Join us on Zoom Saturday, July 11, 2026 12:30 ET - 13:30 ET we’re opening the AI for Life + AI Bits and Pieces session to everyone, including people outside the community. Join instructions https://us06web.zoom.us/meetings/81545596982/invitations?signature=NQBPitO7KYhO4f7NHMddMYVn476zmP8rjoEmkdhIvzY Meeting ID: 815 4559 6982 Passcode: 050131 Hosts: - 𝗠𝗶𝗰𝗵𝗮𝗲𝗹 𝗪𝗮𝗰𝗵𝘁 from 𝗔𝗜 𝗕𝗶𝘁𝘀 𝗮𝗻𝗱 𝗣𝗶𝗲𝗰𝗲𝘀 𝗰𝗼𝗺𝗺𝘂𝗻𝗶𝘁𝘆. - 𝗠𝗮𝘁𝘁𝗵𝗲𝘄 𝗦𝘂𝘁𝗵𝗲𝗿𝗹𝗮𝗻𝗱 from 𝗔𝗶 𝗳𝗼𝗿 𝗟𝗶𝗳𝗲 𝗰𝗼𝗺𝗺𝘂𝗻𝗶𝘁𝘆. This will be guided questions plus an open forum for practical discussion around what is happening in AI right now, including: - The explosion of AIOS aka Second Brain - AI hot topics and trends - Design and development - Workflows and automation - Process improvement - Tooling, use cases, and real-world implementation Join us for an open working conversation with people who have been building, testing, learning, and applying AI and automations in practical ways. 𝗦𝘂𝗯𝗺𝗶𝘁 𝗾𝘂𝗲𝘀𝘁𝗶𝗼𝗻𝘀 𝗽𝗿𝗶𝗼𝗿 𝘁𝗼 𝘁𝗵𝗲 𝗲𝘃𝗲𝗻𝘁 𝗳𝗼𝗿 𝗰𝗼𝗻𝘀𝗶𝗱𝗲𝗿𝗮𝘁𝗶𝗼𝗻. We’ll kick things off with pre-submitted questions. Simply submit your question(s) in the comments below, or direct message me in Skool. ✨ Claude will pick the question order. And of course bring questions, examples, workflows, problems, tools, or ideas you want to discuss during the open forum. Hope to see our friends there: @Ron Nedd @Frank Priboy @Gina Wang @Debbie Ai @Pedro Gomez @Usman Mohammed @Nick Mohler @Mike AI Consultant @Diane McCracken @R S @Collin Thomas @Jacob Brodsky @Bradley Kerman @Md. Abdullah Al Mafi @Michele Wacht @Mark Zayec @John Romano @Josh Frison

This morning, I woke up feeling a little nervous. It wasn't because AI was going to read my inbox—it has been doing that for months. What made me uneasy was knowing that I was no longer going to be the reading it at all for three days. My inbox isn't just business. It's clients, prospects, personal email, financial information, family logistics, subscriptions, and everything in between. I also have a few active deals in progress, so missing the wrong email could have real consequences. Since I had fully committed to letting AI review my inbox first, I wanted to make sure the instructions were as clear and complete as possible, and that ChatGPT and I were on the same page. One thing I like about ChatGPT Scheduled Tasks is that I can prompt directly inside the email notification chat, which means it already has context, that makes it very easy to refine the instructions without starting from scratch. So, without reading my email, I asked a simple question: 💬 The Prompt: I would like to look my email every three days. How should we enhance the prompt? Or is it good? 🤖 ChatGPT’s Response: Your current prompt is good for twice-daily alerts, but if you only plan to personally check email every three days, I would strengthen it. The main enhancement is to make the AI act less like a “notification filter” and more like an email operations assistant with escalation judgment. Here is a stronger version: Review my recent email and notify me only when a message likely needs my attention before my next manual inbox review. I personally review my inbox every 72 hours, so prioritize anything that cannot safely wait three days. Flag emails involving: - Clients or prospects - Time-sensitive requests - Deadlines, renewals, billing, payments, payroll, contracts, or account/security issues - Anything from VIP senders - Messages that require a reply, approval, decision, review, or action Ignore by default: - Promotions - Spam - Newsletters - Automated notifications - Receipts or FYI-only updates, unless they involve money, account access, deadlines, or risk

Ok, I am getting lots of questions on the ChatGPT nutrition tracker, so I want to clarify the platform and intention of the series. First, I may have confused some members by using the word "dashboard". That’s on me. When I say dashboard, I do not mean I built a custom software app in Claude Code. I did not. It is just a prompt I use inside ChatGPT to create a daily graphic snapshot with the output I want to see. By using the word "dashboard", I confused some members, and understandably they thought I had built something more technical around it. I have not. However, I am tracking my daily nutrition in ChatGPT and sharing it for three very specific reasons: 1. To share how I am actually using ChatGPT to track my nutritional habits. 2. To help teach the practical capabilities and limitations of ChatGPT in a real-world use case, including projects, project instructions, context, memory, images, prompts, and daily workflows, and more. 3. And this is the big one for me. I want to personally experience how ChatGPT and LLM technology are improving over time, especially around context, memory, repeated use, and structured outputs. For me, the nutrition tracker is not just about counting calories. It is a practical way to interact with ChatGPT every day around something that matters to me personally. That daily interaction helps me build an intuitive feel for what works, what does not, where the model is improving, and where it still needs clear instructions and boundaries. So when I share this, I am not saying: > Look at this app I built. I am saying: > Here is a simple, practical way I am using ChatGPT in everyday life, and here is what it is teaching me about AI. That leads to the bigger question a member asked, which is a good one: "Do you log it each day? And how do you carry forward session context if you're using ChatGPT? That’s fantastic you're hitting your fitness goals!" Yes, I log it each day. And the way I carry context forward is by using a dedicated ChatGPT Project with specific instructions, repeated daily logging, and simple boundaries like DAY START and DAY LOCK.

When I started using ChatGPT as a nutrition and activity tracker, one of the first problems was not calories, macros, or activity estimates. It was boundaries. Where does one day begin? Where does one day end? That sounds obvious to a person. But ChatGPT is reading a stream of messages. It does not automatically know whether a food entry belongs to today, yesterday, an example, or a correction unless I make that clear. So I added two simple commands inside my Project Instructions: - DAY START - DAY LOCK These commands became the boundaries for the tracker. DAY START tells ChatGPT when a new tracking day begins. DAY LOCK tells ChatGPT when that tracking day is complete. That creates a clean container for the day’s food, activity, steps, workouts, and summaries. Without it, entries can blur together. A snack from last night. A workout from today. A correction from yesterday. A new meal logged after midnight. To a human, those may feel obvious. To an LLM, they need structure. DAY START begins a new tracking day. DAY LOCK finalizes the day. That matters because once a day is locked, I do not want the numbers drifting or changing later. No accidental edits. No mixing with the next day. No reinterpreting old entries. No rolling yesterday into today. The day is done. The AI Lesson: The real lesson is not about nutrition. It is about building reliable AI workflows. LLMs can answer questions, but workflows need boundaries. Together, they turn a loose conversation into a defined tracking period. That is the difference between chatting with AI and building a system. Add the entire section below to your Project Instruction: Daily Boundary Rules Use two commands to manage each tracking day: DAY START When I type DAY START, begin a new nutrition and activity tracking day. Everything logged after DAY START belongs to that day. Do not include food, activity, steps, workouts, or corrections from before DAY START unless I explicitly tell you to. DAY LOCK

In Part 1, we started with a simple experiment. I gave ChatGPT a basic food and activity log and asked: How did I do today? The answer was generic. Why? Because ChatGPT did not know enough about me. It did not know my: - Goal - BMR - Daily calorie target - Protein target It did not know what “good” meant for me. That was the first real lesson: - A generic chat produces generic answers. - The next step was creating better context memory using Projects. Step 1: Create a Dedicated Project Instead of starting a random new chat every day, I created a dedicated ChatGPT Project for nutrition and activity tracking. Why does this matter? Because a regular chat is just a conversation. A Project is more like a focused workspace. It gives ChatGPT a place to keep the work organized around a specific purpose. For this project, the purpose was simple: 🍽️ Track food 🚶 Track activity 🔥 Estimate calorie burn 📊 Summarize the day 🎯 Help me understand whether I am moving toward my goal To create the Project: 1. Click Projects 2. Click New Project 3. Name it Nutrition and Activity Tracker Step 2: Add Basic Project Instructions Next, I gave ChatGPT a few simple Project Instructions. Nothing complicated. Just enough context to make the answers more useful. Something like: You are my nutrition and activity tracking assistant.My goal is to lose body fat while maintaining muscle.My estimated BMR is 1,800 calories per day. When I enter food, estimate calories and macros.When I enter activity, estimate calories burned.When I ask for a summary, show food calories, protein, carbs, fat, activity burn, net calories, and whether the day is trending toward a calorie deficit. Keep summaries concise. That small set of Project Instructions changed the quality of the output because ChatGPT now had context. To add Project Instructions: 1. Open the Project 2. Click the three dots 3. Select Project settings 4. Add your instructions The Same Food Log Became More Useful