Different teams ask different questions of different documents. Marella’s configuration layer
makes that explicit:
- Agents — assistants configured for a job: a contract reviewer for legal, a policy
assistant for operations. Each answers only from the document sets it is scoped to.
- Skills — reusable capabilities agents draw on, so improvements propagate rather than
being rebuilt per team.
- Templates — consistent output shapes for repeatable work: summaries, clause tables,
briefs in your house format.
Administrators configure all three centrally, and agent activity lands in the audit trail like
everything else.
