Security questionnaire
One-page answers for vendor review. Internal / Hypothetical.
How we're different
- We run the underwriting checklist end to end (doc chase to memo to exceptions).
- Policy-gated and human-approved at risk points. No silent automation.
- Evidence-first outputs with citations and an audit trail.
Trust rule: AI drafts, humans decide for sensitive outcomes.
Quick answers
Data handling
Files are stored encrypted at rest (illustrative) and access is role-based. Audit events are hash-chained.
AI usage
AI drafts memos; humans approve sensitive decisions. Outputs are validated and citation-bound.
Retention
Retention tiers are configurable and designed for audit-readiness (illustrative roadmap).
SSO & access
SSO is a roadmap item; MVP uses RBAC and least-privilege roles.
For full details, share the security packet.