Module
Module 4 of 7Lesson 2 of 2~16 min

Judge when an orchestrator and subagents are warranted

Lesson 2 of the module "The agent loop" in the course "Design reliable agents and tool calling".

Take this lesson: your first course is freeSee the full syllabus

Lesson objective

By the end of this lesson, you will be able to judge whether a case warrants an orchestrator and subagents rather than a single agent, and write a subagent's delegation brief.

Where it fits

The agent loop

How does the agent move forward, when does it stop, and does it need several agents?

Lessons in this module

  1. Specify the loop and its stop conditions
  2. Judge when an orchestrator and subagents are warranted (this lesson)

What you will learn in the course

This lesson is part of the course Design reliable agents and tool calling

  • Decide, with explicit criteria, whether a use case calls for a single call, a workflow or an agent, and choose the right pattern.
  • Write tool cards the model uses well (name, description, parameters, return, errors, idempotency, risk level).
  • Specify an agent's loop (goal, context, stop conditions, budgets, error handling) and judge whether an orchestrator and subagents are warranted.
  • Place human approval points and an agent's permissions according to the blast radius of each action.
  • Identify prompt-injection paths through tool outputs and specify structural mitigations that do not rely on the prompt alone.
  • Specify the trace of a run and the evaluation of an agent (task success, trajectory, cost, latency, consistency over several trials).

Related courses