Authorization scope
Each agent is scoped to the accounts, documents, and data it is authorized for. Role-based permissions and separation of duties are enforced inside the agent.
Home / Platform
Fiduciary Reasoning PlatformAgents at the core.
Controls in the loop.
r.Team is built with agents at the center — and fiduciary duty, ethics, compliance, cybersecurity, and advisory regulation are built into those agents, not wrapped around them.
Four gates, every proposal
This is the difference between an assistant with a compliance layer and a fiduciary agent. One is checked afterward. The other cannot reason any other way.
Reviewable objects
Agents produce proposals — a correction, a fee adjustment, an exception, a memo — never silent writes.
Evidence required
No proposal leaves without its evidence: governing document clause, fee schedule line, regulation, or prior decision.
The platform, as one map
Reasoning Engine
Shared context every agent reasons from: instruments, firm policies, regulation, prior decisions.
Agent Studio
Compose governed agents from the Action Catalog. Declare read, propose, and human-stop boundaries per action.
The Bridge
One auditable doorway to systems of record. Read first. Write only after human approval.
Trust Intelligence
Document intake and cited abstracts with human review gates. Abstracts cite — they do not conclude.
The Record
Per-account hash chain. Public fingerprint only; never a client file on the open web.
Natural Language Interface
Conversational layer over existing systems. No rip-and-replace. Same gates as every other agent.
Ontology Builder and Knowledge Graph encode the firm’s vocabulary so the Reasoning Engine can cite it. Legal intelligence is a capability of Trust Intelligence and the Engine — not a separate product.
Open platform on r.team →