A built-in workspace feature in Claude.ai that lets you create separate conversation environments for different tasks or clients. Each Project has its own System Prompt, knowledge base, and team-shareable settings — upgrading one-off Claude conversations into persistent, frameworked, collaborative work infrastructure.

The total amount of information Claude can 'see' in a single conversation — including your messages, uploaded files, and all prior conversation turns. Once exceeded, the earliest content gets cut off.

Custom Instructions are fixed background descriptions you configure in Claude Projects, so Claude automatically knows your role, work context, preferences, and constraints at the start of every conversation in that Project — without you needing to re-explain each time.

Claude outputs incorrect, fabricated, or unverifiable information with high apparent confidence — like a very confident colleague giving you a wrong answer that feels completely reliable. In workplace contexts, the most dangerous aspect isn't Claude making obvious errors, but making errors confidently.

A Claude Projects feature that lets you upload documents for Claude to reference across all conversations in that Project. Store your company overview, terminology guide, brand guidelines, or quality examples — and Claude automatically draws on that context for everything you ask, giving it 'long-term memory' specific to your work context.

An MCP (Model Context Protocol) server is a standardized interface that lets Claude connect to external tools and services. Through MCP Servers, Claude can directly read Google Drive, operate Notion, query databases — turning AI conversations into workflows that actually execute tasks.

The maximum amount of text Claude can process in a single conversation. Once exceeded, earlier content is forgotten, causing Claude to 'lose memory' or stop responding coherently.