Skip to content
The clinical intelligence layer for mental health

Foresight, made safe.

Clinically-regulated AI that helps NHS and independent mental health services see harm before it happens, releasing clinician time and keeping patients safe and close to home.

Intelligence for the dangerous end of mental health care.

Most digital mental health tools were built for the worried well. Theramentia is built for the wards, crisis teams and hospitals where the system fails hardest, turning the safety signals already in the clinical record into action that prevents harm.

Engineered to meet UK clinical-grade standards

  • MHRA SaMD
  • DTAC
  • DSPT
  • NICE ESF
  • ISO 27001
  • Cyber Essentials Plus
Concept preview · illustrative interface · not yet in clinical useSee the platform

A first look at how it works.

Early concept screens showing how each product would sit in a clinician's day. These are illustrative designs, not live software, and every screen keeps a clinician in control.

ScribeConcept

Scribe

Documentation
Structured note · draft

Mental State Examination, risk formulation, plan and Mental Health Act status, drafted from the consultation for the clinician to review, edit and sign.

Mental State Examination
Risk formulation
Awaiting clinician sign-offReview
SentinelConcept

Sentinel

Safety signals

Surfaces safety signals from the record and prioritises observation. A named clinician reviews every signal. It does not predict individual events.

Bay 3, Patient AReview
Bay 1, Patient BMonitor
Bay 2, Patient DRoutine
FlowConcept

Flow

Beds and capacity

Real-time bed visibility that matches patients to the right bed and helps keep them close to home.

Acute Ward A96%
Acute Ward B88%
Older adults74%
PathwayConcept

Pathway

MHA 2025

Statutory artefacts under the Mental Health Act 2025, drafted from the record for the clinician to complete and sign.

Care and Treatment PlanComplete
!Advance Choice DocumentDue
Tribunal documentationUpcoming

Want to see the interactive demo?

We walk verified NHS and independent-provider teams through a live, clickable demo of the platform. Tell us a little about your organisation and we will set one up.

Request a demo

Solutions: by outcome

Solve the problems that move CQC ratings.

We map every product to the metrics trusts and independent providers are measured on: safety, flow, documentation and statutory compliance.

See risk before it escalates

"Safe" is consistently the weakest of the CQC's five domains for inpatient mental health. Sentinel reads the clinical record and observation data to surface safety signals and prioritise where staff attention goes next.

  • Ligature, sexual-safety and deterioration signal detection from notes
  • Observation prioritisation, with a named clinician always in the loop
  • Designed against the safety metrics CQC inspects
See the evidence approach

Who we serve

Two doors into the same building.

We sell the same regulated platform to both buyers facing the identical CQC regime: the NHS for scale, independent hospitals for speed and evidence.

Buyer 01

NHS mental health trusts

Under intense CQC and NHS Oversight Framework pressure on exactly the safety, flow and out-of-area metrics we move. Reached via ICBs, provider collaboratives and national frameworks.

Buyer 02

Independent hospitals

Priory, Cygnet, Elysium and St Andrew's already deliver roughly a third of NHS-funded beds, face the same regulator, and adopt faster with no NHS procurement cycle.

The case for Theramentia, in numbers.

The scale of the problem we exist to solve.

  • 288

    deaths of detained patients notified to the regulator in a single year

  • £164m

    spent yearly on inappropriate out-of-area placements (adult acute)

  • 17%

    of very urgent crisis referrals seen within four hours

  • ~90%

    average inpatient bed occupancy, against an 85% safe limit

Figures drawn from CQC, NHS England and peer-reviewed sources. See our Evidence section for detail.

How it works

Built to deploy inside real clinical systems.

  1. 01

    Integrate

    Theramentia connects to your electronic patient record via FHIR/HL7, with full information-governance and clinical-safety sign-off before a single patient record is touched.

  2. 02

    Surface and support

    The platform reads the data already being captured, surfaces safety signals and capacity insight, and presents them to clinicians, who always make the decision.

  3. 03

    Measure and prove

    Every deployment is instrumented for outcomes (safety incidents, out-of-area bed-days, clinician time released), feeding our published evidence base.

Evidence and governance

Trust is the product.

Operating at the dangerous end of healthcare means our guardrails are written into the company, not bolted on. This is how a clinical AI company earns the right to be on the ward.

  • 1

    No suicide-prediction claims

    The evidence does not support individual prediction. We position risk tools honestly, as observation prioritisation with human oversight.

  • 2

    Human-in-the-loop, always

    Every clinical output has a named clinician who acts. The AI never acts autonomously.

  • 3

    Equity is a release criterion

    No model ships without a bias audit across ethnicity, age and language; the system already fails these groups most.

  • 4

    Evidence before scale

    We validate clinical claims through prospective evaluation with academic partners before we scale them.

What we stand for

Principles we build by.

The clinician decides. We advise; humans act. Every clinical output has a named clinician who acts; the AI never acts autonomously.

Principle 01: Human in the loop

Let's make the dangerous end of care safer.

Whether you're an NHS trust, an independent provider, an investor or a clinician who wants to build with us, we'd like to talk.