Agents and Workflows
3 build exercises to practise the concepts in this domain.
1.1 — Draw the Boundary Before You Build
Intermediate
25 minutes
- How to place a task on the augmented LLM / workflow / agent taxonomy
- How to justify the placement from control-flow ownership and step predictability
- How to decompose an agent-shaped task into an orchestrator-workers design
- How to write a subagent delegation brief that survives context isolation
1.2 — Trip Every Limit on Purpose
Intermediate
30 minutes
- How max_turns and max_budget_usd bound an Agent SDK run
- How to read ResultMessage subtypes and recover by resuming a session
- How the budget cap contains subagent spend
- How a PreToolUse hook denies a tool call deterministically
1.3 — Profile Three Tasks, Pick Three Patterns
Intermediate
30 minutes
- How to write a requirement profile that determines a pattern choice
- How to implement a pattern as plain code before reaching for a framework
- How to wire the evaluator-optimizer loop with a hard round cap
- How to decide what working state must be persisted outside the window