Reference Architectures

Long-Running Agents

Long-Running Autonomous Agents execute complex tasks over extended periods that may span hours or days. These agents maintain persistent context and operate with limited supervision.

Architecture diagram

Agent (Persistent) ---> Task 1 (Hour 1) ---> Task 2 (Hour 3) ---> ...

A persistent agent executes a sequence of tasks over time. Context accumulates across tasks.

Characteristics

Long-Running Agents suit complex workflows that cannot complete within a single session. Session duration creates unique challenges including credential validity, context accumulation, and oversight across time periods.

Priority controls

ComponentPriority Controls
Session ManagementAZN-03, IDN-03, OBS-02
Context AccumulationOBS-05, INT-02, GOV-04
Long-Lived CredentialsIDN-03, IDN-04, AZN-05
Asynchronous InterventionINT-01, INT-02, INT-04

Typical certification profile

Long-Running Agent deployments typically certify at Elevated or Critical profiles. The extended exposure window warrants heightened controls.

Previous
Multi-tenant