1 · A person lives their life
No streaks, no daily obligation, no implication that a quiet week means something is wrong. Healing Space fits around a life; the life does not have to fit around it.
How it works
Therapy happens for an hour. Life happens in the hours between — and most of what matters in those hours has to be reconstructed from memory when therapy begins again. This is how Healing Space helps preserve that thread, and where it deliberately stops.
Six steps. The person does the first two; the technology does the rest of the work, and never crosses the line the third step draws.
No streaks, no daily obligation, no implication that a quiet week means something is wrong. Healing Space fits around a life; the life does not have to fit around it.
In their own words, in conversation — or with a single tap, or a few typed lines at midnight. Nobody should have to write clinical documentation about their own week.
Captured is not shared. Reflections are private unless shared, item by item, and that decision can be changed afterwards. Sharing is something a person does, never something that happens to them.
What has been shared is grouped by the stretch since the last confirmed session, with its date and its author intact. The organising is done by retrieval and comparison over records — counted, not composed.
Read before the hour rather than pieced together during it: what the patient chose to share, the agenda they wrote, how measures have moved, and what was agreed last time.
Nothing is replaced by a summary of itself. Behind every line in the pre-session view is the entry it came from — whole, dated, and attributed to whoever wrote it.
Conversation is the easiest way to say what happened. It is the wrong way to complete a validated questionnaire or change who can see your record. Both exist here, and each is used for what it is good at.
Saying what has happened, how a week has gone, what you keep coming back to, and what you want to make sure gets raised next time. Ten seconds or twenty minutes — both are a complete use of it.
Validated assessments, your safety plan, sharing and privacy controls, appointments, seeing your mood and history over time, and therapeutic exercises. These stay proper screens because clarity, validity, safety and control depend on them being unambiguous.
This part is in development, and described here exactly as it is built rather than as a capability we would like to advertise.
If you clearly state something the record can hold — a mood rating out of ten, how many hours you slept, something you want to raise with your therapist — Healing Space can offer to save it. You see the suggestion, and nothing is written until you confirm it.
The application checks the suggestion against your own message before it is ever shown to you: a mood value must be a rating you actually gave, hours slept must be hours you actually stated, and an agenda item is an excerpt of your own words. Anything inferred, rounded or rephrased is dropped.
This is not an AI writing clinical records about you. A model can suggest; the application validates; you decide. Nothing consequential is written on a model’s say-so, and no automated decision is made about your care.
An agenda item is saved in the words you used, not translated into clinical language. “I want to talk about what happened at work” reaches your next session as that sentence, because how you said it is part of what you said.
Disclosure rather than reassurance — the useful version of this answer is specific.
What you type into the conversation is processed by our AI provider (currently Groq-hosted infrastructure, named in the privacy policy). Training models on patient conversations is disabled, and enabling it would require separate governance and consent.
Intervals, counts, dates, comparisons between two points in time and the history of an agreed goal are retrieved and calculated from what was recorded. They are not generated prose, and they do not change when a model changes.
Healing Space does not diagnose, does not decide what caused what, does not judge whether therapy is working, and does not decide that two difficult periods months apart are the same thing. Those belong to the two people in the room.
Voice is a direction we are developing and evaluating. It is not a finished capability, and we would rather say that than show you a microphone and imply otherwise.
The prototype in the development build uses the browser’s own speech recognition. On some platforms that sends audio to an external vendor’s service, which is not a foundation we are prepared to build a private product on — so that implementation has been rejected as the production architecture rather than quietly shipped.
What we are investigating instead is speech processing that runs on the device, or on infrastructure Healing Space controls. Until that exists and has been tested, typing does exactly the same job, in the same conversation, with the same history behind it — and wherever voice does appear in the product, it says plainly how it is being processed.
It holds the space around therapy. It does not do the work of therapy, and it is not marketed as a companion for your mental health.
Nobody is watching a screen. There is no continuous clinical monitoring, no pattern-watching on a clinician’s behalf, and no response-time promise. In crisis, use the contacts at the top of every page.
It is a lightweight continuity layer around existing clinical work — not an EHR, not practice management, and not somewhere a service is expected to move its whole operation.
The same mechanism, described for the people who use it differently.
For people in therapy For clinicians
For what is and is not in place today — assurance, processors, security and the claims we refuse to make — see the Trust Centre.