Stop Prompting, Start Briefing.

You will learn why maintained context files beat repeated prompting, and how to manage them with Obsidian. End state is your context folder open as a searchable, editable vault, attached to your assistant, with one permanent behaviour rule added and verified. After this module you can change your assistant's behaviour by editing a file once, search every past output, and run a daily update-the-brain, build-the-work loop.

• Claude Help Center, "Get started with Claude Cowork", the surface where files-as-context actually pays off: https://support.claude.com/en/articles/13345190-get-started-with-claude-cowork
• Claude Help Center, "Understanding Claude's personalization features", the built-in alternatives to writing your own context files, and where each stops: https://support.claude.com/en/articles/10185728-understanding-claude-s-personalization-features
• Anthropic, "Agent Skills overview", where a context file stops being enough and a skill starts, with the progressive-disclosure model behind it: https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview
• Gemini Apps Help, "Upload & analyze files in Gemini Apps", file, folder and Drive uploads and their limits: https://support.google.com/gemini/answer/14903178
• Gemini Apps Help, "Tips for creating custom Gems", knowledge files as a standing context folder for a Gem: https://support.google.com/gemini/answer/15235603
• OpenAI Help Center, "Projects in ChatGPT", project files, Google Drive folder links as sources, and project instructions: https://help.openai.com/en/articles/10169521-projects-in-chatgpt
• Microsoft Support, "How Microsoft 365 Copilot Notebooks works", the references-only grounding and the 300-file limit: https://support.microsoft.com/en-us/microsoft-365-copilot/how-microsoft-365-copilot-notebooks-works
• Ruben Hassid, "Prompting is the worst way to use Claude": https://ruben.substack.com/p/stop-prompting-claude