Agentic Design Patterns

An agentic design pattern names a recurring shape for software in which an LLM does not just generate text but decides what to do next: choose a tool, revise a plan, hand off to a peer, ask for approval, stop. "Agentic" is the property of acting under self-direction toward a goal; a pattern in this catalog gives that property a defensible structure. Without named patterns, every agent is a one-off; with them, agents become comparable, composable, and reviewable.

This catalog decomposes agentic design patterns in the manner of Christopher Alexander (1977) and the Gang of Four (1994): intent, context, problem, forces, therefore, solution, consequences (benefits + liabilities), constrains (the hard prohibition the agent is not allowed to violate), and related[] — typed edges to other patterns. The constrains slot is the agentic-era addition; it is how a pattern keeps its shape in the presence of a generator that can talk itself out of almost anything.

The selection below leans into the "agentic" framing: how an agent reasons (ReAct, plan-and-execute, reflection), how it acts on the world (tool use, augmented-LLM, handoff), how multiple agents coordinate (supervisor, orchestrator-workers, subagent isolation), and how the system stays governable (step budget, decision log, agent-as-judge). Open the related guides below for adjacent angles — architecture, multi-agent, RAG, safety.

Field-tested patterns to start with

• ReAct — Interleave a single thought, a single tool call, and a single observation per step so the agent reasons over fresh evidence.
• Plan-and-Execute — Plan all the steps once with a strong model, then execute each step with a cheaper model under the plan.
• Reflection — Have the model review its own output and produce a revised version in one or more passes.
• Tool Use — Let the LLM produce typed calls against an external toolkit instead of producing free-form text the surrounding system has to parse.
• Augmented LLM — Build the foundational agent block as an LLM augmented with retrieval, tools, and memory that the model actively chooses to use, rather than a bare-model call.
• Supervisor — Place a coordinating agent above a set of specialised agents and route work to them.
• Orchestrator-Workers — An orchestrator dynamically breaks a task into subtasks at runtime and delegates each to a worker LLM, then synthesises results.
• Subagent Isolation — Run subagents in isolated workspaces so their writes do not collide and parallelism is safe.
• Handoff — Transfer the active conversation from one agent to another, carrying context across the switch.
• Decision Log — Persist the agent's reasoning trace alongside its actions so post-hoc review can explain why.
• Step Budget — Cap the number of tool calls or loop iterations the agent is allowed within a single request.
• Agent-as-a-Judge — Evaluate an agent's full trajectory (steps, tool calls, intermediate states) by another agent rather than scoring only the final output.

Recommended reading

• Planning & Control Flow — 40 patterns
• Tool Use & Environment — 34 patterns
• Multi-Agent — 44 patterns
• Verification & Reflection — 27 patterns
• Governance & Observability — 27 patterns

Or open the full contents for all 421 patterns in 14 books.

Related guides

• LLM Agent Design Patterns — A GoF-formal catalog of LLM agent design patterns: ReAct, tool use, plan-and-execute, reflection, step budget, and more. Each pattern decom…
• Agentic AI Design Patterns — Agentic AI design patterns for systems already in production — what to ship, what to observe, what to budget, what to gate. Augmented LLM,…
• AI Agent Design Patterns — How to build an AI agent: the named shapes you reach for during design and implementation — reasoning (ReAct, plan-and-execute, reflection)…
• Agent Design Patterns — Agent design patterns treat the agent loop as a software-engineering primitive: an observe→reason→act cycle wrapped in tools, memory, super…
• Agentic Patterns — A complete pattern language for agentic systems, organised in Alexander-style books across reasoning, planning, tool use, retrieval, verifi…
• Agentic AI Architecture — How to structure agentic AI: the architectural patterns that hold an LLM-powered system together. Supervisor, orchestrator-workers, augment…
• RAG Agent Patterns — Patterns for building retrieval-augmented generation agents: naive RAG, agentic RAG, hybrid search, cross-encoder reranking, contextual ret…
• Multi-Agent Patterns — Patterns for coordinating multiple LLM agents: supervisor, orchestrator-workers, handoff, debate, hierarchical agents, swarm, role assignme…
• AI Agent Safety Patterns — Safety patterns for LLM agents: step budget, kill switch, constitutional charter, approval queue, sandbox isolation, input/output guardrail…