← All notes

Architecture patterns: from RAG to agent teams

How the four core patterns relate, and when to reach for each one.

A ladder of patterns

Each pattern adds one capability to the previous one:

PatternAddsUse when
RAGGrounding via one retrievalAnswers must cite a known knowledge base
Agentic RAGA reasoning loop around retrievalQuestions are vague, multi-part, or need retries
Multi-AgentRole specialisation + handoffsA task has distinct stages (research → analyse → write)
Agent TeamsA supervisor that routes & mergesMultiple task types need different specialists

RAG: retrieve-then-read

The baseline. Retrieve top-k chunks, put them in the prompt, generate. Cheap, reliable, and the right default for most “answer from our docs” problems.

Agentic RAG: judge and retry

Wrap retrieval in a loop: grade relevance, rewrite the query, retrieve again. Costs more calls but rescues hard queries. Always cap the loop iterations.

Multi-agent: specialise the work

Split into focused roles with narrow prompts. Easier to test and debug because the trace shows exactly which agent produced which output.

Agent teams: orchestrate

A supervisor routes each request to the right team and reviews the result. This is how you scale to many task types without one mega-prompt. Keep the router simple and let teams encapsulate their own internal agents.

Choosing well

Start at the bottom of the ladder. Only climb when a concrete limitation forces you to — every rung adds latency, cost, and failure modes. The best architecture is the simplest one that works.