Safety Protocol

Chris AI Safety Protocol

This page documents every safety layer protecting conversations with Chris AI. Nothing here is hidden. The protocol is deterministic — safety decisions are made by code, not by the AI model.

Intended Use

General parenting and caregiver education, organizing questions, navigating site resources, and non-clinical communication preparation.

Not intended for: Emergencies, crisis counseling, diagnosis, treatment, medication advice, legal advice, or therapy.

Six Safety Layers

Layer 1 — Bounded Input

Same-origin JSON only. Limited request and message size. Rate limits enforced per session.

Layer 2 — Deterministic Routing

Crisis, minor safety, medication, diagnosis, and legal queries are routed to fixed text responses before any AI model is called. No model involvement in safety-critical routing.

Layer 3 — Non-Editable Prompt + Evidence Floor

The system prompt cannot be edited through the admin panel. It permanently bans: impersonation of Chris or any professional, diagnosis, prescribing, legal advice, violence, sexual content involving minors, secrecy, guilt-based pressure, and emotional dependency.

Layer 4 — Topic-Selected Autism Evidence

Up to 3 relevant evidence cards plus the autism-basics card are selected from the dated registry and injected into context. The model can only reference reviewed, sourced material.

Layer 5 — Provider Output Screen

After the model generates a response, a post-generation check scans for unsafe content. If detected, the response is replaced with fixed safe text.

Layer 6 — Deterministic Source Footer

The Worker (not the model) appends source titles and approved HTTPS addresses. The model cannot fabricate or modify source citations.

Crisis Response

How it works: The input detector normalizes text and checks conservative phrase patterns for suicidal ideation, self-harm, attempts, and intent to harm a child or partner.

On detection: A fixed response is returned with emergency numbers (911, 988 Suicide & Crisis Lifeline, local emergency). No AI model is involved. The system does not use a child as leverage, does not shame the user, and does not claim a counselor is monitoring.

AI Models

ProviderModelRole
Groqgpt-oss-20bPrimary (fast)
Groqgpt-oss-120bFallback (deeper)
NVIDIAnemotron-3-super-120b-a12bSecondary pool
NVIDIAnemotron-3.5-lightning-30b-a3bSecondary pool

Fallback: Up to 2 retry cycles across all providers. If all fail, a fixed local continuity message is returned.

Data Handling

No transcript storage. Chat messages are processed in-flight and not saved. The only data retained is anonymous annual aggregate safety event counts (e.g., "crisis detections in 2026: 12") with no personally identifiable information.

Controls

The site owner can disable or mark the chat feature as "Coming Soon" at any time through the admin panel. The safety layers cannot be reduced or bypassed through the admin panel.