We support those who support others
For therapists working in CBT and schema therapy

A clear picture of the patient,
more confident clinical decisions

A platform built around the real structure of the therapy process,
not around a generic note.

It brings order to thinking about the case, not only to the paperwork. The time that used to go on administration comes back to therapy, to the things there was never room for.

CBT and schema therapy
30 s note after a session
GDPR data held in the EU

This material reached you through a recommendation

Someone among your fellow therapists thought Therapy Support is an application for you.

The foundation

The structure of the process, not a generic note

Therapy Support is not a transcription tool or an AI notepad.

The platform divides the work into the elements known from clinical practice: the initial consultation and the demographic and developmental history, problems and therapy goals, clinical situations, automatic thoughts and cognitive distortions, ABC analysis, case conceptualisation with the vicious cycle model, and in work within schema therapy also schemas, modes with the mode map, coping styles and unmet emotional needs.

Every session is mapped onto the structure you know from practice. The features reflect the therapeutic process rather than redefining it.

From the session

The conversation described clinically, not just transcribed

The application reads the transcript for the structure of the session: it marks distortions, behaviours and the techniques used. The same annotations then feed the note and the conceptualisation.

Clinical annotations Live session · 00:14:32
Patient00:14:02
For weeks I wake up at three in the morning and cannot fall back asleep.
Patient00:14:11
I walk around tense all day, as if something terrible were about to happenCatastrophising. At work I put the presentation off and do not reply to emailsAvoidance - I would rather wait it out.
Therapist00:14:32
It makes sense that in such tension the urge to withdraw appears.Normalisation Anxiety responds to thought, and avoidance lowers it briefly but reinforces it long term.Psychoeducation
Distortion Behaviour Technique

What it changes in practice

  • You do not start from a blank page after a session. The note is already written and waiting for review, not for drafting from scratch.
  • You do not scan a recording looking for the moment. The catastrophising thread from session 3 takes seconds to find, together with the context of what was said.
  • The conceptualisation keeps up with the process. Annotated content feeds the diagram, the vicious cycle model and the mode map, so the picture of the case does not fall behind the therapy.
  • You prepare supervision from material, not from memory. Extracted threads and hypotheses come together in a single document.

The view comes from the application. The patient data is fictional.

In practice

Four moments where the platform helps

The work happens between sessions rather than during them.

01 · After a session

A note ready for review

The session transcript becomes a structured note following the structure of a CBT session: agenda, homework reviewed, interventions detected, new assignment, summary. You check it, correct it, save it. Fifteen to twenty minutes of work becomes two to three minutes of editing.

02 · Between sessions

A coherent view of the process

The catastrophising thread from sessions 3 and 7. Schemas, modes and coping styles tracked from session to session. Your patient fills in the GAD-7 on Sunday, on Monday you see the drop from 14 to 10, and you begin the first minute of the session differently.

03 · During the process

A living conceptualisation

A cognitive diagram, vicious cycle model and ABC analysis, and in schema work the mode map and unmet emotional needs - generated from session content and updated with each new session. In session 6 the patient mentions his father for the first time, you add a hypothesis, and it appears alongside the existing elements of the model.

04 · Before a session and supervision

Context in thirty seconds

You open the patient record and see the homework from the previous session, the questionnaire score from this morning, the thread from session 3. Before supervision: an extract of key threads, hypotheses and moments of change from selected sessions, in a single document.

The boundary

AI proposes. The therapist decides.

The platform organises material from the whole therapeutic process and prepares proposals. Everything produced in the application is a proposal for review, not a finished determination.

On your side

  • The clinical decision
  • The interpretation of material
  • The assessment of patient risk
  • The therapeutic relationship

What the application does not do

  • It does not make DSM-5 or ICD-11 diagnoses
  • It does not recommend interventions, medication or hospitalisation
  • It does not assess suicide or self-harm risk
  • It does not replace supervision, and the patient portal is not a therapeutic chatbot
  • It is not a medical device and does not pretend to be one
Data

Security built into the architecture

Data from therapy sessions is a special category of data. Compliance and privacy are part of the design, not an addition to it.

The platform team cannot read session content

Always Encrypted at database column level, with keys held in Azure Key Vault.

Pseudonymisation before anything reaches the model

Names, national ID numbers, phone numbers and emails are detected and removed before every model call.

An isolated AI instance

Our own Azure infrastructure in inference mode, not the public ChatGPT or Claude API.

Data does not train models

A clause in the contract with the provider, not a marketing claim.

Servers in the European Union

Azure: Poland Central, Sweden Central, West Europe. Compliant with the GDPR and the AI Act.

Patient rights without compromise

Full history export, permanent deletion on request, a complete audit log, and 2FA at sign-in.

Credibility

Clinical validation, not just declarations

A study with the Institute of Psychology, Polish Academy of Sciences

A study of the platform’s effectiveness carried out within the SMART NCBR consortium. It covers 360 synthetic clinical cases, with randomised participants and blind assessment of results.

Report of the PTTPB Ethics Committee

In the report “AI in Psychotherapy” (module 4, a map of psychotherapy tools) Therapy Support was recognised as a promising solution on the Polish market.

Partners: Microsoft for Startups · Polish Academy of Sciences · SWPS Booster · Lublin Medicine · Sanitas Medical Centre · Poznań Science and Technology Park

See the application in action

The simplest route is an onboarding call: we show the application on an example close to your own practice and answer questions about data security.