RAG where an agent decides what to retrieve, when, and from which source — instead of a single static query.
2 min readupdated 2026-06-21
/ quick answer
Agentic RAG combines retrieval with agent loops. The model plans sub-queries, picks data sources (vector store, SQL, web), critiques results, and re-queries until it has enough evidence to answer. It handles ambiguous questions that classic single-shot RAG fails on. RAG where an agent decides what to retrieve, when, and from which source — instead of a single static query.
RAG where an agent decides what to retrieve, when, and from which source — instead of a single static query. Agentic RAG combines retrieval with agent loops. The model plans sub-queries, picks data sources (vector store, SQL, web), critiques results, and re-queries until it has enough evidence to answer. It handles ambiguous questions that classic single-shot RAG fails on. In practice: A finance assistant gets 'why did revenue drop in Q2?', runs a SQL query for raw numbers, retrieves the relevant board notes from a vector store, then pulls a competitor news article from the web before composing the answer. This dictionary node is part of the Onexial knowledge graph and links to related concepts, workflows and tools below.
Definition
Agentic RAG combines retrieval with agent loops. The model plans sub-queries, picks data sources (vector store, SQL, web), critiques results, and re-queries until it has enough evidence to answer. It handles ambiguous questions that classic single-shot RAG fails on.
Example
A finance assistant gets 'why did revenue drop in Q2?', runs a SQL query for raw numbers, retrieves the relevant board notes from a vector store, then pulls a competitor news article from the web before composing the answer.
Agentic RAG combines retrieval with agent loops. The model plans sub-queries, picks data sources (vector store, SQL, web), critiques results, and re-queries until it has enough evidence to answer. It handles ambiguous questions that classic single-shot RAG fails on.
What is an example of Agentic RAG?
A finance assistant gets 'why did revenue drop in Q2?', runs a SQL query for raw numbers, retrieves the relevant board notes from a vector store, then pulls a competitor news article from the web before composing the answer.
Why does Agentic RAG matter for AI and automation?
RAG where an agent decides what to retrieve, when, and from which source — instead of a single static query. It connects to the workflows, prompts and tool stacks linked on this page, so you can move from definition to execution without leaving Onexial.