Topic
Tatsulok guides on this topic.

Chatting with your documents means uploading your files and asking questions in plain language. Tatsulok answers with citations to the exact source, privately.
Read the article
RAG (retrieval-augmented generation) lets AI search your internal documents and answer with citations to the exact source. Learn how private RAG and verification work.
Read the article
AI context is the background information, your documents, history, and instructions, that a model reads to produce relevant, accurate answers. Here is how it works.
Read the article
An AI context window is the maximum amount of text, measured in tokens, a model can consider at once. Here is what it means for working with long documents.
Read the article
Context engineering is the practice of curating everything an AI sees at answer time; RAG is one technique within it. Here is how they relate and when each matters.
Read the article
Shared AI context lets a team's AI answer from the same trusted documents, with every answer cited and access controlled. Here is how to set it up.
Read the article
AI forgets because each chat starts blank and only sees what fits its context window. The fix: give it persistent, retrievable, cited context from your own documents.
Read the article