Not a wrapper
UnderwriteKit is a workflow engine for underwriting ops, not a chat surface.
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.
Wrapper-proof features
- Orchestrator for long-running workflows, retries, and SLAs.
- Policy engine with approval gates and versioning.
- Evidence graph linking memo claims to documents.
- Structured output contracts with JSON schema validation.
- Immutable audit trail with chained hashes.
- Template library for memos and checklists by product.
- Exception taxonomy with standardized routing.
- Connector library for email, storage, and LOS export.
- Evaluation harness with golden files and regression tests.
- Permissioning, redaction, and retention controls by role.
The wrapper test
- What state is this packet in, and why?
- What evidence supports every memo claim?
- What happens automatically after 3 days of no response?