Skip to content
Menu
Book a strategy call

AEC × AI glossary

What is retrieval-augmented generation (RAG)?

Also called: RAG

Definition

Retrieval-augmented generation (RAG) is a technique in which an AI system first searches a set of trusted documents for relevant passages and then uses them to write its answer, usually with references. RAG lets an AEC firm's assistant answer from its own specifications, standards and past projects instead of general internet knowledge.

By Published

Why does retrieval-augmented generation (RAG) matter for architects, engineers and contractors in India?

RAG lets an AEC firm's assistant answer from its own specifications, standards and past projects instead of general internet knowledge. Because answers point back to sources, reviewers can check them quickly.

What is an example of retrieval-augmented generation (RAG)?

A firm indexes its specification library so staff can ask which waterproofing system was used on past basements and see the source documents.

Where does CloudBrain come in?

Our custom AI tools and agents service helps architecture, engineering and construction firms put this into practice. See the related terms below, or browse the full AEC × AI glossary.

Related

Talk through your AI plans with an architect

Book a strategy call. We'll look at where AI can save your team time, what it will take, and what to leave alone.

Book a strategy callWhatsApp +91 98107 51856 (opens in a new tab)