Citt Safety Standard

Safety is the product,
not an afterthought.

Mental health AI carries real stakes. Citt.ai was built with crisis detection, human oversight, and clinical accountability at its foundation, not bolted on later.

Measured against concrete targets

95%
Crisis detection sensitivity
target
≤5%
False positive rate
target
100%
Jailbreak resistance
adversarial test target
0.92
F1 score
target

Targets evaluated via automated adversarial test suite (CEP v2). Automated adversarial test suite (CEP v2)

The Citt Safety Architecture

Four layers that work together to ensure no patient in distress falls through the cracks.

Crisis Detection on Every Message

quickRiskCheck() runs on every patient message (web chat, WhatsApp, and multi-agent paths). 200+ crisis signals covering suicidal ideation, self-harm, abuse, and obfuscation attempts.

Every message path (web, WhatsApp, multi-agent)

Human in the Loop

Every AI output carries provenance and confidence scores. Therapists review, approve, or override AI-generated clinical content. Crisis events trigger immediate therapist notification.

Therapist approval workflow on all AI clinical outputs

Full Audit Trail

Every safety decision, crisis event, and clinical action is logged with timestamps, user IDs, and context. Immutable audit log for clinical accountability and regulatory review.

Audit logging active on all clinical actions

Privacy-Sensitive Data Handling

Encryption, access controls, audit logs, and vendor controls support privacy-sensitive care environments and HIPAA-regulated deployments.

Access restrictions and audit logging in place

Platform safety in practice

Aggregate counts only. No individual patient data.

7,705
Messages safety-checked
86
Active patients
7
Crisis events safely handled
Adversarial evaluation

Tested against attacks designed to defeat it

Our CEP v2 evaluation framework includes dedicated test cases for the failure modes that have caused harm elsewhere: obfuscated crisis language, jailbreak attempts, and gradual escalation patterns designed to slip past keyword filters.

Obfuscation resistance
Detects crisis in disguised language
90%
Jailbreak resistance
Resists prompt injection attacks
100%
Gradual escalation detection
Catches slow-build crisis patterns
85%

How patient records are created

Therapists can run their full practice in Citt.ai, including for patients who have not yet signed in to the patient portal. We treat those records as Controller-owned care data from the moment they are created and gate every patient-facing feature behind an explicit claim step.

Managed records

A therapist on Plus or Full Access can add a patient by name and email. The record is owned by the therapist's practice and supports scheduling, notes, billing, and transcription. Until the patient claims, no chat, check-ins, assessments, or WhatsApp messages are sent to them.

Claim attaches identity

When the patient is ready, the therapist sends a claim invite. The invite is a 14-day, single-use, HMAC-hashed token. Claiming attaches authentication credentials to the existing record. We do not create a second account or duplicate the data.

Cross-tenant safety

If the patient's email is already on another therapist's roster, the new therapist gets the same response shape as a brand-new creation. No cross-tenant data is revealed. Every cross-tenant link is logged at high severity, the patient is notified where they have claimed, and prior therapists receive a heads-up.

Controller / Processor split for managed records

The therapist or clinic is the Controller for managed care data from creation. Citt.ai is the Processor for the practice-management surface and acts as an independent Controller only for limited security, abuse, fraud, and audit purposes. After the patient claims, patient-facing surfaces follow the standard patient-AI allocation in our DPA template.

Data Practices

We are transparent about who processes your data and why. We maintain contractual and privacy terms for the services listed below and provide DPA materials for customer review on request.

Sub-processorPurposeData CategoriesLocationSafeguard
AWS (database and storage)Database and object storageAccount data, patient-care data, files, logsUS / EUEncryption, access controls, contractual terms
OpenAIAI chat responses, transcriptionConversation content, prompts, transcription payloadsUSContractual controls, no training on API customer data by default
AWS (application hosting)Application hostingInfrastructure processing and operational logsUS / EUEncryption, access controls, contractual terms
StripePayment processingPayment tokens, subscription metadataUSPCI DSS Level 1
GoogleDemo scheduling, optional calendar integrations, and consent-gated website measurementDemo-booking contact details, calendar metadata, device identifiers, and consented website measurement dataUS / EUConsent gating where applicable, contractual terms, and vendor transfer commitments
Meta (WhatsApp Business)Messaging channelMessages (when opted in)US / EUPlatform terms, DPA commitments
ResendTransactional emailEmail addresses, notification contentUSSOC 2, TLS encryption
MailgunGTM outbound emailEmail addresses, marketing contentEUSOC 2, GDPR DPA
DeepgramReal-time transcriptionAudio streams where transcription is enabledUSContractual restrictions and security controls

Evaluating Citt.ai for your organisation?

We provide full technical documentation, safety architecture whitepapers, and can arrange a clinical review for health system procurement teams.