Healthcare Patient Google Review Reply Emails: Use case and AI Confidentiality
A one star Google review lands on a Saturday and the practice manager wants a calm, professional reply by Monday. The quickest route is to paste the review and the patient’s chart notes into ChatGPT or Claude and ask for a response. The result is fluent, and it may confirm that the reviewer’s husband attended, what was found and what was prescribed, which the practice must not say in public. This page marks each item in the email that carries the review, the chart extract and the drafts, against the Privacy Act, Ahpra’s advertising rules on testimonials and Good medical practice, and shows how the same draft is handled on Ermos.
The email drafting a reply to a patient’s Google review
Sent by the practice manager to the doctors after a negative online review that mentions a clinical visit. It carries the review, the doctor’s summary of the consultation and the draft reply for approval.
From: Helen Tran
To: Dr Helena Voss; Dr Chidi Eze
Sent: Monday 2 November 2026, 4.10pm
Subject: One star Google review from Bev Cranston: draft reply for approval1
Helena, Chidi,
A review went up on Saturday morning. Here is what it says: “Dr Eze brushed off my husband’s chest pain on Thursday as reflux and sent him home with antacids. He was in the emergency department at Royal North Shore by 9pm. Two hours in the waiting room and a rude receptionist. Avoid.”2
Chidi gave me this summary so I could answer properly: Alan Cranston, DOB 8 January 1958, attended Thursday 29 October at 2.40pm with two days of central chest tightness on exertion. ECG normal, examined, pain judged atypical, omeprazole started, told to go to the emergency department if the pain returned at rest. Emergency department that night: normal troponin, reflux diagnosed.3
I wanted something calm but kind, so I pasted the review and Chidi’s summary into ChatGPT and asked it to write a reply that shows we followed the guidelines.4 It gave me this:
“Dear Mrs Cranston, we reviewed your husband’s visit on 29 October. Dr Eze took a full history, performed a normal ECG and treated him for reflux in line with guidelines. We are glad his hospital tests were also normal.”5
I have not posted it. It confirms he was our patient and says what we did and what the hospital found, which I do not think we can do. Here is the version I would post:
“Thank you for taking the time to leave feedback. We take every concern seriously and cannot discuss any person’s care in a public forum. We would like to talk with you directly. Please contact our practice manager on (02) 5550 0142.”6
Two other points. Ahpra says to take care engaging with reviews on third-party sites because it can be treated as using a testimonial, so I would reply only to the non-clinical points and never thank anyone for praise about treatment.7 Bec has asked Google to remove the review as defamatory. I expect it will stay, and I will call our indemnity insurer before we post anything.8
On the waiting time: we were running 45 minutes late on Thursday afternoon because of an emergency, and Bec says she was short with a patient who shouted at her. I will raise both at the team meeting.9
Please reply to approve or change the wording before 9am tomorrow. Nothing goes up until Dr Voss says so. Helen10
An invented email. The reviewer, her husband and the visit are fictional. Hover or tap any highlighted item for the analysis; the full list is below.
Online review reply drafter
An Agent+ that drafts a reply to a negative online review using the practice's own reply guidelines and tone. It works from the review text and the practice manager's notes, keeps the draft general, and flags any sentence that refers to a visit or to the patient's care.
What it does
- Reads the review and the practice's reply guidelines
- Drafts a short, general reply in the practice's tone
- Flags wording that refers to the patient's care
What stays with your people. The practice manager and the treating doctor approve the final wording and post the reply. The agent drafts; it does not publish.
An Agent+ is built once and anyone in the practice can run it. It works from your own documents and runs on Ermos Dominion, the AI unit in your office, or on Ermos Edge, your own instance in an Australian data centre.
What leaves the practice
- 1The reviewer’s name and the rating
A Google display name and a one star rating. The review is already public, so the name is not secret. Tying it to a patient record is what turns a public comment into a privacy question for the practice.
Frontier Models (ChatGPT, Claude) Already public on Google; the harm is tying it to a patient record Ermos Edge Nothing patient-held in the name itself; stays on your instance anyway Ermos Dominion Nothing patient-held in the name itself; stays on the unit anyway Use case Online review reply drafter. Drafts a short, general reply to a negative online review from the practice's reply guidelines, and flags any wording that refers to a clinical visit. See the use case - 2The review itself
A public account of a clinical visit, written by the patient’s wife. The patient is free to say what he likes about his care. The RACGP says a practice must not breach a patient’s privacy no matter what the patient has posted, and should not confirm whether the reviewer attended or share why or what treatment was given. Patient data guide.
Frontier Models (ChatGPT, Claude) The review is already public; the harm is confirming it with the chart Ermos Edge Nothing patient-held in the public text itself; stays on your instance anyway Ermos Dominion Nothing patient-held in the public text itself; stays on the unit anyway Use case Online review reply drafter. Drafts a short, general reply to a negative online review from the practice's reply guidelines, and flags any wording that refers to a clinical visit. See the use case - 3The chart extract
A name, date of birth, symptoms, an ECG result, a prescription, advice given and what happened at the hospital. All of it is health information (Privacy Act s 6FA) and so sensitive information under s 6(1), collected to provide a health service and used here for a different purpose, which engages APP 6.1. Patient data guide.
Frontier Models (ChatGPT, Claude) Sensitive health information transmitted; on consumer tiers it can train future models Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office Use case Online review reply drafter. Drafts a short, general reply to a negative online review from the practice's reply guidelines, and flags any wording that refers to a clinical visit. See the use case - 4Pasting the review and the chart into ChatGPT
The step itself. The review and the summary go together to an AI company, which can link the public name to the patient’s health information. It is a disclosure by the practice, and an act of an employee in the course of their duties is treated as the practice’s act (s 8(1)(a)). Patient data guide.
Frontier Models (ChatGPT, Claude) The review and the chart sent together, so the AI company can link a public name to a patient’s health information Ermos Edge Stays on your instance in Australia; leaves only inside a permitted excerpt, per question, to the named provider Ermos Dominion Stays on the unit in your office Use case Online review reply drafter. Drafts a short, general reply to a negative online review from the practice's reply guidelines, and flags any wording that refers to a clinical visit. See the use case - 5The AI draft that confirms attendance and treatment
A reply that says he attended, what was done and what the hospital found. Posting it would disclose health information in public. It also confirms, in writing, that the reviewer’s husband was a patient, which the RACGP advises against even when the reviewer has posted details herself. Patient data guide.
Frontier Models (ChatGPT, Claude) A draft that confirms attendance and treatment is created and kept on the AI company’s side Ermos Edge Stays on your instance, but the draft can still say too much; a person must read it before it is posted Ermos Dominion Stays on the unit, but the draft can still say too much; a person must read it before it is posted Use case Online review reply drafter. Drafts a short, general reply to a negative online review from the practice's reply guidelines, and flags any wording that refers to a clinical visit. See the use case - 6The reply to post
Generic wording that thanks the reviewer, says the practice cannot discuss any person’s care in public and offers a direct conversation. It discloses nothing and matches what the RACGP suggests: keep public responses simple and take the conversation offline.
Frontier Models (ChatGPT, Claude) Generic wording that discloses nothing Ermos Edge Not about where data goes Ermos Dominion Not about where data goes Use case Online review reply drafter. Drafts a short, general reply to a negative online review from the practice's reply guidelines, and flags any wording that refers to a clinical visit. See the use case - 7The advertising rule on testimonials
Ahpra’s testimonial tool defines a testimonial as recommendations or positive statements about the clinical aspects of a regulated health service used in advertising, and says advertisers should take care when engaging with reviews on third-party websites because that may be considered using a testimonial. Section 133 of the National Law is the provision it refers to. Advertisers are not responsible for removing testimonials on platforms they do not control.
Frontier Models (ChatGPT, Claude) Describes a public advertising rule; the decision to engage is the practice’s Ermos Edge Not about where data goes Ermos Dominion Not about where data goes Use case Online review reply drafter. Drafts a short, general reply to a negative online review from the practice's reply guidelines, and flags any wording that refers to a clinical visit. See the use case - 8Asking Google to remove the review
The RACGP says a practice can ask a site to remove a review that breaches the site’s policies or that it considers defamatory, that most sites will not remove a review because the practice disagrees, and that the practice should seek advice from colleagues, its medical defence organisation or a legal adviser before responding. The insurer’s terms decide what its policy covers.
Frontier Models (ChatGPT, Claude) General guidance on removal requests; the outcome depends on the site and the insurer Ermos Edge Not about where data goes Ermos Dominion Not about where data goes Use case Online review reply drafter. Drafts a short, general reply to a negative online review from the practice's reply guidelines, and flags any wording that refers to a clinical visit. See the use case - 9The waiting time and the receptionist
Operational facts about a busy afternoon and a named receptionist. Ahpra says comments about customer service or communication style are not testimonials, so a general reply about waiting times can be made without breaching privacy. The staff detail is internal and is not for the public reply.
Frontier Models (ChatGPT, Claude) General waiting-time detail with a named receptionist; low risk alone Ermos Edge Not about where data goes Ermos Dominion Not about where data goes Use case Online review reply drafter. Drafts a short, general reply to a negative online review from the practice's reply guidelines, and flags any wording that refers to a clinical visit. See the use case - 10The approval step
The instruction that nothing is posted until a doctor approves. The decision about what the practice says in public stays with a person.
Frontier Models (ChatGPT, Claude) An instruction to wait for approval Ermos Edge Not about where data goes Ermos Dominion Not about where data goes Use case Online review reply drafter. Drafts a short, general reply to a negative online review from the practice's reply guidelines, and flags any wording that refers to a clinical visit. See the use case
What happens in Frontier Models (ChatGPT, Claude)
- The whole document is transmitted to the provider’s servers. On personal plans the user cannot choose where it is stored or processed, and for the major providers that has generally meant outside Australia, under that country’s legal process. Some business plans offer storage in Australia, but the provider still receives the content.
- On consumer tiers, prompts can be retained and used to train future models.
- The provider’s staff and systems can reach the content under the provider’s own policies.
- Once sent, the practice no longer controls it. Retention and deletion happen on the provider’s terms.
The same document on Ermos
Ermos Dominion
The document is drafted on a unit in your office, from your own templates and the patient record. Every marked item stays on the unit, which keeps working with the internet switched off. Nothing in it is transmitted to an AI provider, so there is no disclosure to analyse: the confidentiality work is the same as for your file server.
Ermos Edge
Your documents, the index and your access boundaries stay on your own instance in an Australian data centre. When a staff member asks for this draft, only their question and the excerpts they are permitted to see go to a named Australian provider, who is contractually barred from keeping the content or training any model on it. Nothing is processed outside Australia.
| Frontier Models (ChatGPT, Claude) | Ermos Edge | Ermos Dominion | |
|---|---|---|---|
| Where the document is processed | Provider servers, generally offshore on personal plans | Your instance in an Australian data centre; answers generated in Australia | The unit in your office |
| Who can read it | Provider staff and systems, under policy | Your staff, within the boundaries you set. The named Australian provider processes only permitted excerpts, under contract, and keeps nothing | Your staff only |
| Is it kept | On the provider’s terms | Kept on your instance; the provider is barred from retaining it | Stays on the unit |
| Can it train a model | On consumer tiers, yes | No, by contract | Only your own unit learns from it, on your hardware |
Part of Use cases in healthcare practices. See how this works in practice: Patient messages on Ermos.
Common questions
Do ChatGPT and Claude use the information in an email drafting a reply to a patient's Google review?
Can we use ChatGPT or Claude to reply to a patient's Google review if we remove the names?
What if staff use their own ChatGPT or Claude account to reply to a review?
How can a practice use AI for a reply to a Google review without sending it to ChatGPT or Claude?
Can a practice reply to a Google review?
Are patient reviews testimonials under Ahpra's advertising rules?
Does the Privacy Act stop a practice confirming that someone is a patient?
See Dominion answering from your own documents.
A demonstration takes 30 minutes, uses no client data, and comes with no obligation.
Book a demo