Choosing the process
Together we pick the process that repeats most often, has a clear definition of "done" and has its data in your systems. We define what the AI does on its own and what it does only after a person approves.
AI for healthcare providers
Reception calls, record summaries from Cliniko or CGM and the national e-health system, insurer and health insurance billing documents, internal procedures in Teams: the same jobs repeat every day in a medical practice. We implement private AI that takes them over: data stays in the EU, every action is logged for GDPR, and medical decisions are made only by the clinician.
Built for ISO 27001NIS2 DORA
- Front desk assistant for patients
The front desk is drowning in calls, and the doctor reads patient records in Cliniko or CGM after hours
- Lithuania health data in private AI in the EU
- 0 diagnoses or treatment decisions from AI
- Cliniko, CGM via API or export, national e-health system read-only
- Log every request and answer logged for GDPR
A typical clinic day: reception answers the same questions about appointment times, test preparation and the price list, and the phone is busy exactly when a patient is standing at the desk. Before a visit, the doctor pages through years of discharge notes and test results in Cliniko or CGM and the national e-health system, administration reconciles national health insurance billing reports with the services provided by hand and keys in private insurer notices, and new staff ask colleagues in Teams where to find the current hygiene procedure or the medication ordering process. Each of these jobs is small on its own, but together they eat hours every week and add a risk of errors where errors are most expensive.
AI takes over the repetitive part: it answers patients' organisational questions and records the booking in Cliniko or CGM, prepares a summary of documents for the doctor from your clinic system with links to the originals, extracts the data from health insurance and insurer documents and reconciles it with bookings, and finds the right procedure for a staff member in a Teams window. For health data we always propose private AI: models in the MDP CLOUD GPU cloud in Lithuania (EU), in an environment dedicated to your practice. Copilot and Claude are used only where there is no patient data, for example for internal procedures. We connect to Cliniko and CGM through an API, a file export or an email flow, depending on your version. The agent never writes to the national e-health system itself: only the clinician makes entries there. The first step in any project is not the model but access rights, data location in the EU, logs and a clear rule that the AI does not diagnose, does not suggest treatment and is not responsible for a patient's condition. That stays with the clinician.
What we implement for healthcare providers
The 5 solutions we implement most often in this industry. Each one starts with a single process, has a human approval step and is measured.
Front desk assistant for patients
Answers patients on your website, in Messenger or by phone about available appointments, test preparation, required documents and FAQs, and records the booking in Cliniko or CGM as unconfirmed, which the receptionist sees in the usual window. Voicemails from missed reception calls are transcribed and passed on. It does not answer medical questions: it offers a consultation and hands the patient to the receptionist, and urgent cases are sent straight to the emergency number.
We implement: Private model in the EU + Cliniko or CGM booking integration, voicemail transcription
Summaries of records and documents for doctors
Before a visit, a private model reads the patient's discharge notes, test results and referrals from Cliniko or CGM, including documents imported from the national e-health system into your clinic system, and prepares a chronological summary with a link to every original. The doctor checks the source in one click, and the summary never offers a diagnosis or a treatment suggestion and is not written to the national e-health system.
We implement: Private model in the MDP CLOUD GPU cloud in Lithuania (EU) + Cliniko or CGM read-only integration
Processing insurance and billing documents
Recognises national health insurance billing reports on paid and rejected services, private insurer notices and supplier invoices from email and scanned files, extracts the amounts, patient identifier and service codes, reconciles them with bookings in Cliniko or CGM and posts them to the accounting system. Mismatches go to the administrator's list for approval.
We implement: Document recognition in a private environment in the EU + health insurance billing exports, Cliniko or CGM and accounting integration
Internal procedures assistant for staff
Nurses, receptionists and administrators ask in Teams about hygiene procedures, medication ordering, how sick-leave certificates are issued and cover rules, and get an answer with a link to the current document in SharePoint. The assistant ignores outdated versions, holds no patient data and, when a question has no source, says it found nothing.
We implement: Copilot Studio agent in Teams + SharePoint procedures library
Classifying feedback and complaints
Patient feedback from post-visit surveys, email, the website form and review sites is automatically assigned a category (waiting time, service, price, hygiene), a department and an urgency level, and complaints involving possible harm go straight to the manager's register with a notification in Teams. A person replies to the patient; the AI only prepares a draft reply and a monthly overview.
We implement: Private model in the EU + Power Automate flow into the register, notifications in Teams
How we implement it
From the first conversation to a working solution, with measurement and ongoing support.
Access and data
We put access to files and systems in order, give the AI its own identity with the least privileges it needs, turn on an action log and choose where the model runs: your Microsoft 365, Amazon Bedrock in an EU region or our GPU cloud in Lithuania (EU).
Build and test
We build the solution with Copilot, Claude or ChatGPT, whichever fits the task, connect it to your systems and test it on historical documents and enquiries until accuracy reaches the agreed threshold.
Launch and support
We launch with a person in the loop, review the logs and exceptions and adjust the rules. Once the first process runs reliably, we move on to the next one on the list.
Are your processes different?
These solutions are a starting point for a conversation, not a complete list. Tell us which processes repeat in your company, and in one conversation we will tell you what is worth handing to AI and what is not.
Frequently asked questions
Will patient data end up on the servers of foreign AI vendors?
No. For health data we implement private AI: models in the MDP CLOUD GPU cloud in Lithuania (EU), in an environment dedicated to your practice, where data is not used for model training and does not leave the EU. Public ChatGPT or an unvetted assistant is not suitable for such data, and we write that into the implementation rules. We use Copilot only where there is no patient data, for example for internal procedures in Teams.
Does it work with Cliniko or CGM, and does the AI write to the national e-health system?
We connect to Cliniko and CGM through an API, a file export or an email flow, depending on your version and the vendor's terms; we choose the integration method after checking your environment. The agent writes nothing to the national e-health system: summaries and bookings stay in your clinic system, and entries in the e-health system are made, as before, by the clinician or the receptionist. We use health insurance billing data from the reports you export.
Can the AI suggest a diagnosis or treatment, and how will we prove it to an auditor?
No, and we do not implement that. The AI prepares summaries, answers organisational questions and handles documents, while every medical decision stays with the clinician: to questions about symptoms or medication the assistants reply by referring the patient to a specialist. Every request, answer, source and human approval is written to a log, access is managed through Microsoft Entra ID by role, and we prepare the GDPR record of processing together with your data protection officer. We work to ISO 27001 requirements.
Related services
AI by industry
The value of AI depends not on the platform but on which processes in your industry repeat.
AI for investment management
Market reviews from Bloomberg Terminal and LSEG Workspace, prospectuses, client reports built from Euroclear and Excel data, compliance documents…
AI for law firms
Contracts are reviewed by hand in Word, case material is hunted down across Clio and SharePoint folders, and hours are entered from memory in the…
AI for leasing companies
Applications with financial statements and an Experian query, asset documents from the vehicle registry, insurance policies, contracts signed via…
Expertise confirmed by certifications
This service is delivered by specialists with valid international certifications. Their expertise is confirmed by independent organisations, not by us.
-
Artificial Intelligence Security Professional
AI systems are deployed with protection against data leakage and model abuse.
-
ISACA Advanced in AI Security Management
The AI security programme and its controls are managed following the ISACA methodology.
-
ISACA Advanced in AI Risk
AI risks are identified and managed like any other IT risk.
Let's discuss AI for your healthcare practice
Tell us which processes repeat most in your company. Within 1 business day we will tell you where it makes sense to start and how long it would take.
We reply within 1 business day