Product · Live fleet steering
Steer active agent populations while they run.
Traditional guardrails and session termination either prevent execution before it starts or destroy context once something goes wrong. PRAE enables security operators to steer active agent populations in real time — fencing cohorts, mutating execution constraints, and changing what agents can do while they are running.
Change the constraint. Keep the execution.
-
01 · Active agent
Mid-session, doing its work: reading, calling tools, reaching data.
-
02 · PRAE runtime
prae-gate at the agent’s tool seam judges each call against the constraints in force.
-
03 · Steering decision
An operator fences a cohort and signs a new constraint with the operator key.
-
04 · Updated constraint
Each targeted agent’s gate verifies the signature and adopts it, with no restart.
-
05 · Next execution
The agent keeps running. Only what the new constraint denies or holds is stopped, and the intervention is on the record.
Govern → Enforce → Prove
In developmentStatus: in development, not yet production-ready. Live fleet steering is demonstrated today in PRAE’s local Command Center on a simulated population of Claude Code sessions: each session’s tool calls are judged by its own PRAE gate, and a steering constraint reaches each gate signed with the operator key, is adopted mid-session, and is sealed in that session’s name. Steering a live fleet, a hosted or multi-host control plane, and fleet steering over the Node / TypeScript SDK, the MCP Gateway or cloud runtimes are not built yet.
How it differs
-
Not policy enforcement
Policy enforcement determines what an agent is allowed to do. Live steering lets operators change those constraints while agents are already running.
-
Not session termination
Ending a session destroys its context. A steered agent keeps running with its context intact; stopping execution is a separate, deliberate action.
-
Not red teaming
Red teaming tests scenarios before deployment. Steering acts on live agents, during execution.