Skip to slide
089 / 221

CH 07 · Retrieval: RAG vs Tools vs Long Context · 01/07

Read as one page

Retrieval: RAG vs Tools vs Long Context

Long context, RAG, and tool-based retrieval fetch facts with different cost and freshness trade-offs. Covers picking the right default.

7 slides · 4 min read

Contour map for Retrieval: RAG vs Tools vs Long Context

In this chapter

  1. 01The three strategies
  2. 02Why tools are often the right default for document agents
  3. 03When to add search (the hybrid)
  4. 04A decision guide
  5. 05Retrieval and the citation contract
  6. 06The bottom line

An agent is only as good as the information it can bring to bear. Getting the right facts in front of the model is the retrieval problem, and there are three broad strategies: stuff everything into a long context, retrieve relevant chunks (RAG), or let the model fetch what it needs through tools. This chapter compares them and explains when each wins, and why a tool-based approach is often the right default for document agents.

Finished this idea?

Your learning progress stays in this browser.