AI in Optometry (2026): What It Actually Does Today — Scribes, Receptionists, Coding and Claims, With Honest Costs
Quick answer. In 2026, AI in an optometry practice does five concrete jobs: it answers the phone and books appointments, sends reminders and intake forms, verifies vision and medical benefits before the visit, drafts exam documentation with ICD-10 and CPT suggestions for the doctor to approve, and runs recalls and contact-lens refills. It does not diagnose, and it does not bill without a human reviewing the claim.
Last reviewed: August 29, 2026 · Jelo Editorial Team
"Optometry AI" is now asked of ChatGPT and Google's AI Overviews far more often than it is typed into a classic search box, and most of the answers those assistants give are borrowed from general medicine. This guide is the optometry-specific version: what each category of tool actually does in an eye-care office today, what it costs against the staff it supplements, where the data goes, and what it still cannot do. Where we mention Jelo, we say exactly what ships and what is still in development.
Five jobs AI does in an optometry practice today
AI in optometry today is operational, not clinical. The five jobs it reliably performs are phone reception, scheduling and reminders, insurance benefits verification, exam documentation and coding, and patient recall. Each replaces repetitive front-desk or charting work, and each requires the practice's EHR to be the system of record for the AI to be useful rather than a message-taker.
1. Phones and reception
An AI receptionist is a phone agent that answers inbound calls, books and reschedules appointments, answers "are you in my network?" questions, and hands anything it cannot resolve to a person. The useful ones are built into the EHR so they book into the real schedule; the generic ones take a message or push a booking into a calendar link. Jelo's receptionist answers after one ring, 24/7, in English and Spanish, and books directly into the Jelo schedule. It is in development as an add-on from $290 a month on top of the $300 a month platform; book a demo for early access. If your desk is checking someone out while two lines ring, this is the job to automate first. See the AI receptionist for optometry page for scope, comparison, and pricing.
2. Scheduling and reminders
AI scheduling in optometry means the agent knows provider availability, exam-length rules, and appointment types, then confirms by text, sends the intake form, and reminds the patient before the visit. The measurable result is fewer no-shows and fewer empty slots; the no-show guide walks through the reminder cadence that works for eye exams specifically.
3. Benefits verification
AI benefits verification checks the patient's vision plan (VSP, EyeMed, Davis, Spectera) and medical insurance before the appointment and summarizes exam copay, refraction coverage, frame and lens allowances, and last date of service. The front desk sees what is covered and what the patient owes before check-in. Jelo checks eligibility at check-in today; the AI biller add-on (in development, priced at 10% of insurance reimbursement) will run it automatically on the booking call and the night before. The mechanics, plans, and denial loop are on the insurance verification and claim appeals page.
4. Exam documentation and coding
An AI scribe for optometry drafts the assessment, plan, and ICD-10 codes from the findings the doctor enters during the exam, and suggests whether the visit supports an eye code (92004, 92014) or an E/M code (99213, 99214). The doctor accepts, edits, or rejects each suggestion; nothing files without sign-off. This is different from general-medicine ambient scribes, which listen to a conversation and produce a note you paste into the chart. Jelo's scribe works from the documented findings inside the chart itself, with citations back to those findings, so there is no microphone, no second app, and no copy-paste. It is in development as an add-on from $70 a month. Details on the AI scribe for optometry page; the coding decision itself is explained in 92014 vs 99214.
5. Recalls and contact-lens refills
AI recall contacts patients before their vision benefits expire, offers the contact-lens reorder before the box runs out, and books the annual exam. Because a third of eye-exam patients do not come back on their own, recall is the highest-leverage revenue job in the practice; the recall playbook covers the sequence.
AI scribe comparison table
An AI medical scribe is software that produces clinical documentation from an encounter. The three best-known products, Freed, Heidi, and Nuance DAX Copilot, are ambient dictation tools built for general medicine: they record the visit, transcribe it, and generate a note that the clinician pastes into the EHR. Jelo is an exam-native scribe: it drafts the assessment, plan, and codes from the findings already entered in the optometry chart. The table shows where that difference matters for an OD.
| Capability | Freed | Heidi | Nuance DAX Copilot | Jelo |
|---|---|---|---|---|
| How it captures the visit | Ambient audio | Ambient audio | Ambient audio | Findings entered in the chart |
| Optometry vocabulary (refraction, SLE, DFE, IOP, OCT, CL parameters) | General medicine | General medicine | General medicine | Native |
| Drafts ICD-10 codes | Check vendor | Check vendor | Check vendor | Yes, with citations to findings |
| Suggests eye code vs. E/M level | No | No | Check vendor | Yes |
| Writes into the EHR | Copy/paste or integration | Copy/paste or integration | Epic/other integrations | Inside the chart, no paste |
| Doctor review before filing | Yes | Yes | Yes | Yes, per suggestion, audited |
| HIPAA / BAA | Yes | Yes | Yes | Yes, signed BAA |
| Price | ≈ $99 per clinician/month | Free tier + paid tiers | Enterprise, check vendor | Add-on from $70/month (in development) |
Vendor features and pricing change often; verify with each vendor. The practical question for an OD is not which scribe writes the prettiest paragraph, it is whether the note lands in your exam template with the codes attached, or whether someone still has to paste it in and code it afterward.
AI receptionist comparison: generic vs. EHR-native
An AI medical receptionist that "books into the schedule" needs four things a calendar link does not provide: live access to the provider schedule and appointment-type rules, the ability to capture and verify insurance on the call, a lookup into the patient's chart for reorders and recall status, and a defined escalation path to a human. Generic receptionists (Goodcall, Smith.ai) and phone platforms (Weave) deliver call answering and message capture well; they cannot see the chart or the plan.
| What "books into the schedule" requires | Generic AI receptionist | EHR-native (Jelo) |
|---|---|---|
| Live provider availability and exam-length rules | Calendar link, one shared view | Reads the real schedule |
| Insurance captured and verified on the call | Takes a message | Verifies vision + medical benefits |
| Chart lookup (last exam, CL Rx, recall status) | No | Yes |
| Contact-lens reorder from the Rx | No | Yes |
| English and Spanish | Check vendor | Yes |
| Escalation to a human at the desk | Message / transfer | Transfer or callback task in the EHR |
| Pricing | Per-plan or per-call tiers | Add-on from $290/month (in development), on top of the $300/month platform |
If your EHR is one of the legacy systems and you are not switching, a generic receptionist is still better than voicemail. If you are choosing an EHR, choose one where the receptionist is native. The full breakdown, including what it escalates and a live-call demo, is on the AI receptionist page.
What it costs vs. a front-desk hire
The honest cost comparison for an AI receptionist is against the calls a practice currently misses, not against firing anyone. A full-time front-desk employee in the US typically costs $38,000 to $48,000 a year fully loaded and covers roughly 40 hours a week; the phone rings outside those hours and during every check-out. Jelo's receptionist is an add-on in development, priced from $290 a month on top of the $300 a month platform, with no per-call charge.
A worked example for a one-doctor practice, with illustrative assumptions you should replace with your own call log:
| Assumption | Value |
|---|---|
| Inbound calls per day | 40 |
| Calls that go unanswered (busy desk, lunch, after hours) | 20% → 8 calls |
| Missed callers who would have booked | 30% → 2.4 visits |
| Average exam + materials value | $180 |
| Recovered per day | ≈ $430 |
| Recovered per month (21 working days) | ≈ $9,000 |
| AI receptionist add-on per month (from) | $290 |
Cut every assumption in half and the receptionist still returns more than fifteen times its cost. The ROI calculator on the receptionist page lets you run your own numbers. For the exam side, the value of an AI scribe is time rather than recovered revenue: a doctor who spends 6 to 10 minutes per encounter on the assessment, plan, and codes gets most of that back, which across 15 to 20 exams a day is one to two more patients or an earlier end to the day.
HIPAA, BAAs, and where the data goes
AI in optometry is HIPAA compliant when the vendor signs a Business Associate Agreement, encrypts protected health information in transit and at rest, keeps role-based access and audit logs, and does not use PHI to train external models. Any tool that hears a phone call, reads a chart, or drafts a note touches PHI, so a BAA is not optional. Ask each vendor four questions before you sign.
- Will you sign a BAA? If the answer is anything other than yes, stop. A consumer chatbot subscription is not a covered arrangement.
- Is PHI used to train your models or a third party's? The right answer is no, in writing. Jelo does not use PHI to train external models.
- Who can see the transcript or draft, and is every AI call and every doctor decision logged? Jelo audits every AI call and every accept/edit/reject decision with immutable logs.
- Where is the data stored and for how long? Ask for the region, the retention policy, and how a patient's data is deleted on request.
Call recording adds a state-law layer on top of HIPAA: several states require all-party consent, so the greeting should disclose recording where required and the practice should confirm the rule with its state board or counsel. Jelo's HIPAA checklist for optical shops covers the rest of the practice, including texting and POS.
A note on optometry telehealth
Optometry telehealth in 2026 is mostly follow-up: post-op co-management check-ins, red-eye triage, dry-eye and medication reviews, and contact-lens compliance visits that do not require a slit lamp. AI's role here is the same as in the office: the receptionist books the video slot, the scribe drafts the note and the code from what the doctor documents, and the billing engine routes it to the right payer with the right modifier. Refraction and dilated exams still happen in the chair.
How to evaluate optometry AI in a 30-minute demo
The fastest way to separate an optometry-ready AI tool from a general-medicine product with an eye-care landing page is to run the demo on your own workflow instead of the vendor's script. Ask for these six things, in this order, and watch what the software actually does rather than what the slide says.
- Call the number. For an AI receptionist, ask the vendor to ring your practice line, or to let you call theirs. Book a new-patient exam, then reschedule it, then ask "do you take EyeMed?" If the agent takes a message for any of the three, it is not booking into a schedule.
- Open the booking in the EHR. The appointment should appear in the real schedule with the right provider, the right exam length, and the insurance captured. If someone has to re-key it, you have bought a message service.
- Enter a real exam. For a scribe, document a diabetic annual with a dilated fundus exam and a refraction. The draft should propose the ICD-10 for the diabetes and any retinopathy, put the refraction on its own line as 92015, and suggest 92014 rather than a generic E/M, with a citation to the finding that supports it.
- Reject a suggestion. The tool should let you decline one code without wiping the rest, and the rejection should show up in an audit log.
- Ask for the BAA and the training policy in writing. Before the demo ends, not after the contract.
- Ask what happens when it fails. A missed call should become a callback task; an uncertain code should be flagged, not silently filed. The right answer to "what does it do when it isn't sure?" is "it asks a person."
Jelo's demo runs exactly this way, on a live practice, in about 20 minutes. Bring your own call log and a recent chart.
What AI does not do yet
The honest list matters more than the feature list, because it is what an OD is really asking when they type "optometry ai" into an assistant.
- It does not diagnose. A scribe drafts an assessment from findings the doctor entered; it does not read the OCT for you or decide the patient has glaucoma. The doctor reviews and signs everything.
- It does not bill autonomously. Code suggestions are reviewed before they hit the claim. At Jelo, the AI claims agent that drafts and files appeals is a separately priced add-on still in development (10% of insurance reimbursement); the live product scrubs claims, submits them, posts ERAs, and puts denials in a worklist with the reason code.
- It does not replace the technician. Pretesting, imaging, and the patient in the chair are still human work. AI removes typing and phone tag, not clinical staff.
- It does not fix a bad schedule or a bad fee schedule. If the practice under-codes 92014 as 92012, or does not know what VSP actually pays for a refraction, AI will make the same mistake faster. Start with the eye-code vs. E/M decision and VSP vs. EyeMed reimbursement.
Frequently asked questions
What EMR do optometrists use?
Most US optometrists use one of six systems: RevolutionEHR, Eyefinity (OfficeMate and ExamWRITER), Compulink Advantage, Crystal PM, MaximEyes, or Jelo. RevolutionEHR and Eyefinity have the largest installed bases; Jelo is the newer all-in-one platform ($300 a month flat for the EHR, optical POS, CRM and billing) with the AI receptionist and exam-native scribe arriving as add-ons. Our best optometry software roundup compares them on price and features, and the RevolutionEHR alternative page shows a side-by-side for practices considering a switch.
Is AI in optometry HIPAA compliant?
Yes, when the vendor signs a Business Associate Agreement, encrypts PHI, keeps audit logs, and does not train external models on patient data. Jelo meets all four. A consumer AI chatbot used without a BAA is not compliant, even if the practice pastes in de-identified text.
Can AI answer phone calls for an optometry office?
Yes. An EHR-native AI receptionist like Jelo's answers after one ring, 24/7, in English and Spanish, books exams directly into the schedule, verifies benefits, handles reschedules and contact-lens reorders, and routes anything it cannot resolve to a person at the desk.
What is an AI medical scribe?
An AI medical scribe is software that produces clinical documentation from an encounter. General-medicine scribes (Freed, Heidi, DAX Copilot) listen to the visit and generate a note to paste into the EHR. Jelo's optometry scribe drafts the assessment, plan, ICD-10 codes, and exam-level suggestion from the findings the doctor enters in the chart, with citations, for the doctor to approve.
Does AI replace the optometric technician?
No. The technician still pretests, images, and prepares the patient. AI removes the typing, the coding lookups, and the phone interruptions around that work.
Ready to hear it answer a call or see the note draft itself? Start with the AI receptionist for optometry for the front desk, or the AI scribe for optometry for the exam lane. Both are part of the Jelo optometry EHR.