Security

Every agent and workflow on the platform emits a stream of security-relevant audit events — tool executions, network egress decisions, LLM calls, guardrail checks, and quota denials. In the console this area is called Governance: it is where you read that stream, define the policies that produce the denials, watch enforcement trends, and manage token spend budgets.

The model is layered:

• Events are the raw, per-invocation record of what agents did and what the platform allowed, blocked, or masked.
• Policies come in two kinds, side by side under Governance → Policies:
  • Security policies (org-level and workspace-level) define what is denied, what is allowed, which guardrails are required, and the numeric ceilings agents run under. Publishing a policy propagates it to running agents.
  • Compliance policies govern individual tool calls by their argument values: allow, defer for human approval, or deny — an org-wide baseline plus optional per-agent tightening, enforced by the platform's policy decision point (PDP).
• Approvals is each user's personal queue of tool calls that a compliance rule parked for their sign-off, plus the consent prompts agents raise when they need a user to connect their own account.
• Posture rolls the event stream up into enforcement trends: block rates, the rules doing the work, quota hits, and policy rules that never fire.
• Usage and quotas track token spend and executions, and let org admins set windowed token budgets that gate agent invocations before they start.

The Governance area also hosts the Tool Registry — the org-scoped catalog of admitted tools that skills are allowed to reference; unregistered tool references are rejected when a skill is saved and when an agent builds.

Section map