What is the difference between RAG and agents, as Gaurav Sen explains it?

Gaurav Sen describes RAG as fetching context from a data store, usually a vector database, by matching the query's embedding to similar chunks and adding them to the prompt along a predefined path. An agent instead runs a loop, makes tool calls that act in the real world, and decides for itself when it has enough context. In RAG the LLM compiles an answer; in an agent it is the decision maker.

• Sen says RAG can only read, while an agent's tool calls are equivalent to performing actions.

▸In their words

“Here it's more like answer compiler. Here it's a decision maker.” Gaurav Sen · at 2:33 — open in the transcript →

Source: our own transcription of the episode. The full conversation is on Gaurav Sen (2026-08-21). Read the whole episode summary →

▸More from this episode