Control & Govern
Govern agent activity across your deployment. Set guardrails and spend limits, contain a misbehaving agent with the kill switch, and control who can do what with roles and permissions.
Understand how guardrails work, create them, review blocked requests, and look up the available policies.
Cut a misbehaving agent off from its LLM providers, MCP servers, and other agents, yourself or with a policy.
Read LLM spend against the previous period, break it down by agent, model, provider, user, or tag, and export the report as CSV.
Cap LLM spend with per-agent budgets, and see what the Agentic Data Plane records automatically and where to view it.
Label Agentic Data Plane resources with key/value tags so access policies, spend reports, and list filters can act on a whole team or environment.
Group LLM spend by the tags you set on agents, so you can attribute cost to a department, team, or environment for chargeback and reporting.
Store API keys, tokens, and certificates in the Agentic Data Plane secret store, then rotate or delete them without exposing their values.
Control who can do what in the Agentic Data Plane with access policies.
