Agent Design Patterns

Step back from the AI hype and "agent" becomes a software primitive: a thing that observes, decides what to do next, acts, and remembers. Agent design patterns are what you write down once you accept that primitive and start designing around it — how the loop terminates, how a plan is revised when reality contradicts it, how state survives a crash, how a peer agent receives a half-finished task without re-doing it.

These patterns are deliberately about the *shape* of the loop, not the model that drives it. The same patterns held in earlier agent literature (BDI, RL, dialogue systems), and they hold now with augmented LLMs at the centre. The catalog inherits the GoF discipline: intent, context, problem, forces, therefore, solution, consequences, constrains, related[] — typed edges to other patterns.

The selection below is the agent-loop spine: ReAct (observe-think-act), plan-and-execute (separate planning from execution), augmented LLM (model + retrieval + tools + memory), reflection (self-critique), decision log (auditable trail), supervisor (a parent that can stop the child), handoff (transfer control), agent resumption (survive a crash). For adjacent framings see the related guides.

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.
• 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.
• Tool Use — Let the LLM produce typed calls against an external toolkit instead of producing free-form text the surrounding system has to parse.
• Reflection — Have the model review its own output and produce a revised version in one or more passes.
• Decision Log — Persist the agent's reasoning trace alongside its actions so post-hoc review can explain why.
• Supervisor — Place a coordinating agent above a set of specialised agents and route work to them.
• Handoff — Transfer the active conversation from one agent to another, carrying context across the switch.
• Agent Resumption — Persist agent execution state so a long-running run survives restarts, deploys, or user disconnects.
• 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.
• Subagent Isolation — Run subagents in isolated workspaces so their writes do not collide and parallelism is safe.
• Step Budget — Cap the number of tool calls or loop iterations the agent is allowed within a single request.

Recommended reading

• Planning & Control Flow — 40 patterns
• Tool Use & Environment — 34 patterns
• Multi-Agent — 44 patterns
• Verification & Reflection — 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 Design Patterns — A GoF-formal catalog of agentic design patterns — named, reusable shapes for building autonomous AI agents: agent loops, tool use, planning…
• 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)…
• 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…