Security and privacy, in plain terms
Everything Kelu does to keep your knowledge, your users, and your compliance posture safe. Written as a checklist your security team can actually run through.
Data protection
- Workspace isolation across content, embeddings, and conversations
- Encryption in transit and at rest
- Optional PII masking of indexed content and of widget, API, and Ask questions, before any LLM call and before storage
- Zero-retention mode: per-workspace toggle — questions and answers stream and are dropped, never persisted
- Your data is never used to train models — ours or a third party's
- Delete a source and its indexed content is removed
Identity & access
- SSO via OIDC and SAML 2.0 on Enterprise
- Per-knowledge-base permissions for workspace members
- Restricted-document visibility within a knowledge base
- Client keys scoped per knowledge base, revocable instantly
- Allowed-groups enforcement on integration keys (can narrow, never widen access)
Auditability
- Workspace audit logs for admin actions
- Conversation history with citations preserved
- Traces record the question, answer, latency, and tokens behind every answer
- Signature verification on every webhook
AI safety
- Abstention gate refuses low-confidence questions rather than hallucinating
- Answers carry structured citations to their source documents
- Public surfaces retrieve only from public documents
- Bring-your-own-model (BYOK): answers run on your provider account under your DPA
Certifications and compliance
SOC 2 Type II
In progressVanta-managed. External audit scheduled; the corresponding trust portal will be linked here once live.
HIPAA BAA
Available on EnterpriseContact sales for the BAA and the corresponding technical controls checklist.
GDPR + Standard Contractual Clauses
Every planThe DPA is part of the Terms for every customer, with SCCs for data from the EEA, the UK and Switzerland. Enterprise customers can request a countersigned copy. Data is stored in the United States.
The short answers
Is my content used to train AI models?
No. Indexed content, embeddings, and conversations stay isolated to your workspace and are used only to answer your own questions. Nothing is shared across customers or used to train any model — ours or a third party's. This is contractual on paid plans and technical on every plan.
How is PII handled?
When you switch it on for a knowledge base, PII (emails, phones, credit cards, IBANs, IP addresses, names after a title) is masked in indexed content before it is stored or embedded, and in widget, API, and Ask questions before chat or reranking sees them. Questions from bots, the form deflector, helpdesk automation, and MCP are not masked.
What is zero-retention mode?
A per-workspace toggle. Questions and answers stream to the caller in real time and are then dropped — no conversation row is created, no feedback can be attached. Retrieval still runs against your indexed content; the answer is still cited. Only the transcript is not persisted.
What data does the LLM provider see?
The retrieved chunks plus the user's question (PII-masked when masking is on). Providers we use run under zero-retention API terms (no training on inputs). With BYOK, answers run on your own provider account under your own agreement.
How do you handle SSO?
OIDC and SAML 2.0 on Enterprise. Members authenticate via your identity provider; per-knowledge-base permissions and restricted-document visibility apply on top.
Where is our data stored, and can we sign a DPA?
Data is stored in the United States. Our DPA is part of the Terms of Service for every customer, and for data from the EEA, the UK and Switzerland we use Standard Contractual Clauses. Enterprise customers can request a countersigned copy.
Bring this to your security review
Request the security whitepaper, DPA, and (once live) the SOC 2 report. Your legal and security teams can send us their questionnaire directly.