Back to Home

Security Overview

Launch trust starts with an accurate posture

This page summarizes the current public security story for NeutralAI: what is live, what is suitable for evaluation, and what is still part of the production-hardening path.

Gateway boundary

NeutralAI applies masking policies to supported AI requests between customer applications and external model providers.

Operational checks

The live runtime exposes health and readiness endpoints to support smoke tests, deployment checks, and simple launch monitoring.

Data handling posture

Reversible mappings are encrypted and retained for a limited period, controlled by the configured retention policy.

Production hardening

Discuss evidence retention, enforcement requirements, and deployment scope with us before your production rollout.

Technical controls

Mask first, then route the sanitized request

NeutralAI adds a policy gateway before external model providers so sensitive values can be detected, tokenized, and audited before prompt egress.

Walk through the full flow
01
Client app or browser extension
02
NeutralAI policy and masking gateway
03
Sanitized request to external LLM provider

Encryption and token vault

Sensitive values can be replaced with reversible tokens backed by an AES-256-GCM vault, then restored only through governed paths.

Detection pipeline

Detection combines Presidio NER, pattern matching, semantic validation with Qdrant, and configurable confidence thresholds.

Entity coverage

Coverage includes EMAIL, PHONE, PERSON, CREDIT_CARD, IBAN, SSN, TR_ID, UK_NHS, IP_ADDRESS, and tenant-specific rules.

Governed restore path

Reversible masking is separated from normal model traffic so restored values can remain behind explicit authorization and audit controls.

Data Flow

How a prompt is sanitized before it leaves.

The gateway processes supported outbound prompts, runs multi-stage PII detection, tokenizes detected entities into the encrypted vault, and forwards the permitted request with detected identifiers replaced.

Prompt egress — outbound data-flow

Prompt Egress Data-Flow DiagramA data-flow diagram showing how a user prompt passes through the NeutralAI Gateway. The flow is: User / Client sends a prompt to the Gateway; within the gateway boundary, Presidio NER and pattern matching detect PII entities; detected entities are masked or tokenized and the tokens are stored in an AES-256-GCM encrypted Token Vault with a TTL; an immutable Audit Trail records detection metadata; and the permitted prompt is forwarded to the external LLM Provider with detected identifiers replaced.NEUTRALAI GATEWAY BOUNDARY — DETECTED IDENTIFIERS REPLACED BEFORE EGRESSUser / ClientApp or extensionpromptDetectPresidio NER+ Pattern matchMask / TokenizeAES-256-GCM vaultReversible tokensanitized onlyLLM ProviderOpenRouter / BYOK🔐Token VaultAES-256-GCM encryptedTenant-bound · TTL 15 minGoverned restore path onlystore token📋Audit TrailDetection eventsEntity types loggedImmutable append-onlylog event🚫Detected PIIcontrolled restorationmasked before egresstime-limited mappingsMain flowToken storeAudit eventGateway boundaryFig 1 — NeutralAI prompt egress: detected identifiers are tokenized before LLM forwarding.

See the full ingress unmask path and token vault lifecycle on the Trust Center.

Readiness snapshot

Current public position

  • Public endpoints are live behind TLS on api.neutralai.co.uk.
  • Docker-based deployment and reverse proxy setup are already in place.
  • Review the security pack for current controls, audit status, and available evidence.
  • Confirm storage requirements and security review scope before production use.

Useful links

Validate or get in touch

Public health endpointPublic readiness endpointPublic security.txtSecurity mailbox
Production discussions should include the immutable storage milestone and any customer-specific evidence requirements.