Summarising several therapy sessions into a course of therapy
A progress summary condenses several documented sessions into one coherent text. It does not answer what was said in a single session, but what has developed across the sessions. Technically this is a different process from transcription: it is based not on audio files but on sessions that have already been documented.
Why the topic matters
A transcript captures a single session. But the professionally interesting part often lies in between — in the development over weeks. Until now, this connection is made in one’s head or by rereading old notes, and it is exactly what an application, a report or a handover needs. That is why the course of therapy, not the transcript, is the real bottleneck.
How the process works
Documented sessions as the basis
The summary starts from documented sessions, not raw recordings. Whatever has not been documented is not included.
Choosing the period
You determine which sessions are included in the summary.
Condensing
The AI creates a structured progress summary from them — a draft, not a finished text.
Review and approval
The draft is read, corrected and deliberately approved. Summaries of individual sessions can be regenerated when needed.
What AI can do here
- Name recurring themes across several documented sessions.
- Condense a long series of individual documentation entries into a readable text.
- Regenerate the summary on request if its basis has changed.
- Provide the condensed text as a starting point for a draft application.
What AI does not do here
It cannot form a course of therapy from sessions that have not been documented.
Source: Features page, section “Sessions & summaries”
It does not assess the success of therapy and does not derive an indication.
Source: Product definition on /en/about
It delivers a draft, not a finished professional text.
Source: FAQ “Who is responsible for AI results?”
How Psymira implements the process
Psymira can automatically condense several documented sessions into a structured progress summary; summaries of individual sessions can be regenerated when needed. The course of therapy stays accessible in the case context, so that the connection is not spread across individual tabs and files.
Data protection and professional control
The basis is exclusively sessions that have already been documented. Before AI calls, identifying master data are reduced; pseudonymous codes are used instead of real names. Free text such as notes and transcripts may still contain names — control over this lies with the practice. Professional approval of the summary is deliberately given by the psychotherapist.
Full details on sub-processors, processing locations and retention periods on Privacy & security.
Sources
Primary sources for the legal and technical statements on this page. Product statements are marked above with their origin in our own material.
- § 630f BGB (German Civil Code) — documentation of treatment (in German)
Statutory basis of treatment documentation, including the retention period.
- Google Cloud — data governance for generative AI on Vertex AI
Provider information on how customer data is processed on Vertex AI and not used for training.
- BPtK — practice information “Administrative KI in Ihrer Praxis” (February 2026, in German)
Guidance from the German Federal Chamber of Psychotherapists on the responsible use of administrative AI systems — data protection and professional law requirements, EU AI Act, Medical Device Regulation. It explicitly points out that important questions in the AI context have not yet been settled in a legally binding way.