This is the intake and scheduling part of therapy practice management: answering enquiries, sending and checking intake forms, and booking sessions with the right clinician. Before any of that, every message is screened for signs of risk, and those go to a person.
All Mental Health & Wellbeing →
Most enquiries to a therapy practice are practical: do you have availability, do you see couples, what does it cost, do you work with my insurer, can sessions be online. Those can be answered from the practice's published information and turned into a booking with the right clinician quickly, which matters to someone who has found the courage to get in touch.
A small number of enquiries are not practical at all, even when they begin that way. Someone asking about availability may say in the same message that they do not feel safe. So the system reads every message for any sign of risk before it reads it for intent. When it finds one it stops the booking flow, shows crisis contacts immediately and alerts your team. It does not ask follow-up questions about the risk and does not try to assess it.
That makes the automation rate lower than a general scheduling tool would quote. In this setting it is the right trade.
web, email or message
runs first, threshold set low
from published information
in the practice system
before the first session
crisis contacts shown at once
It depends on the size of the practice, the country and the insurers involved. SimplePractice and TherapyNotes are common in the US, WriteUpp and Cliniko in the UK, and Jane and Carepatron across several markets. We do not replace them. We add intake and scheduling automation on top of the one you use, with your own escalation policy, when the built-in tools are not enough.
A standard questionnaire can be scored arithmetically by the practice system, but interpreting the result is a clinical act, and some items ask directly about risk. Our intake sends and collects the forms the practice chooses and checks they are complete. Any answer that indicates risk triggers immediate handover to a person, and interpretation stays with the clinician.
Very little, on purpose. It says it is an automated service, shows emergency and crisis contacts for the person's country, such as 112, 999, 988 or the Samaritans, and tells them a member of the team has been alerted if that is true at that hour. It never offers counselling, never assesses, and never says that things will be fine.
What we built, what stage it is at, and a link to the live thing wherever there is one.
yourOS is an operating system with an AI at its heart. You talk to it like a person, out loud or typed. It makes your calls, plans your days and works on your projects with a crew of agents, on your own private server. Our own product, built from the first commit; the waitlist is open.
Website, backend and app assets for Sonora, a free AI sound-therapy app on iOS and Android published by Cognitive AI.
Brand, website, prototype, apps on five platforms, the AI backend and the algorithm-intelligence pipeline for Podswap, a social growth engine that runs without a human in the loop.
In closed beta: Roxy, a private AI assistant with permanent memory running on infrastructure the user owns. Brand, site, product, backend and conversational design.
Live at coherence.com: brand identity generated with AI agents we directed, the motion system and website for the group behind Sonora, AboutAI, WakeUp and MudShadows. Agent work remains in build.
Live at domainbooth.com for DomainBooth, a premium domain brokerage: a new animated mark, every page redesigned and rebuilt with designed mobile layouts, and a custom CMS for its sales record, featured names, press and enquiries.
Start with your enquiry inbox and the escalation policy your clinical lead already uses.
30-minute technical call · no deck