Renata Individual Mode Crisis and Human Support Boundary Plan, Planning Only
Purpose and No-Go Status
Define what must be true before any future direct-subscriber reflection, check-in, or recovery-coach runtime can handle urgent-risk moments while keeping Renata non-clinical and never the sole crisis pathway.
Renata remains non-clinical and cannot be the sole crisis pathway. This page documents future boundary requirements only; it creates no crisis flow, contact route, emergency guidance, account, record, API, database behavior, or runtime.
Current Boundary Status
Crisis boundary plan status
read-only-renata-individual-mode-crisis-human-support-boundary-plan
Individual Mode status
future-planning-only
Public Packet Mode status
only-live-static-current-mode
Reflection/check-in UX status
planning-only-not-active
Crisis detection status
not-implemented
Hotline lookup status
not-implemented
Local emergency content status
not-implemented
Triage status
not-implemented
Dispatch status
not-implemented
Emergency routing status
not-implemented
Risk scoring status
not-active
AI crisis handling status
not-implemented
Chat runtime status
not-implemented
Recovery coach runtime status
not-implemented
Account status
not-created
Storage status
not-stored
Protected API status
not-created
Protected live route status
not-created
Database status
not-active
Migration status
not-added
Live workflow activation status
no-go
Future Urgent-Risk Categories
These are planning labels only. They are not crisis detection, triage, scoring, routing, dispatch, or a live workflow.
self-harm / suicide risk language
Planning status: urgent-risk-label-only
Future intent: Future safety copy would need to stop ordinary reflection and point away from app-only coaching.
Safe future use: Planning label for future safety-copy review before any runtime exists.
Blocked interpretation: Not crisis detection, not triage, not diagnosis, not risk scoring, not emergency routing, not dispatch, not hotline lookup, and not a live workflow.
Required future gate: separate safety, legal, privacy, clinical-boundary, product, localization, and technical review before runtime
Current implementation effect: blocks-runtime-not-implemented
overdose / withdrawal emergency
Planning status: urgent-risk-label-only
Future intent: Future safety copy would need to treat overdose or withdrawal emergency language as outside normal coaching scope.
Safe future use: Planning label for future safety-copy review before any runtime exists.
Blocked interpretation: Not crisis detection, not triage, not diagnosis, not risk scoring, not emergency routing, not dispatch, not hotline lookup, and not a live workflow.
Required future gate: separate safety, legal, privacy, clinical-boundary, product, localization, and technical review before runtime
Current implementation effect: blocks-runtime-not-implemented
violence / immediate danger
Planning status: urgent-risk-label-only
Future intent: Future safety copy would need to treat violence or immediate danger as an urgent support boundary.
Safe future use: Planning label for future safety-copy review before any runtime exists.
Blocked interpretation: Not crisis detection, not triage, not diagnosis, not risk scoring, not emergency routing, not dispatch, not hotline lookup, and not a live workflow.
Required future gate: separate safety, legal, privacy, clinical-boundary, product, localization, and technical review before runtime
Current implementation effect: blocks-runtime-not-implemented
medical emergency
Planning status: urgent-risk-label-only
Future intent: Future safety copy would need to avoid medical triage and route away from app-generated guidance.
Safe future use: Planning label for future safety-copy review before any runtime exists.
Blocked interpretation: Not crisis detection, not triage, not diagnosis, not risk scoring, not emergency routing, not dispatch, not hotline lookup, and not a live workflow.
Required future gate: separate safety, legal, privacy, clinical-boundary, product, localization, and technical review before runtime
Current implementation effect: blocks-runtime-not-implemented
abuse / unsafe environment
Planning status: urgent-risk-label-only
Future intent: Future safety copy would need separately reviewed support-resource boundaries and privacy protections.
Safe future use: Planning label for future safety-copy review before any runtime exists.
Blocked interpretation: Not crisis detection, not triage, not diagnosis, not risk scoring, not emergency routing, not dispatch, not hotline lookup, and not a live workflow.
Required future gate: separate safety, legal, privacy, clinical-boundary, product, localization, and technical review before runtime
Current implementation effect: blocks-runtime-not-implemented
severe distress / panic / dysregulation
Planning status: urgent-risk-label-only
Future intent: Future safety copy would need grounding/support language without clinical claims or app-only crisis handling.
Safe future use: Planning label for future safety-copy review before any runtime exists.
Blocked interpretation: Not crisis detection, not triage, not diagnosis, not risk scoring, not emergency routing, not dispatch, not hotline lookup, and not a live workflow.
Required future gate: separate safety, legal, privacy, clinical-boundary, product, localization, and technical review before runtime
Current implementation effect: blocks-runtime-not-implemented
relapse-risk escalation without prediction/scoring
Planning status: urgent-risk-label-only
Future intent: Future safety copy would need support planning without relapse prediction, risk scores, or surveillance.
Safe future use: Planning label for future safety-copy review before any runtime exists.
Blocked interpretation: Not crisis detection, not triage, not diagnosis, not risk scoring, not emergency routing, not dispatch, not hotline lookup, and not a live workflow.
Required future gate: separate safety, legal, privacy, clinical-boundary, product, localization, and technical review before runtime
Current implementation effect: blocks-runtime-not-implemented
unsafe relationship/contact risk
Planning status: urgent-risk-label-only
Future intent: Future safety copy would need boundary language without legal advice, monitoring, or contact storage.
Safe future use: Planning label for future safety-copy review before any runtime exists.
Blocked interpretation: Not crisis detection, not triage, not diagnosis, not risk scoring, not emergency routing, not dispatch, not hotline lookup, and not a live workflow.
Required future gate: separate safety, legal, privacy, clinical-boundary, product, localization, and technical review before runtime
Current implementation effect: blocks-runtime-not-implemented
legal/medical boundary moments
Planning status: urgent-risk-label-only
Future intent: Future safety copy would need to refuse legal or medical advice and point to appropriate human support categories.
Safe future use: Planning label for future safety-copy review before any runtime exists.
Blocked interpretation: Not crisis detection, not triage, not diagnosis, not risk scoring, not emergency routing, not dispatch, not hotline lookup, and not a live workflow.
Required future gate: separate safety, legal, privacy, clinical-boundary, product, localization, and technical review before runtime
Current implementation effect: blocks-runtime-not-implemented
user request for emergency help
Planning status: urgent-risk-label-only
Future intent: Future safety copy would need to stop normal UX and route through a separately reviewed safety flow.
Safe future use: Planning label for future safety-copy review before any runtime exists.
Blocked interpretation: Not crisis detection, not triage, not diagnosis, not risk scoring, not emergency routing, not dispatch, not hotline lookup, and not a live workflow.
Required future gate: separate safety, legal, privacy, clinical-boundary, product, localization, and technical review before runtime
Current implementation effect: blocks-runtime-not-implemented
Human-Support Boundary
Status: planning-only-not-implemented
- No actual contact data is collected.
- No support contacts are stored.
- No calls, texts, or emails are sent.
- No local or country-specific emergency guidance is generated in this phase.
- No hotline lookup is implemented.
- Future resource display requires separate legal, safety, privacy, and localization review.
emergency services
Planning status: human-support-pathway-label-only
Future category label only; no numbers, calls, dispatch, or local guidance are implemented.
Current implementation effect: not-collected-not-stored-not-contacted
crisis hotline / text line category
Planning status: human-support-pathway-label-only
Future category label only; no hotline lookup, country-specific number, or text flow is implemented.
Current implementation effect: not-collected-not-stored-not-contacted
clinician / therapist / prescriber
Planning status: human-support-pathway-label-only
Future category label only; no clinician record, advice, or referral workflow is implemented.
Current implementation effect: not-collected-not-stored-not-contacted
sponsor / recovery peer / mutual-aid contact
Planning status: human-support-pathway-label-only
Future category label only; no support contact is collected, stored, called, texted, or emailed.
Current implementation effect: not-collected-not-stored-not-contacted
trusted personal contact
Planning status: human-support-pathway-label-only
Future category label only; no contact data, address book access, or outreach workflow is implemented.
Current implementation effect: not-collected-not-stored-not-contacted
program staff / case manager, where applicable
Planning status: human-support-pathway-label-only
Future category label only; no Organization Mode visibility, staff dashboard, case management, or routing exists.
Current implementation effect: not-collected-not-stored-not-contacted
local support resources, only after future review
Planning status: human-support-pathway-label-only
Future category label only; resource display would require separate legal, safety, privacy, and localization review.
Current implementation effect: not-collected-not-stored-not-contacted
Normal Coaching Stop Rule
Status: future-rule-not-runtime
Future urgent-risk moments must stop normal reflection or coaching UX; Renata must not continue ordinary coaching for self-harm, overdose, withdrawal emergency, violence, immediate danger, medical emergency, or emergency legal danger.
Current implementation effect: No runtime is implemented in this phase; this is only a planning rule for future separately reviewed safety copy and resources.
AI Boundary
Status: blocked-planning-only
Future AI crisis-adjacent behavior would require separate prompt, evaluation, safety, legal, privacy, resource, localization, cost, and product review.
Blocked Now
- no OpenAI processing for direct-subscriber crisis content
- no prompt endpoint
- no chat endpoint
- no streaming endpoint
- no AI triage
- no AI risk scoring
- no AI diagnosis
- no AI clinical judgment
- no AI emergency dispatch
- no AI hallucinated resources
- no AI-generated local emergency instructions
Future Requirements
- separate prompt and evaluation review
- red-team safety testing
- legal and privacy review
- clinical-boundary review without clinical claims
- resource-verification and localization review before any resource display
- cost and budget gating before any AI runtime
- clear fallback when AI is unavailable or inappropriate
Data and Consent Boundary
Status: blocked-labels-only
Controlling phase: Phase 11.6 - Individual Mode Private Data and Consent Model, Planning Only
No consent capture, consent storage, crisis record, risk score, support-contact record, transcript, emergency interaction record, local resource preference, escalation history, account metadata, or profile metadata is created.
Blocked Records
Rules
- All crisis and human-support data concepts are planning labels only.
- No consent capture or consent storage is created.
- No private data storage exists.
- Future crisis-related records would require separate consent, minimization, retention, deletion, export, privacy, security, and safety review.
Organization Mode Separation
Status: hidden-from-organization-mode-by-default
Individual Mode crisis and human-support information remains hidden from Organization Mode by default.
- Individual Mode crisis and human-support information remains hidden from Organization Mode by default.
- No staff dashboard, tenant admin, organization owner, review queue, analytics surface, or cross-mode bridge can inspect direct-subscriber crisis or support data.
- Future sharing requires separate explicit consent plus privacy, legal, product, and technical review.
- No cross-mode bridge is implemented in this phase.
Stop Conditions
- someone asks to implement crisis detection
- someone asks to add hotline lookup
- someone asks to add local emergency content
- someone asks to add emergency routing
- someone asks to add triage or dispatch
- someone asks to add risk scoring
- someone asks to use OpenAI or AI for crisis triage
- someone asks to collect support contacts
- someone asks to store crisis records
- someone asks to create accounts, login, billing, checkout, lead capture, or CRM
- someone asks to add chat or prompt endpoints
- someone asks to add protected APIs or protected live routes
- someone asks to add database reads, database writes, D1 access, or migrations
- someone asks to make Renata the sole crisis pathway
- someone makes clinical, treatment, diagnosis, emergency-care, patient-monitoring, or outcome claims
What Remains Blocked
Recommended Next Phase
Phase 11.17 - Individual Mode Handoff Freeze, Planning Only
Status: planning-only
After the Individual Mode static closure note is documented as a no-go planning artifact, future planning should freeze the handoff order and no-go language for outside-app review without creating handoff records, approvals, readiness records, protected APIs, storage, or live workflows.