AI Agent Design Patterns

An AI agent is an LLM wrapped in a decision loop: observe, reason, act, repeat. AI agent design patterns name the parts of that loop and the recurring shapes around it — how to reason without runaway cost (ReAct, plan-and-execute, reflection), how to act on the world without losing accountability (tool use, agentic RAG, handoff), and how to keep the loop safe enough to ship (step budget, kill switch, human-in-the-loop).

These patterns are not framework features. They are commitments about behaviour that can be defended on specific grounds — and refused on specific grounds. The catalog decomposes each pattern in the manner of Christopher Alexander (1977) and the Gang of Four (1994), with the LLM-era constrains slot (the hard prohibition the agent must not violate) added so each pattern keeps its shape under a generator that can argue.

The selection below is a practical starter set for "how do I build an AI agent?". Open the related guides for adjacent framings: the broader agentic design pattern language, agentic AI architecture, multi-agent coordination, RAG, and the safety stack.

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.
• Tool Use — Let the LLM produce typed calls against an external toolkit instead of producing free-form text the surrounding system has to parse.
• 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.
• 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.
• Agentic RAG — Replace static retrieve-then-generate with autonomous agents that plan, choose sources, retrieve iteratively, reflect, and re-query.
• 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.
• Step Budget — Cap the number of tool calls or loop iterations the agent is allowed within a single request.
• Kill Switch — Provide an out-of-band control plane to halt running agent instances without redeploy.
• Human-in-the-Loop — Require explicit human approval at defined points before the agent performs an action.
• Decision Log — Persist the agent's reasoning trace alongside its actions so post-hoc review can explain why.

Recommended reading

• Reasoning — 17 patterns
• Planning & Control Flow — 40 patterns
• Tool Use & Environment — 34 patterns
• Retrieval & RAG — 17 patterns
• Safety & Control — 48 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,…
• 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…