Agent infrastructure, security, and operations.

• ML inference architecture Serving paths, memory, scheduling, and the limits that decide whether a request meets its objective.
• Agent infrastructure Identity, control, and the path an agent takes in production.
• Observability What the system did, from traces and operator evidence.
• Policy enforcement What an agent may reach, and the boundary around that reach.
• Open and local models Models you can run, inspect, and serve yourself.
• Networking and security Paths, failure surfaces, and the controls that keep the rest dependable.