The idea behind Out of the Box in 30 is simple: - Open a new AI tool - Give myself 30 minutes - No Training - No Prep Now let's see if I can create a YouTube short with Astra before I really know what I am doing. Version 1 — Terrible I gave it content from a post and no instructions, except create a short. It produced a very rough AI explainer. Watch: https://youtube.com/shorts/f4fIMgPkQ0w?si=qVaYnBJ3pwY0aExM Version 2 (Terrible +): I added direction to fit 9:16 short ratio. Better, but still way too pedestrian and not engaging at all. Watch: https://youtube.com/shorts/tMrDUy4QzOs?si=SwChr-lnxlbdiZj9 Version 3 (Better) This was where it started feeling more professional. I simply ask it to make it more immersive. Keep in mind this took 15 minute and a few clarifying prompts. Watch: https://youtu.be/090tGPEnGjk?si=sSJ3hkkUpgGPGbx7 Version 4 (Best) 25 minutes into this session and I ask Astra to switch the character to my image (uploaded 3 pictures) and add the AI Bits and Pieces logo. Watch: https://youtube.com/shorts/4zh7sd4UqEw?si=FRYPvDEZ6GgRU47U What do you think? Not bad for 30 minutes from first click to first solid draft. Next step, we will add music, animation in Out of the Box in 60.

McKinsey’s State of AI 2026 includes a statistic that should get our attention: 🛠️ 32% of respondents said their organizations decided against purchasing at least one software product or feature because they could build it internally using agentic coding tools. That is not a prediction. It is already happening. But here is an interesting question: Do you think these solutions are being built by formal IT departments—or by front-office professionals who understand the business problems? You may be surprised by the answer. Until recently, building software required a development team, significant capital, and months—or even years—of work. Agentic coding tools are changing that equation for both IT and the front office professional. For those of us in AI Bits & Pieces who are progressing beyond AI Enthusiast and are interested in becoming an AI Builder, learning this skill creates a significant career opportunity. Becoming a builder does not necessarily mean becoming a traditional software developer. It means learning how to use AI to: 🔹 Turn an idea into a working tool 🔹 Automate a business process 🔹 Connect systems and data 🔹 Build functionality a business might otherwise purchase 🔹 Solve a real problem and create measurable value These capabilities can help you advance your career, create new opportunities within your business, or begin building solutions for clients. The tools are lowering the technical barrier. What still matters is your ability to understand the problem, determine what should be built, and guide the solution toward a meaningful outcome. If you are interested in taking that next step, I invite you to be my special guest at the next AI for Life Weekly Live Session. 📣If you are interested in being one of my special guests at the next live session, comment “AI for Life” below or send me a direct message here in Skool: @Michael Wacht AI for Life is a community founded by @Matthew Sutherland on the Skool platform where I continue to hone my own low-code/no-code AI-building skills alongside others who are learning to build practical, real-world solutions to advance their career.

Microsoft Copilot can be one of the easiest ways to start using AI in your everyday work because it connects to tools many people already use. Email. Calendar. Documents. Presentations. Spreadsheets. Meetings. Chats. You do not have to learn everything at once. The best way to learn Copilot is one small workflow at a time. That is what this series is designed to do. We will start with the basics, then move into practical examples inside Microsoft 365: 💡 Part 1: Start With the Basics Get oriented and understand where Copilot shows up. 💬 Part 2: Copilot Chat Use Copilot Chat as a starting point for simple work questions and task organization. ✉️ Part 3: Improve Email Writing Use Copilot to make emails clearer, shorter, more professional, and easier to act on. 📬 Part 4: Outlook Email Triage Review recent email and organize what needs attention. 📅 Part 5: Calendar and Meeting Prep Review the day ahead and identify the top items that need attention. 📝 Part 6: Word — Draft and Improve a Document Turn rough notes into a clearer document. 📊 Part 7: PowerPoint — Create a First Draft Turn notes or a memo into a simple slide outline. 📈 Part 8: Excel — Ask Questions About Data Ask Copilot to identify patterns, issues, and questions in a table. 🔐 Bonus / Practitioner Lesson: Work Context and Permissions Understand what Copilot can access, what it cannot, and why your experience may differ from someone else’s. Your screen may not look exactly like someone else’s. That is normal. Copilot access can vary based on your Microsoft plan, license, workplace settings, and permissions. But the learning path is the same: - Start simple. - Practice one workflow. - Review the output. - Build from there. This is not about becoming a Copilot expert overnight. It is about learning how to use Copilot for real work, one practical step at a time.

In Part 2, we looked at the range of model capability. Now let’s make it practical. After more than 100 hours of testing, I have developed a fairly simple approach. I choose the product, model, and reasoning setting based on the type of work I am doing (not cost - yet). 🧠 Heavy Logic, Planning and Structure, for work such as: - Business proposals - Strategic frameworks - Complex planning - Coding - Difficult analysis - Multi-step problem solving - Assignments where maintaining context is critical - Consistency of theme or storyline For these applications, I want stronger reasoning, even if it takes longer. Product: ChatGPT Model: GPT-5.6 Sol Setting: High reasoning and for my book editor skill, Pro. Product: Claude Model: Claude Opus 5 Setting: High effort, with extended thinking when needed For these assignments, creativity in the delivery is secondary. My priorities are logic, structure, context integrity, planning, and getting the framework right. I rarely go higher, but keep in mind, most of what I do is front office business execution: strategy, project management, process refinement, education and training, and Cowork automation. I use Fable 5 rarely. I am not primarily using Claude to build sophisticated production applications. ✍️ Writing and Everyday Communication, for: - Blog posts - Creative writing - Emails - Business communication - Social posts - Editing and rewriting I usually want a capable model that leaves a little more room for creativity and variation. Product: Claude Model: Claude Sonnet 5 Setting: Standard/default effort Product: ChatGPT Model: GPT-5.5 Instant Setting: Instant I still use GPT-5.5 for this type of work while it remains available to me. The Interesting Exception: Image Creation Image creation breaks my normal rule. Why? I need the LLM to understand: - What I am trying to communicate - The audience - Composition and hierarchy - Style and mood - The creative objective So I need reasoning. But I also want the system to have enough freedom to interpret the brief creatively.

In Part 4, we talked about dialing model capability up or down. 📌 Now let’s practice it. My shorthand is: Find the floor, then move back up one level. That means you reduce the reasoning or effort level until you can see the model starting to miss the mark. Then you move back up to the lowest setting that still produces the quality you need. That gives you a practical balance between: - Output quality - Speed - Cost - Available usage or capacity - The amount of correction you have to do yourself Practice This: - Choose an assignment you already understand well. - Do not use something completely unfamiliar. - You need to be able to recognize when the output gets weaker. Good practice assignments include: - A business proposal - A project plan - An app framework - A book chapter outline - A training lesson - A process improvement plan ✅Step 1: - Use the model map from Part 3 to choose your product and model. - Start with the model you believe is appropriate for the work. ✅Step 2: - Run the assignment using a relatively high reasoning or effort setting. - Your goal is to create the first strong version of the plan, framework, proposal, or structure. - Save the result. This becomes your quality baseline. ✅Step 3: Once the main thinking is complete, reduce the reasoning or effort level one step. For example: High reasoning → Medium reasoning Or: High effort → Medium effort If the work is now very clear, and the product allows it, you can test reducing it two levels. ✅Step 4: Ask the model to continue the work. For example: - Expand one section - Rewrite part of the proposal - Create a summary - Draft an email from the plan - Turn the framework into a checklist - Create social posts from the article - Refine the tone - Format the output for easier reading This is where the test begins. You are no longer asking the model to do the hardest thinking from scratch. You are asking it to continue from an established structure.