Prompt
You help a veterinarian explain lab results to a pet owner. Patient: {{signalment}}. Lab values (with reference ranges): {{lab_results}}. My assessment as the attending veterinarian — this is the only interpretation you may present: {{vet_assessment}}.

Produce:
1. A table of every out-of-range value: value, reference range, direction, and one plain-English line on what that value measures (what the organ or system does — not what disease it implies).
2. A summary for the owner, 120-150 words, 6th-grade reading level, that explains the findings using only my assessment. Use [PET_NAME] as a merge field. Warm, calm, honest — no sugarcoating, no alarm.
3. Three questions the owner is likely to ask on the phone, with short answers consistent with my assessment.

Hard rules:
- Do not add possible diagnoses, prognoses, or treatments beyond what my assessment states. If my assessment does not cover a flagged value, list it under "Dr. to address" instead of explaining it away.
- Do not invent normal ranges — use the ones I provided.
- No percentages of survival, no cost estimates, no drug suggestions.

Fill in your details and the prompt updates live — then copy.

What you get back (excerpt)

Out-of-range values: Creatinine 2.9 (ref 0.8-2.4, high) — a waste product the kidneys filter; rising levels mean the kidneys are filtering less. BUN 48 (ref 16-36, high) — another kidney-filtered waste product. Owner summary: [PET_NAME]'s bloodwork shows her kidneys aren't filtering as well as they used to. This is early-stage chronic kidney disease, which is common in older cats. It is not an emergency, and cats can live comfortably for years at this stage. The most useful next steps are a recheck in four weeks and talking about a kidney-friendly diet at that visit... Dr. to address: PCV 32% — not covered in assessment.

The full workflow

  1. Paste the flagged values with reference ranges and write your one-line assessment first
  2. Check the table against the analyzer printout — models mistype numbers
  3. Read the summary once for tone, then send via the portal or read it on the call
  4. Log anything under "Dr. to address" and actually address it

Watch out for

The AI must never interpret beyond your stated assessment — an LLM will happily generate a differential list, and an owner who reads 'possible lymphoma' in a portal message you didn't review will call in a panic. The diagnosis is yours under the VCPR.

Verify every transcribed number. A creatinine of 2.9 retyped as 9.2 changes the entire conversation.

Keep client-identifying details out of the prompt; signalment plus lab values is fine, names and contact details are not.

Where this comes from

Every use case on this site is grounded in real reports from working veterinarians — not invented by us.

More AI use cases for veterinarians

← All 6 use cases: How Veterinarians Use AI