Search across all documentation pages
9 pages in this section.
Explore the agent loop's perceive, reason, act, and observe phases. Understand how these steps drive agent behavior and diagnose common failures.
Learn agent loop basics with Python examples. Explore perceive, reason, act, observe rhythms, tool calls, multi-step loops, and stop rules.
Learn how reasoning traces, like chain-of-thought, guide agent decisions. Understand their impact on quality, cost, and debuggability in AI systems.
Learn how to implement robust stopping conditions for agent loops, covering max turns, timeouts, cost budgets, and goal checks to prevent runaway agents and optimize
Understand how the context window dictates agent behavior. Learn to manage system rules, tools, and prior messages to control agent decisions.
Learn ten best practices for agent loops, covering control plane, decision quality, and operations to keep them bounded, observable, and predictable.