If you're an allergist looking at AI scribes, you've probably noticed that most of them are built for primary care and sold to every specialty with the same demo. This guide explains what an allergy note needs that a general-purpose scribe tends to miss, what the randomized trials of ambient AI documentation actually found, and how to evaluate a tool in your own clinic.
A note on terms: people search for "AI scribe", so that's the word in the title. Medora is the AI copilot built only for allergy; it drafts the note, connects it to the skin-test record and the patient's history, and leaves every decision and signature to the clinician.
What the trials say about ambient AI scribes
Documentation burden is well measured. In a time-and-motion study of 57 US physicians, nearly 2 hours of EHR and desk work accompanied every hour of direct clinical face time during the office day, plus 1 to 2 hours of after-hours work each night.[1]
Ambient scribes are now supported by randomized evidence, though not allergy-specific evidence:
| Trial | Design | What it found |
|---|---|---|
| Lukac et al., NEJM AI, 2025[2] | 238 outpatient physicians, 14 specialties, two commercial scribes vs usual care | One scribe cut time-in-note by 9.5%; the other showed no significant change. Burnout and task-load measures suggested improvement with both. Clinicians reported clinically significant inaccuracies "occasionally". |
| Afshar et al., NEJM AI, 2025[3] | 66 practitioners, 24-week stepped-wedge randomized trial | Lower work exhaustion and interpersonal disengagement; 0.36 fewer hours per day on notes; diagnostic billing codes improved; documentation quality held up. |
Read together, these say three things. The benefit is real but product-dependent. Burnout improves even when minutes saved are modest. And review is not optional, which makes "how fast can I check this draft?" the most important question you can ask.
What an allergy note needs that generic scribes miss
A structured allergy history
Environmental, food, drug and venom histories each have their own shape: the trigger, the reaction, its timing and severity, what was done, and whether the patient tolerates the item now. A generic scribe tends to flatten this into prose, which makes the next visit harder.
Testing results in the note, not re-typed into it
The 2008 AAAAI/ACAAI parameter lists what a skin-test record contains: method, allergen and concentration, histamine and saline controls with results in millimeters, and wheal and erythema sizes in millimeters.[4] If the scribe doesn't know what the testing room recorded, someone retypes it, and that's where transcription errors creep in.
Sensitization versus allergy
A positive test is not a diagnosis. NIAID's food allergy guidelines say the skin prick test alone cannot be considered diagnostic of food allergy.[5] A scribe that writes "peanut allergy" because a test was positive has made a clinical decision it had no right to make.
Pertinent negatives
"No wheezing, no hives, no lip swelling with the last exposure" is clinically meaningful in allergy. Scribes that drop negatives produce notes that look complete but aren't.
Visit types
New patient, follow-up, skin testing (prick, intradermal, patch), immunotherapy, asthma, and drug and food challenges all need different structure.
How to evaluate an AI scribe for allergy
- Bring your hardest visit type. Test with a new-patient visit that covers food, drug and environmental history, not a simple follow-up.
- Check the pertinent negatives. Did the draft keep what the patient said they didn't have?
- Trace three statements to the source. Can you see where in the conversation each line came from, before you sign?
- Look for invented treatment. Does the draft add medications, doses or plans nobody discussed? Any of that is a stop sign.
- Ask how test results get into the note. Shared record, or retyping?
- Check codes are suggestions, not submissions. ICD-10 suggestions are useful; auto-submission without review is not.
- Get the BAA and hosting details in writing.
- Trial it in your own clinic. Two weeks with your own patients will tell you more than any demo.
How Medora Copilot handles the allergy visit
Medora Copilot, built only for allergy
- Listens to the visit (ambient) and drafts an allergy-structured SOAP note: HPI, ROS, assessment and plan, and workup, with pertinent negatives. Recording can be paused and resumed.
- Visit templates built for allergy: new patient, follow-up, skin testing (SPT, intradermal, patch), immunotherapy, asthma, and drug and food challenges.
- Suggests ICD-10 codes from the note for the clinician to review, and drafts patient instructions and follow-up outputs for review.
- Smart Learning adapts the draft to each provider's documentation style.
- Evidence Mapping links lines of the note, including review of systems and past, family and social history, back to where they were said in the visit, so you can check the source before signing.
- Shares one patient context with skin testing, so the clinician sees the wheal sizes, controls and grades the nurse recorded alongside the drafted note.
- The clinician reviews, edits and signs every note. Nothing is filed without the clinician.
Medora Scribe is $99 per provider per month after a 14-day free trial, and no card is needed to start. Medora signs a BAA (through AdvanceAI LLC) and runs on HIPAA-eligible AWS in us-east-1 with AES-256 encryption at rest and TLS 1.2+ in transit. See the Medora Scribe product page.
Frequently asked questions
What is the best AI scribe for allergists?
The best one is the one that handles your hardest allergy visits accurately and lets you check the draft quickly. Test candidates on a new-patient visit with food, drug and environmental history, check pertinent negatives, and trace statements back to their source before signing.
Do AI scribes save time?
In a 2025 randomized trial of 238 physicians, one scribe reduced time-in-note by 9.5% and another showed no significant change. A second 2025 trial found 0.36 fewer hours per day on notes. Results vary by product and neither trial was allergy-specific.
Is Medora an AI scribe?
Medora is the AI copilot built only for allergy. Its Copilot module drafts the visit note like a scribe, and it also shares one patient context with skin testing and the patient's history. The clinician reviews and signs every note.
How much does Medora Scribe cost?
Medora Scribe (Copilot) is $99 per provider per month after a 14-day free trial, and no card is needed to start. Skin testing pricing is not published; practices talk to us.
Does Medora work with my EMR?
Medora pulls the schedule from, and integrates with the chart of, supported EMRs. Ask us about yours on the demo page.
Related guides
Sources
Last reviewed October 8, 2026. Summaries paraphrase the cited documents; read the originals before making clinical decisions.
- Sinsky C, Colligan L, Li L, et al. Allocation of physician time in ambulatory practice: a time and motion study in 4 specialties. Ann Intern Med. 2016;165(11):753–760. doi.org
- Lukac PJ, Turner W, Vangala S, et al. Ambient AI scribes in clinical practice: a randomized trial. NEJM AI. 2025;2(12). ClinicalTrials.gov NCT06792890. doi.org
- Afshar M, Baumann MR, Resnik F, et al. A pragmatic randomized controlled trial of ambient artificial intelligence to improve health practitioner well-being. NEJM AI. 2025;2(12). ClinicalTrials.gov NCT06517082. doi.org
- Bernstein IL, Li JT, Bernstein DI, et al. Allergy diagnostic testing: an updated practice parameter. Ann Allergy Asthma Immunol. 2008;100(3 Suppl 3):S1–S148. www.aaaai.org
- NIAID-Sponsored Expert Panel (Boyce JA, et al.). Guidelines for the diagnosis and management of food allergy in the United States. J Allergy Clin Immunol. 2010;126(6 Suppl):S1–S58. pmc.ncbi.nlm.nih.gov