Security.
How we protect your data.

Uploaded documents, exports and backups are stored in AWS ap-south-1 (Mumbai) with server-side encryption at rest (AES-256). All traffic is encrypted in transit with TLS 1.2 or later. LexVio staff do not read your documents — access is restricted to logged security or abuse investigations, or support you ask for, per our DPA. Audit logs are append-only, enforced by database triggers, and kept for at least seven years.

Every model vendor is reached through a gated client. An air-gapped deployment disables every external model vendor and all telemetry with one setting. User-supplied text is screened for prompt injection before any model sees it, on every vendor path. Each request carries input and output token caps, and each organisation has a daily AI-spend ceiling that stops further model calls when it is reached. Repeated prompt context is cached so the same document is not re-sent in full on every turn. Each Anthropic request is routed by task across Claude Haiku 4.5, Sonnet 5, Opus 5 and Fable 5.1; an organisation on zero-data-retention terms is served from Opus rather than Fable, because Fable requires 30-day retention. Under Anthropic's, OpenAI's and Google's API terms, your content is not used to train their models; we do not train models on your data without explicit consent.

Your organisation sets its own controls. Under Access Policies an admin can restrict sign-in to an IP allowlist, choose which platforms may be used (the web app, the phone app) and cap how long a session lasts from sign-in; every authenticated request is checked, and a change that would lock out the admin making it is refused. Multi-factor authentication is not offered today: a setting for it can be stored, but it is not enforced, and the console says so. Under AI Administration an admin can lower the model tier the organisation uses, switch individual AI features off, set a daily AI spend cap, and read the AI request history (request type, user, model and time, never the content); prompt-injection detections and blocked requests are recorded as a hash of the content, never the text.

Documents are filed by category, and the category decides what may happen to them. An identity document is never sent to an AI model, never embedded and never indexed for search. An admin can set a retention period per document category and for meeting audio; when it ends, the stored file is purged and the purge is recorded in the audit log. Dictated audio is transcribed and not stored. Client contacts reach the client portal only through a one-use link, valid for 15 minutes, sent to the address your firm holds for them; they see only what a live share grants, and a revoked share closes on their next request. Every portal read and write is audited. Credentials for your own email relay, SMS or WhatsApp account are stored encrypted and never returned in full.

DPDP Act 2023 aligned; independent assessment not yet completed. SOC 2: controls mapped and evidenced in-product, not yet audited. ISO 27001: not yet certified. Automated dependency and static-analysis scans run weekly; a third-party penetration test has not yet been performed. Current status on /trust; the full measures and sub-processor list are in the DPA.