What can I use Voyage for during a case?

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.

Can it interpret lab results and diagnostic images?

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.

Does it cite its sources?

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.

What happens when the literature has no defensible answer?

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.

Can it diagnose a patient or replace 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.

Can it write SOAP notes and client handouts?

Yes. From an answer you can generate a SOAP note or a plain-language client handout in one step, with the citations from the underlying answer carried through.

Which species does it cover?

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.

How is this different from asking a general-purpose AI?

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. The source manifest and product evaluations are public, so you can examine the coverage and limitations yourself.

Who can get access, and is it free?

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.

Is patient and clinic information kept private?

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 medical record of record; your practice management system remains the custodian of the patient record.

Free for verified vets, techs & students

Clinical reasoning,with evidence beside it.

Work through a case, interpret labs and images, inspect the sources, and prepare the clinical note. Built for the decisions you make.

Photos
Lab reports
Radiographs
PDFs

How it works

From scattered signals to a usable clinical record.

Illustrative case · no patient diagnosis or treatment protocol

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
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
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.

Trust you can watch

Check the claim against the source.

Ask for the check — one tap, or leave it running on every answer — and a second agent goes through the answer section by section against the literature: hedging weak claims, deleting any number it can't source, re-checking every citation. Then it shows you exactly what it changed. Nothing is edited silently.

Illustrative review

GI stasis · Holland LopReviewedv0v1

Uncited number

GI stasis recurs in ~40%figure removed — unsourced of rabbits after a first episode.

No source cleared the bar — the figure is removed, not guessed.

Citation check

Motility returns within 24–48 h of prokinetics^K5Background

Source is topical, not direct support — demoted, never hidden.

Weak claim

Cisapride may shorten time to first fecal output^K3Limited

Backed only by a single case report — hedged, and the source labelled.

Every version is kept — nothing is edited silently; every change is yours to inspect.

Every section it checks, it shows you — including what it removed.

Clinical reasoning architecture

Clinical intelligence.
With a second look built in.

Voyage brings patient context, diagnostic images and veterinary literature into one clinical reasoning workflow—with dedicated calculation tools and an integrated evidence review layer.

CASE DESK / 01

One patient. A connected record.

Illustrative workflow · not a real patient

Thoracic study

REVIEW NOTES

Right lateral · thorax

Lateral view with the original R marker preserved.

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.

Agentic evidence review

Beyond finding a source.
Checking what it supports.

Evidence Check reviews the connection between a clinical statement and its cited evidence, then revises the answer where needed. Enable Auto-check sources or request a review when you need a second look.

Evidence Check, step by step

01
Review
Examine clinical claims and the evidence attached to them.
02
Revise
Revise wording and citations where the review identifies gaps.
03
Verify support
Check the revised statement against its cited evidence.

Illustrative source check · fictional example

Draft statement

“The study supports use in dogs and cats.”

After evidence review

“The study reports findings in dogs. It does not establish use in cats.”

Why the wording changes: the example source includes dogs only. A citation should support the scope of the statement it accompanies.

Review supports your assessment. Clinical judgment stays with you.

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

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%

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
System	Correct recalls	All 3 correct
Voyage	72/72	24/24
ChatGPT Free	63/72	21/24

Selected-pet routing favours Voyage. ChatGPT Free 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.

Veterinary reference works, indexed journal articles and live literature, alongside the documents you upload. Open the citation to inspect the source; use the manifest to check available titles and editions.

Reference works & formularies

Plumb's Veterinary Drug Handbook
The Merck Veterinary Manual
Bonagura & Twedt — Kirk's Current Veterinary Therapy
Blackwell's Five-Minute Veterinary Consult

See available titles and editions in the source manifest.

Peer-reviewed journals

JAVMA — J. of the American Veterinary Medical Association
AJVR — American Journal of Veterinary Research
Frontiers in Veterinary Science
Animals (MDPI)

Indexed articles complement the reference works; journal coverage is not exhaustive.

Guidelines & clinical references

WSAVA guidelines
CAPC — Companion Animal Parasite Council
eClinPath — Cornell clinical pathology
Cornell & UC Davis veterinary medicine

Indexed references, live literature, and the documents you add.

+ Every title named here was checked against the live index. The manifest also says what we don't carry — and what to do about it. Read the source manifest →

Before you apply

The questions worth asking.

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.

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.