A graph model for making agent blast radius visible across runtimes, tools, actions, systems, policy boundaries, leases, and proof evidence.
AREG, short for Agent Runtime Exposure Graph, is the runtime security map behind OSuite.
Decision records are useful, but isolated records do not answer the question security leaders ask during rollout and incident review: if this agent goes wrong, where can the damage travel?
AREG connects agents, runtime lanes, tools, systems, actions, policy boundaries, approval leases, proof receipts, and closure events into one graph.
Agent protocols make runtime edges more visible: an MCP call, A2A handoff, ACP message, workflow event, or managed connector invocation can tell the graph how work moved. That is valuable evidence, but it is not the same as governance closure.
AREG treats protocol records as graph edges whose assurance depends on the surrounding control path. If a protocol lane lacks dissent preservation, human escalation, approval binding, proof receipts, or exception ownership, the graph should show that as an evidence gap rather than hiding it behind a green integration status.
| Node or edge | Product meaning |
|---|---|
| agent | The autonomous or semi-autonomous actor requesting work. |
| runtime lane | The place where action enters OSuite, such as hook, MCP, SDK, workflow, or gateway. |
| action | The canonical action object produced by CAVA. |
| target system | The repository, SaaS object, API, table, customer record, account, or endpoint affected. |
| boundary | Production, customer data, external communication, money, network, privilege, or policy boundary. |
| lease | The BAF Action Gate Lease that allows or rejects reuse. |
| proof receipt | The replayable evidence that closes the decision. |
Agent security is not only about whether one action was allowed. It is about exposure shape.
One agent may be harmless because it only reads internal drafts. Another may be dangerous because it can write to production, send external messages, and trigger downstream workflows. AREG makes that difference visible.
This lets OSuite answer practical questions:
CAVA gives OSuite a governable action. PCAA gives the action an authority model. BAF makes approval bounded. AREG shows how the governed action sits inside the customer's runtime environment.
The result is not another dashboard for curiosity. It is a map for readiness, blast radius, and incident evidence.
Customers experience AREG as the Agent Runtime Security page: runtime map, exposure vectors, top blast-radius agents, firewall lanes, readiness score, and evidence bundle paths.
Request enterprise access and send your first governed decision today.
