Retrieval-augmented generation RAG
Fetch the relevant documents first, paste them into the prompt, and the model answers from your data instead of its training.
RAG splits the job in two. Retrieval finds passages that fit the question, usually by comparing embeddings in a vector-database. Generation then gives those passages and the question to the model and asks for an answer based on them.
No training is needed, and that is the draw. Your documents can change every hour while the model stays the same, and answers can quote the passage they used, so you can check them.
When a RAG system fails, retrieval is usually the culprit. If the right passage never gets fetched, no prompt rescues the answer. Chunk size, how you split documents, and whether keyword search runs next to vector search all matter more than which model writes the final text.
Tagged
Where this comes up
Prompts, configs and tutorials in the library that touch this term.
- GuideUniversal
Turn a messy task into a prompt in five minutes
Most weak prompts come from a task nobody fully described. A five-step routine to fix that before you type, with a worked example.
- GuideUniversal
Summaries you can trust
A summary is a claim about a document, so it can be wrong in the same ways as any claim. Four habits keep it honest.
- GuideUniversal
Briefing a coding assistant: the first message
A coding assistant works from what you tell it and what it can see. Here is what to put in the first message so you spend less time correcting it.
- GuideUniversal
How to check what an AI tells you
A few checks that catch most wrong answers: which claims to verify, how to ask for sources, and why a confident tone tells you nothing.
- CheatsheetChatGPT
ChatGPT commands and keyboard shortcuts
The commands and shortcuts the interface never shows you, in one table. Mostly keyboard, mostly undocumented.
Tested on GPT-5 · May 2026
- GuideUniversal
How to write a prompt that actually works
A short checklist to run any prompt through before you send it: who, what, shape and what to leave out. Those four things separate a specific prompt…