> ## Documentation Index > Fetch the complete documentation index at: https://docs.tatara.app/llms.txt > Use this file to discover all available pages before exploring further. # Tatara documentation > A governed document store where your company keeps its business knowledge, and where agents read and write it over the Model Context Protocol. Tatara is a governed document store where your company keeps its business knowledge: how you position the product, what you charge, why a decision went the way it did, how a process runs. The AI agents you run in production read that knowledge instead of guessing. People and agents share the same brain. People read and write in the web app. Agents connect over the Model Context Protocol (MCP) and work the same documents through a set of tools. A document has to carry the structure that makes it findable later (where it lives, what it is, what it is about, what it links to) at the moment it is written, not in a cleanup pass afterwards. Brains written that way do not decay into folders of orphaned notes. Start with the quickstart to get an agent connected, or read the core concepts first if you would rather understand the model before you write anything. Go from nothing to an agent that can read and write your brain. Brains, documents, folders, links, tags, and the rules that hold them together. Add the MCP server to your client and authorize it. Boards, trackers, tables, and saved views over your documents. Writing, organizing, and searching your brain by hand. Install the skills that teach an agent to write correctly.