An O'Reilly Live Learning course teaching business professionals how to extract maximum value from AI tools like Microsoft 365 Copilot, ChatGPT, Claude, and Google Gemini.
Last updated: December 2025
| # | Segment | Duration | Key Topics |
|---|---|---|---|
| 1 | Core Prompting & Context Engineering | 50 min | CRAFT/CLEAR frameworks, context engineering stack, with/without context scenarios |
| 2 | Multimodal Prompting & AI-Assisted Coding | 50 min | Imagen 3, DALL-E 3, vision analysis, GitHub Copilot instruction files |
| 3 | AI Workspaces & Custom Assistants | 50 min | M365 Notebooks, ChatGPT Projects, Gemini Gems, Custom GPTs, M365 Agents |
| 4 | Agentic AI & Autonomous Coding | 50 min | Claude Code, GitHub Copilot Coding Agent, Copilot Studio, MCP |
- You are the pilot; the AI is your co-pilot. You're responsible for its actions.
- Always know who you're signed in as and who you're chatting with.
- The more you disclose about yourself in trust, the more the AI can help you.
- Anything you leave out of your prompt will be inferred by the AI.
- Role play like you're a director.
- Don't swallow the elephant—break down complex tasks with the AI.
- Surgically sculpt your context. Just because you can doesn't mean you should.
- Always have a trusted LLM to cross-reference responses.
- Strike while the iron's hot.
- Every AI chat has its own lifecycle; develop your "prompt smell."
- If you need to remind the AI of something, add it to custom instructions.
- Periodically refactor your custom instructions and memories.
- Think meta: Prompt about prompting and custom instructions.
- Use your voice if using your words is difficult.
- Pick up a good book on technical writing essentials.
- Protect your LLM against abuse by integrating test prompts.
- Each LLM (and vendor) has its own priorities and personality.
- Expect breaking changes. Stay agile, adaptable, and be an eternal learner.
| Prompt Engineering | Context Engineering |
|---|---|
| Focus on what to say | Focus on what the model knows |
| One-off interactions | System-wide reliability |
| Phrasing and examples | Everything in the context window |