How to Prompt.

You will learn how current frontier models follow instructions, and the five fixes that turn vague prompts into precise ones. End state is a rewritten version of your own worst prompt, tested side by side against the original. After this module you can scope outputs explicitly, cap length and format, use positive instructions and action verbs, and know when to ask for extra reasoning and when to turn the reasoning control instead.

• Anthropic, "Prompt engineering overview", the techniques that hold across every current model: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/overview
• Anthropic, "Prompting Claude Opus 5", the source for the response-length reversal and for leaving self-verification to the model: https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/prompting-claude-opus-5
• Claude Help Center, "Change the model effort and thinking settings", where the effort lever lives in claude.ai and what each level costs you: https://support.claude.com/en/articles/8664678-change-the-model-effort-and-thinking-settings
• Anthropic's interactive prompt engineering tutorial (9 chapters, exercises, also as Google Sheets for non-coders): https://github.com/anthropics/prompt-eng-interactive-tutorial
• Gemini Apps Help, "Use Gemini Apps", where the model picker lives in the Gemini app and what each model is for: https://support.google.com/gemini/answer/13275745
• Google, "Gemini thinking", the thinking_level control in the Gemini API and its dynamic default: https://ai.google.dev/gemini-api/docs/thinking
• OpenAI Help Center, "Model Release Notes", the model picker, the Thinking models and the thinking level toggle in ChatGPT: https://help.openai.com/en/articles/9624314-model-release-notes
• OpenAI, "Prompt engineering", including why reasoning models want high-level guidance rather than step-by-step instructions: https://developers.openai.com/api/docs/guides/prompt-engineering
• Microsoft Support, "Conversation modes in Microsoft Copilot", Quick response and Think Deeper in the consumer Copilot app: https://support.microsoft.com/en-us/microsoft-copilot/conversation-modes-in-microsoft-copilot
• Microsoft Support, "Get started with Researcher in Microsoft 365 Copilot", the deeper-reasoning route in Microsoft 365 Copilot and its licence requirement: https://support.microsoft.com/en-us/microsoft-365-copilot/get-started-with-researcher-in-microsoft-365-copilot
• Ruben Hassid, "Prompt 4.7": https://ruben.substack.com/p/prompt-47
• For participants who want to go deeper: module 18, Prompt Engineering Deep Dive