Feedback arrives from post-visit surveys, email, Google Business Profile and the website form, and a complaint involving possible harm can sit in a shared inbox for a week. The solution assigns each piece of feedback a category, a department and an urgency, logs serious complaints in the manager's register with a Teams notification and prepares a draft reply, while a person replies to the patient.
Built for ISO 27001NIS2 DORA
A medical practice receives feedback from several sources: post-visit surveys sent from Cliniko or CGM, email, a complaints form on the website, Google Business Profile reviews and social media. They all land in different inboxes read by different people when they have time, and a future patient sometimes sees a Google review before the manager does. Most feedback is about waiting time or service at reception, but among it are complaints about possible harm to a patient, for which the law and internal procedures set deadlines and a register. Such a complaint, read a week later, is a risk to the practice and a loss of trust for the patient.
The solution collects feedback from all sources through Power Automate flows: surveys from Cliniko or CGM, the mailbox, the website form and Google Business Profile reviews, while reviews from other portals are uploaded by a responsible employee. A private model in the MDP CLOUD GPU cloud in Lithuania (EU) assigns each piece of feedback a category (waiting, service, price, hygiene, communication), a department or doctor according to your structure, and an urgency level, after first removing unnecessary personal data from the text. Complaints with signs of possible harm, or ones that require an official response under your rules, are immediately entered in the manager's register in SharePoint with a deadline and a notification in Teams. For every piece of feedback that needs a reply, the agent prepares a draft in your tone, both for a public Google Business Profile reply and for an email to the patient, but only the responsible person replies: they review, edit and send or publish it. The model does not assess the quality of treatment and does not form conclusions about harm; it only classifies and routes. At the end of the month the solution builds an overview by category and department, with quotes free of personal data. We take survey data from Cliniko and CGM through an API, an export or an email flow, depending on the version; we choose the method after checking. Texts stay in the EU and are not used to train the model, every classification is logged for GDPR, and the register and notifications stay in your Microsoft 365 tenant. We maintain the model environment like our other GPU cloud servers.
Four steps from input to a record in your system, with human approval wherever there is risk.
Flows take feedback from post-visit surveys in Cliniko or CGM, the mailbox, the website form and Google Business Profile, while reviews from other portals are uploaded by a responsible employee. Before classification, unnecessary personal data is removed from the text, leaving only what is needed for the reply.
A private model in the EU assigns a category, a department or doctor according to your structure, and an urgency level according to your rules. Signs of possible harm or a demand for an official response are flagged separately, and doubtful cases are assigned a higher urgency, not a lower one.
Complaints involving possible harm are entered in the manager's register in SharePoint with a deadline and a notification in Teams. Others are routed to the department owner with a draft reply, either for an email or for a public Google Business Profile response. Only a person who has reviewed and approved the text replies to the patient.
At the end of the month an overview is built, with figures by category, department and source and with quotes free of personal data. Together with your quality manager we check classification accuracy and refine the categories and urgency rules.
Power Automate flows for surveys from Cliniko or CGM, the mailbox, the website form and Google Business Profile reviews, with a window for manually uploading reviews from other portals.
Your structure of categories, departments and urgency levels with a list of signs of possible harm, agreed with the quality manager and the internal procedures.
A complaints register in SharePoint with deadlines and Teams notifications, and draft replies in your tone for the responsible employees, for emails and public Google replies.
A private model in the EU, an automatic monthly overview for management, a full log of classifications and replies for GDPR, and our support after implementation.
Private model in the MDP CLOUD GPU cloud in Lithuania (EU) + Power Automate flows from Cliniko or CGM surveys, email and Google Business Profile into a SharePoint register with Teams notifications; we connect to the clinic system through an API, an export or an email flow, depending on the version. We choose the platform by the task and by where your data may be located; read more about this service and its limits on the service page.
No. The agent only prepares a draft reply, and the responsible employee replies to the patient or publishes a public reply on Google Business Profile after reviewing and approving the text. For complaints involving possible harm, the reply is prepared by the manager or the quality manager according to your internal procedure.
Yes. We take post-visit survey results from Cliniko or CGM through an API, a file export or an email flow, depending on the version, and read Google Business Profile reviews through its interface. We choose the integration method after checking; if a source has no interface, reviews are uploaded manually into the same flow.
No, it only recognises signs from a list you define and routes the complaint to the register so deadlines are not missed; the assessment and conclusions are made by the responsible people in your practice in line with the applicable law. Before classification, unnecessary personal data is removed from the text, the model runs privately in the MDP CLOUD GPU cloud in Lithuania (EU), data is not used for training, and the register and log are kept in your Microsoft 365 tenant under your permissions.
National health insurance billing reports on paid and rejected services, private insurer notices, pre-invoices and supplier invoices arrive by…
Hygiene procedures, the medication ordering process, how sick-leave certificates are issued through the social security portal, cover rules and…
Before a visit, a doctor has a few minutes to read dozens of discharge notes, test results and referrals in Cliniko or CGM and the national…
The reception phone is busy, and most calls are about free appointments, test preparation and required documents.
This service is delivered by specialists with valid international certifications. Their expertise is confirmed by independent organisations, not by us.
AI systems are deployed with protection against data leakage and model abuse.
The AI security programme and its controls are managed following the ISACA methodology.
AI risks are identified and managed like any other IT risk.
We reply within 1 business day
