When to Use Each Design Pattern

Match your use case characteristics to the right pattern before building.

Design Patterns Strategy

Pattern Selection by Use Case

Most enterprise agent implementations can be matched to one or two primary patterns based on the characteristics of the use case. Use this table as a starting point, then read the individual pattern pages for implementation guidance.

Data table
CharacteristicPrimary PatternSecondary Pattern
Sequential steps, dependent on each step's resultReActChain of Thought
Long-horizon task with a plannable sequencePlan-and-ExecuteHuman-in-the-Loop
High-stakes output that must be verifiedReflectionHuman-in-the-Loop
Multiple independent data lookups neededParallelizationReAct
Task spans multiple specialist domainsMulti-Agent CollaborationOrchestrator-Subagent
Single entry point for diverse request typesRouterMulti-Agent Collaboration
Agent needs context from past sessionsMemory-AugmentedReAct
Complex tool selection with many optionsTool UseRouter
Clear hierarchical task decompositionOrchestrator-SubagentPlan-and-Execute
Irreversible or high-value actionsHuman-in-the-LoopReflection
Complex reasoning with audit requirementsChain of ThoughtReflection

The Most Common Pattern Combination

The most common production enterprise agent combines three patterns: ReAct (the core reasoning loop), Tool Use (the MCP tool set design), and Human-in-the-Loop (approval gates for high-stakes actions). This combination covers the majority of enterprise use cases and is the right starting point for most implementations.

Put these cookbook patterns to work

Get started