Trust portal
Sign in
04Trust portal
Last reviewed 12 June 2026

AI posture

Where Limena's AI features run, what data they see, and how the boundary is enforced.

Provider

Limena’s AI features route through Anthropic Claude by default. Tenants choose where inference runs:

Provider tiers
managed_tier
Anthropic Claude, hosted APIRuns on Limena Labs Ltd’s commercial Anthropic account ("Limena AI").
bring_your_own_key
OpenAI, Azure OpenAI, any LiteLLM-compatible provider
self_hosted
your own Ollama server

Independently of the inference tier above, Limena’s semantic-search and record-similarity features send short text snippets from your records to OpenAI’s Embeddings API (United States) to generate vectors. This applies to every tenant. It is a distinct capability from chat and draft generation, and does not depend on your chosen inference tier. Per OpenAI’s API terms, these inputs are not used to train their models.

What’s sent

Only content the tenant explicitly enters into the product (outreach drafts, contact metadata, message bodies, and the analytics questions they type) is sent to the AI provider. Limena does not transmit credentials, billing info, audit logs, or other tenants’ data.

Training

Anthropic’s API Commercial Terms commit to not training their models on inputs sent via the API. Limena does not retain prompts or responses beyond what’s needed for debugging and audit (every AI call writes a structured row to ai_usage_logs; payload content is not stored).

Residency

Limena AI defaults to Anthropic’s US infrastructure. EU-only data residency is available on request via AWS Bedrock EU; see hello@limena.io.

Controls

  • Tenant admins can switch off AI features for their tenant from Settings → AI at any time.
  • Per-tenant monthly token ceiling and hourly velocity cap protect against runaway agent loops and leaked API keys. Tripping either pauses AI for the tenant; the in-app banner explains the state and points to support.
  • Limena platform admins can disable a tenant’s AI access (one-flag kill-switch) from the operator dashboard.
  • Every AI call writes an attributable row to ai_usage_logs: tenant, user (if logged in), model, token counts, latency. Available to the tenant via the audit-log export in Settings → Audit log.