Agentic AI Design Patterns

Agentic AI design patterns are the building blocks of AI systems that act — systems where the LLM is not the product but the engine of a decision loop. These are the patterns you reach for when you stop asking "what should the model output?" and start asking "what should the agent do next, with which tool, under whose authority, on what budget?".

The selection below is biased toward production: the augmented-LLM primitive (model + retrieval + tools + memory), the loops that wrap it (ReAct, plan-and-execute), the orchestration shapes that scale it (supervisor, orchestrator-workers), the retrieval shape that grounds it (agentic RAG), and the governance shapes that keep it accountable (decision log, step budget, sandbox isolation). Together they answer "what does an agentic AI system actually look like once you ship it?".

Each pattern is decomposed GoF-style: intent, context, problem, forces, therefore, solution, consequences (benefits + liabilities), constrains (the hard prohibition that holds the pattern together under a powerful generator), and related[] — typed edges to other patterns. See the related guides below for adjacent framings — architecture, agentic design patterns more broadly, multi-agent coordination, RAG, and safety.

Field-tested patterns to start with

• 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.
• 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.
• 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.
• Orchestrator-Workers — An orchestrator dynamically breaks a task into subtasks at runtime and delegates each to a worker LLM, then synthesises results.
• 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.
• Sandbox Isolation — Run agent-emitted code or actions in a contained environment with restricted filesystem, network, and process privileges.
• Approval Queue — Queue agent-proposed actions for asynchronous human review while the agent continues other work.
• Reflection — Have the model review its own output and produce a revised version in one or more passes.

Recommended reading

• Planning & Control Flow — 40 patterns
• Tool Use & Environment — 34 patterns
• Retrieval & RAG — 17 patterns
• Governance & Observability — 27 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…
• 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…