Agentic Patterns

Where the other guides on this site focus on a single angle (the agent loop, multi-agent coordination, RAG, safety), "agentic patterns" is the umbrella term for the whole vocabulary. A pattern is agentic when it presupposes that the system itself decides what to do next; the catalog collects every such decision-shape and arranges it as a language.

The language is organised as Alexander-style books — one per concern: reasoning, planning and control flow, tool use and environment, retrieval, verification and reflection, multi-agent coordination, routing and composition, safety and control, governance and observability. The selection below is one canonical pattern from each book, so this page reads as a map of the language rather than a re-list of agent-loop primitives. Open the dedicated guides for depth.

Every pattern is GoF-decomposed: intent, context, problem, forces, therefore, solution, consequences (benefits + liabilities), constrains (the hard prohibition), related[]. The constrains slot is the agentic-era addition; it is what keeps a pattern named in the presence of a generator that can argue its way around any rule of thumb.

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.
• Tool Use — Let the LLM produce typed calls against an external toolkit instead of producing free-form text the surrounding system has to parse.
• Agentic RAG — Replace static retrieve-then-generate with autonomous agents that plan, choose sources, retrieve iteratively, reflect, and re-query.
• 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.
• 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.
• 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
• Verification & Reflection — 27 patterns
• Multi-Agent — 44 patterns
• Routing & Composition — 21 patterns
• Safety & Control — 48 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 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)…
• 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 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…