We are building a system that tells someone they are heading for burnout. Getting that wrong in either direction causes harm, so here is exactly how it is governed.
Every message is classified before it is answered, which is how crisis language is routed away from the ordinary conversational path.
Chooses the response type against a clinician reviewed taxonomy rather than generating freely and hoping.
Checks the response against the rules the clinical board set, including what the AI must never say.
The final check before anything is shown, with hard stops for medical advice, diagnosis and self harm content.
Our board reviews the models, the escalation logic and the language used with a caregiver in distress.
Crisis paths surface professional resources and human lines rather than an AI reply, every time.
These are enforced in the pipeline, not written in a policy document and hoped for.
Population norms carry the biases of the populations they were built on. Caregiver burden instruments were largely validated on specific demographics, and applying their cut-offs uniformly imports that history.
Measuring each person against their own rolling baseline sidesteps a large part of that problem, because the comparison is internal. It does not eliminate bias, since the signals themselves can be culturally patterned, which is why the clinical board reviews the signal taxonomy and why we publish the limits rather than the marketing version.
We would rather have this conversation early. Write to connect@taloshealth.ai.
A layered pipeline rather than a single model, combining a proprietary semantic layer with general purpose language models under strict prompt and output constraints. The layers are what make it safe, not the base model.
Behavioural crisis and burnout pattern detection tests around 93 percent internally on our own evaluation set. That is a useful engineering number and not a clinical validation, and we describe it that way.
We are. The clinical advisory board reviews escalation logic, incidents are logged and reviewed, and the safety gate is a blocking component rather than a monitoring one.
Yes. You can decline assessments and still use the coordination features. The load measurement is a service to the caregiver, not a condition of access.
If something here does not match what you see in the product, tell us.