Medical letters & documentation
Dictation or findings in – a structured medical letter, documentation and coding proposals (ICD, EBM/GOÄ – the German billing schemes) out.
Letter finished before the patient leaves the practice
Your patients.
Your knowledge.
Your agent.
AI for medical letters, incoming findings and practice knowledge – from an on-demand assistant to an agent with its own area of responsibility. Running in your practice or in a German data center. Not a single piece of patient data leaves the EU.
Three use cases that save time from day one
Processing incoming findings
External findings, discharge letters and faxes in – a summary, red flags and a filing proposal for the patient record out.
Nothing gets lost in the inbox
Practice knowledge on demand
“Which billing rule applies here?” – an answer with its source from the QM manual, billing requirements and practice guidelines.
Fewer queries, fewer billing errors
0
patient data outside the practice – technically ruled out
2
operating models: in your own server room or hosted in Germany
8
weeks from first conversation to an evaluated pilot
Why sovereign – and why in a medical practice this is not an option but an obligation
Patient confidentiality – § 203 StGB (professional secrecy) and Art. 9 GDPR: health data is the most sensitive category there is. On-premise makes the question of where it sits moot.
Patient data is never used to train third-party models – technically ruled out, not just contractually promised.
KBV IT security guideline (German statutory physicians' association), NIS2 – local inference with full logging meets the documentation duties; a chat tool in a US cloud does not.
Traceable – every query and answer is logged and attributable to a person; the physician decides, the AI documents.
The platform – two operating models, one software
On-premise · NN-Forge appliance
A pre-configured inference server in your own server room – no internet connection needed in operation.
Hosted EU · data center in Germany
Operated by Neuronetz; connected to your practice management system or document storage with permission-aware access.
OpenAI-compatible interface · open-weight models only · switch from hosted to on-premise at any time, with no data migration.
From assistant to agent – automation in three stages
STAGE 1 · ASSISTANT
The human asks, the AI answers
Medical letters, findings summaries, practice knowledge – on demand, with sources.
STAGE 2 · AUTOMATION
The AI prepares the work, the human signs off
Incoming findings pre-sorted, prescription and appointment requests prepared, draft letters ready – for the physician's sign-off.
STAGE 3 · AGENT
Its own role, its own mailbox
Runs the inbox and first drafts for the practice; physician and staff review spot checks and exceptions.
Each stage builds on the previous one. You set the pace – trust is built on results, not promises.
A pilot in 8 weeks – no investment decision required
WEEK 1
Scoping
Half a day: use case, specialty, 3–5 users.
WEEKS 2–3
Setup
Platform, connection to your document store, permissions, onboarding.
WEEKS 4–7
Operation
Daily use in real work, weekly check-ins.
WEEK 8
Evaluation
Time saved, quality, adoption – roll out or stop.
You provide: one contact person from the business side and the documents of one specialty. We deliver: platform, setup, support and a final report. We discuss terms in the first conversation.
Let's talk about your practice.
Stephan Kasdorf · Managing Director · Neuronetz UG (haftungsbeschränkt)
Exposé as PDF