a more complicated story.

Follow-up · clinician-reported

Bright, ambulatory,
tolerating feeds.

What still needs explaining

Persistent jaundice. An unexpectedly low glucose result. Uncertain total food intake.

2 reports · 1 clinical picture

01 / 04

Review supports your assessment. Clinical judgment stays with you.

From case context to clinical work

The case moves forward.
Your work comes with it.

Bring patient context, diagnostic images and veterinary literature into the discussion. Keep current facts, relevant history and unresolved questions visible as the case changes.

Case workspace

Case facts & records

Illustrative workflow · not a real patient

Case materials

Case continuityRelevant patient context carries into the next question.

Thoracic study

Review notes

Right lateral · thorax

Lateral view with the original R marker preserved.

Right lateral · thorax

De-identified right lateral veterinary thoracic radiograph

De-identified image · original view · no diagnostic annotation

Imaging / right lateralReal radiograph. Illustrative workflow; no patient finding is represented.
Observation
Image review belongs beside the clinical question
Interpretation
Assess available views and image quality, then relate visible findings to the history and accompanying report.
Still needed
Additional views or original report, if unavailable

Into the workup

Separate visible findings from interpretation and identify what requires further review.

Multimodal case reasoning

Read photos, lab panels, radiographs and PDFs alongside the clinical question and available patient history.

Evidence-grounded synthesis

Bring veterinary references and current literature into the discussion, with sources you can inspect.

Tool-backed calculations

Dedicated clinical calculators support dose and fluid calculations, with structured results you can review.

Beyond the first response

Edit the draft. Keep the work moving.

Create a SOAP note or client handout, review and edit it, then save your version. Adapt that saved revision for another language, recipient or length—with the original still available.

Document workspaceSynthetic document · illustrative workflow

From the case

Luna · reduced appetite

Since yesterday · no vomiting reported · examination pending

Generated draft

SOAP note · Luna

SSubjective

Owner reports reduced appetite since yesterday. No vomiting reported.

OObjective

Examination findings not yet documented.

AAssessment

Reduced appetite; cause undetermined pending examination.

PPlan

Complete the examination, review the history, and confirm next steps with the attending veterinarian.

01 / 04

Refined through real-world use.

Evaluation / public results

Inspect the performance.

Frozen cases. Named systems. Open score inputs.
Captured August 2026.

VetEvidenceBench 2.5

50 paired cases · Voyage v3.2
01 / 03 · Evidence coverage

Risk-weighted coverage measures how much clinical content has supporting evidence, with greater weight on higher-risk claims.

Voyage v3.2
49.3%
GPT-5.6 Sol
7.9%
Claude Opus 5
2.5%
0%25%50%75%100%

System evaluation, not clinical accuracy. 10,000-iteration case bootstrap. Judge-derived values remain provisional pending blinded veterinary calibration. Results describe the tested configuration, not a guarantee for every live answer.

Methods & full scorecard

PetMemoryBench 2.0

Patient-specific recall under changed facts and cross-pet interference. 24 tasks, repeated in three fresh chats each.

Read the memory study
Memory response accuracy and strict task reliability
SystemCorrect recallsAll 3 correct
Voyage72/7224/24
ChatGPT63/7221/24

Selected-pet routing favours Voyage. ChatGPT is a dated product snapshot, not all models or plans. Synthetic short-term tasks do not establish long-term retention or clinical outcomes; model-based grading has not been human-calibrated.

Where the answers come from

A reference base
you can inspect.

Selected veterinary reference works, indexed journal articles and guidelines—with citations you can open. Explore 16 veterinary titles from our reference base.

Live literature and your uploaded documents complement the indexed references. Coverage is not exhaustive.

The reference shelf · 16 selected titles
  • 01

    Plumb's Veterinary Drug Handbook

    Veterinary reference works

  • 02

    Veterinary Pharmacology and Therapeutics

    Veterinary reference works

  • 03

    Blackwell's Five-Minute Veterinary Consult: Canine & Feline

    Veterinary reference works

  • 04

    Small Animal Critical Care Medicine

    Veterinary reference works

  • 05

    Textbook of Veterinary Diagnostic Radiology

    Veterinary reference works

  • 06

    Cowell and Tyler's Diagnostic Cytology and Hematology of the Dog and Cat

    Veterinary reference works

  • 07

    Duncan & Prasse's Veterinary Laboratory Medicine: Clinical Pathology

    Veterinary reference works

  • 08

    Pathologic Basis of Veterinary Disease

    Veterinary reference works

  • 09

    Small Animal Surgery

    Veterinary reference works

  • 10

    Withrow & MacEwen's Small Animal Clinical Oncology

    Veterinary reference works

  • 11

    Veterinary Ophthalmology

    Veterinary reference works

  • 12

    Handbook of Veterinary Neurology

    Veterinary reference works

  • 13

    Small Animal Clinical Nutrition

    Veterinary reference works

  • 14

    Infectious Diseases of the Dog and Cat

    Veterinary reference works

  • 15

    Exotic Animal Emergency and Critical Care Medicine

    Veterinary reference works

  • 16

    Fowler's Zoo and Wild Animal Medicine

    Veterinary reference works

A selection, not a complete catalogue. Editions vary. Hover to pause and read.

◆Before you apply

The questions worth asking.

Use it to work through a differential, interpret case files, search veterinary references and live literature, check dose math, ask follow-up questions, and prepare a SOAP note or client handout. Voyage keeps the discussion connected to the patient while leaving the clinical decision with you.

Yes. Add a photo, lab report, radiograph, ultrasound image, or PDF to the clinical question. Voyage can describe visible findings, explain patterns in a panel, and relate the material to the available patient history and literature. Image quality, missing views, and incomplete clinical context limit interpretation; Voyage does not acquire the study or replace your examination and judgment.

Yes. Citations appear beside supported clinical claims so you can open the veterinary source and inspect the relevant passage. Sources are listed with each answer, and the available reference base is published at thevoyage.ai/forvets/sources.

An evidence gap should stay visible. Voyage can indicate insufficient support, qualify a conclusion, and withhold a dose card when it cannot locate a supporting source. Inspect the references and unresolved questions; absence of a warning is not validation. Confirm treatment and dosing against your current formulary and clinical judgment.

No. Voyage is a reference and reasoning tool that surfaces cited evidence to inform your decision. It does not examine the patient, does not establish a veterinary-client-patient relationship, and does not replace your clinical judgment. Confirm dosing and treatment against current formularies before you act.

Yes. Create a SOAP note or client handout from an answer or your notes. Review and edit the draft, then save your version. Language, recipient and length changes use the saved revision; the original stays available. Clinical documents remain drafts for professional review before sharing or use in care.

Dogs and cats, plus exotic companion species — rabbits, guinea pigs, ferrets, rodents, birds, and reptiles. Exotic coverage is a deliberate focus rather than dog guidance reshaped to fit another species.

Voyage combines veterinary references and live literature with patient-scoped context, multimodal case reading, calculator-backed dose math, and clinical documents. You can inspect citations and request a review of the answer against its sources. Selected reference titles and product evaluations are public, so you can examine the sources and limitations yourself.

Yes. VetEvidenceBench 2.5 publishes 50 paired veterinary cases, and PetMemoryBench 2.0 publishes 24 multi-pet memory tasks with three recalls each. The frozen prompts, dated product captures, adjudications, schemas, score inputs, methods, and offline scorers are public. These are system evaluations: each result describes the tested product, model, tools, memory configuration, and run protocol together — not an underlying language model in isolation.

Access is free for licensed veterinarians, credentialed veterinary technicians, and veterinary and vet-tech students. There is no card or paid clinical tier. Create an account, then submit a licence number and jurisdiction, an applicable technician credential, or a school email. The application is reviewed before the clinical desk opens.

Case details you enter are used to answer your question and to keep context across a case — not sold. Voyage is a working aid, not the official medical record; your practice management system remains the custodian of the patient record.

Source review runs when you request it, or when Auto-check sources is enabled. Auto-check is off by default and the setting is stored on the current device. You can inspect the review and resulting revisions. A check may identify gaps or remain inconclusive; it does not validate an answer for clinical use.

Use the same-patient continuation action and explicitly confirm the patient. Review current facts, relevant historical statements, changes and case constraints before proceeding. A folder name alone does not establish patient identity; owner and professional information does not automatically synchronize.

No. Uploading does not establish that a file was read or used in an answer. Case facts and records show source information, readability and available use status. A file marked as read still does not establish how it influenced the clinical answer. Review the original material and unresolved gaps.

◆For working clinicians

Ready to see every claim traced to its source?

Create your account→

Free for verified vets, techs & students · No card, no waitlist.

Voyage surfaces cited veterinary evidence to inform your clinical judgment — never to replace it. Always confirm dosing and treatment against current formularies.

Built for pets. Not repurposed from humans.

Built by Voyage