Building & Product

What is RAG in AI?

RAG (retrieval-augmented generation) means the AI first looks up passages from a set of documents you choose and then answers from them, instead of relying only on its training. The term comes from a 2020 paper by Patrick Lewis and others. A RAG pipeline splits your documents into chunks, stores them in a search index (often a vector store), finds the chunks closest to each question and hands them to the model with the question. For a founder, it is how a support bot or internal assistant answers from your current policies and can cite them. Retrieval is where it fails: Anthropic found that adding context to each chunk cut failed retrievals by 49%, and by 67% with reranking.

Part of AI agents on eChai Explore.

On the AI map, 29 October 2026 Frontier models Open-weight models Decision models

Go deeper

6 resources.

Terms in this answer

Retrieval-Augmented Generation

More in AI in Your Product

Should my startup add AI features, and which ones actually matter to users? 21 → How do founders ship their first AI feature (APIs, wrappers, RAG in plain terms)? 21 → How much does it cost to run AI features, and how do I keep costs sane? 22 → Which AI model should I build on (GPT, Claude, Gemini, open-source), and how do I avoid locking myself in? 20 → How do I test whether my AI feature actually works before launch (evals, in plain terms)? 18 → How do I stop my AI feature from making things up in front of customers? 17 → Prompt engineering, RAG, or fine-tuning: which one does my product actually need? 18 → How do I design AI features people trust (chat vs buttons, streaming, showing the work)? 18 → What is my moat if I'm building on someone else's model? 19 → Should I put an AI agent in my product, or is a simple workflow enough? 20 → Is it safe to send customer data to AI APIs, and what about privacy laws like India's DPDP Act? 18 → How should I price AI features: per seat, per use, or per outcome? 20 → My AI feature is live. How do I monitor it and make it better with real usage? 18 → How do I get an API key for OpenAI or Gemini? 6 →

Also in Starting Up

The same ground, over in Build the product, our Starting Up track.

I'm non-technical, do I actually need a technical co-founder? 18 → I'm not a designer, how do I make my product not look terrible? 18 →
eChai Partner Brands The partnership →