1.0
Batch work without hiding risk
Support leads can clear approval debt quickly while high-risk replies remain prominent and explicit.
- Risk filters
- Draft preview
- Rejection reasons
Home
Product
Approvals
A human review lane for risky drafts, send decisions, rejection reasons, and approval evidence.
Default
Human
Outbound replies wait for review unless policy allows otherwise.
Evidence
Attached
Risk, sources, and policy checks travel with each draft.
Audit
Prewrite
Decisions are recorded before execution.
2.0
Approval is not a vibe
Every approval is tied to a thread, policy result, actor, and executor-ready action proposal.
- Actor metadata
- Policy version
- Idempotency key
Operations
What this means in production.
These pages describe the product contract behind the UI, not a decorative brochure. Each surface should connect back to the same governed support loop.
Control boundary
High-risk work cannot be silently sent.
Operator workflow
Support moves through secure ingest, AI preparation, human approval, outbound execution, and audit evidence.
Configuration impact
Provider setup, project policies, knowledge trust, retention, and billing limits decide how this behaves for a real workspace.
Proof points
Designed for governed support, not hidden autonomy.
High-risk work cannot be silently sent.
Rejected drafts keep a reason.
Every decision lands in audit.
References
Official stack and legal references.
These external links point to provider documentation, privacy notices, data-processing terms, or platform terms that shape production operation.
Next