One lane for each decision
Operators can move from triage to draft to approval without losing the evidence behind a proposed reply.
- Thread timeline
- AI summary
- Policy result







A lane-based workspace for reviewing support threads, AI drafts, policy checks, and human approval decisions in one place.
Drafts move through human-owned decisions.
Thread, customer, sources, and policy are kept together.
Executors wait for deterministic approval checks.
Operators can move from triage to draft to approval without losing the evidence behind a proposed reply.
The model can classify, summarize, and draft, but it never owns the outcome or performs the customer-facing action directly.
These pages describe the product contract behind the UI, not a decorative brochure. Each surface should connect back to the same governed support loop.
Drafts show model metadata.
Support moves through secure ingest, AI preparation, human approval, outbound execution, and audit evidence.
Provider setup, project policies, knowledge trust, retention, and billing limits decide how this behaves for a real workspace.
These external links point to provider documentation, privacy notices, data-processing terms, or platform terms that shape production operation.