| Agent Lifecycle Management |
Managing agent lifecycle on the platform via the operator — deploy, hibernate, wake, scale |
Jarek Cwiklik, Paolo Dettori |
| Agent Runtime |
Agent runtime, proxy |
Hai Huang, Ed Snible |
| Audit Trail |
Security audit trail — full record of autonomous agent actions for compliance |
Parul Singh |
| Authorization and Policy Management |
Scoped permissions with runtime policy enforcement that limit what an agent can do |
Rong Chang, Maia Iyer, Alan Cha, Hai Huang |
| Benchmarking |
Agent benchmarking and test infrastructure |
Kelly Abuelsaad |
| Guardrails |
Content safety and compliance policies for agents making autonomous decisions |
Evaline Ju |
| Identity Management (Keycloak) |
Identity and access management |
Alan Cha, Maia Iyer |
| Intent Based Access Control |
Intent based access control |
Hai Huang |
| MCP Gateway |
Unified front door for MCP servers — tool routing, auth, token exchange |
Hai Huang, Ed Snible |
| Network Security |
Secure network architecture and isolation between agents and external systems |
Hai Huang |
| Observability & Token Cost Management |
Tracing, token cost attribution, and auto-instrumentation |
Evaline Ju, Ilya Kolchinsky |
| Resiliency & Consistency |
Ensuring environment consistency and preventing corruption from agent actions, inconsistent states |
Sahil Suneja |
| Sandboxing |
Isolated execution environments for code dev, AI-generated code, and MCP tools |
Ladislav Smola |
| State Management |
State, context, and session management — persistent state so agents retain memory across restarts and sessions |
Maia Iyer, Evaline Ju, Alan Cha, Kelly Abuelsaad |
| Workload Identity and Security |
Zero-trust auth and identity management for agents, tools, and users — cryptographic workload identity via SPIFFE/SPIRE |
Mariusz Sabath, Maia Iyer, Alan Cha, Morgan Foster, Akram Ben Aissi |