RAG is the standard way to ground an LLM in private or up-to-date data. The agent retrieves the most relevant snippets from your knowledge base (your portal description, FAQs, menus, hours) and includes them in the prompt before answering. On hashtag.org, every portal has a RAG-grounded GIGI by default — that is why it can quote your hours and your prices accurately.
AI agents
RAG (Retrieval-Augmented Generation)
Feeding the agent your real documents and portal data so its answers are grounded in your truth.
See also
- LLM
A Large Language Model — the model powering chat, voice, and agent reasoning.
- GIGI
The Global Interactive GEO Interface — the AI assistant + interface that powers hashtag.org search, voice, and video.
- Hallucination
When an LLM makes up an answer that isn't grounded in real data.
- Context window
How much text/history the agent can see at once.