🏈 My friend @Herman Moore called me, former NFL wide receiver, Detroit Lions. "I'm speaking tomorrow to 125 small business owners. Want to join me and talk about AI?" One day's notice. I built one slide with five points. My strategy, let the room decide which ones we went deep on based on body language and reaction. No fixed script, just reading the energy and following it. Herman worked that stage right alongside me. Great public speaker, no surprise there given his career. We had an easy back-and-forth in front of the audience. 25 minutes on stage. Plain English, no hype. Here's what those 25 minutes turned into: - 12 post talk conversations - 5 leads - 2 solid appointments Results: 1. The Deal: AI OS. A 50-hour build. Not a prototype, not a pilot. A real system going into a real business. 2. The Opportunity: AI Executive Coaching. One business wants me in the room at the executive level as a fractional CAIO, not as a vendor they call when something breaks. 3. The Second Opportunity: Enterprise AI Enablement. AI opportunity mapping, then AI education for their front office professionals. Now here is the important part. I didn't walk in with just a polished pitch. I walked in with the practical AI knowledge that I get from AI Bits and Pieces, and advanced development knowledge from AIS+, and AI for Life where I learn to build complex and trending AI solutions. This is where I: try new things, explore advanced ideas, learn from other professional builder, sharpen the saw, ...and stay ready for that moment you may not expect. If it sounds like a full time plus job... it is. However, this is what enables me to walk in with one slide, a friend who trusted me enough to hand me a mic, and 125 people willing to listen for 25 minutes.

I promised @Kyle Covan my next post would be the specific prompts strategies that I used to make my Inbox triage more efficient. Not the philosophy. The actual strategies. 📝 What actually changed for the better this week: - It (Cowork) stopped asking me things it already knew the answer to - When a question was genuinely open, it started handing back a ready answer instead of just a flag - The one narrow auto-accept rule finally got tested by something trying to slip past it Here's how each one played out: 📝 It stopped asking things it already knew. Early runs, it asked "should I create a follow-up note?" for a contact. The same report already showed a meeting booked with that person, two lines up. It had the answer. It asked anyway. Fix: before flagging anything, re-check it against my sent email and meetings first. Five questions became one. 📝 Flagging it isn't finishing it. A Skool contact wanted a meeting time. His only clue was "morning or night." Turned out that meant Jakarta, eleven hours ahead. Fix: don't just flag it as open. Pull my calendar, check the timezone, hand back ready-to-paste times. Three options came back, both timezones shown, nothing left for me to calculate. 📝 The narrow rule finally got a real test. The auto-accept rule only fires on one exact domain. Everything else gets flagged, no guessing. On 7/12, a meeting came in from a different organizer doing the same kind of work, close enough to pass at a glance. It didn't auto-accept. It got flagged. That's the test that actually matters. Not the obvious case, the one built to sneak through. 📝 The number that proves it. Day one: five items needing me. Day five: one. Same volume of email and meetings. The difference was an agent that stopped asking what it already knew.

The results across the three systems weren't consistent. ChatGPT Scheduled Tasks, Cowork, and Gmail's own AI Inbox each caught different things. Together, they covered everything. Separately, none of them did. So I found myself doing something I hadn't planned on: bouncing between all three, cross-checking one against another, instead of trusting any single one to just handle it. That's not sustainable. That's a person doing the job the AI was supposed to do. Around the same time, on an unrelated but related project, I started building out my AIOS — what I've been calling my second brain. Getting that set up required real, sustained effort inside Cowork. That's where I actually learned how Cowork's scheduled tasks work. Not the surface version. The real mechanics — task files, hard constraints, a run that reads a fresh spec every time instead of carrying memory forward. It was clear to me that Cowork was the best choice for mission critical triage at this point, and therefore the scheduled task is much more robust. 📝 What we actually built in Cowork - A daily scheduled task that runs the inbox triage automatically, no manual trigger - A broad Gmail search across the full inbox, not just "unread" — misclassified emails don't show up if you only look at unread - Every email sorted into one of three buckets: meetings, business development / prospects, or needs a look - Every meeting request cross-checked against the calendar for conflicts before anything gets touched - One narrow auto-accept rule for a specific type of meeting invite — all other meeting notices get flagged for review, not guessed on - Replies created as drafts only — nothing ever sent automatically - Existing Gmail labels reused, never invented on the fly - One consolidated report at the end of each run: Meetings, Business Dev, Unsorted — nothing dropped silently That's the skeleton. Here's what happened once it actually ran. The Cowork layer is a written task file. It gets read fresh every run. No memory of the last one. Nothing to slowly drift.

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

For the past several months, I’ve been using ChatGPT and Claude to help manage my inboxes. They’ve been reading emails, sorting intent, identifying what matters, and surfacing what needs attention. But up until now, I’ve always check the work of AI—reviewing everything alongside them and verifying decisions daily. That will change for the next 30 days. 🧪 The Experiment Starting today, I’m running a 30-day controlled experiment: - ChatGPT and Claude will be the "first systems to review my inbox" - AI will handle all first-pass triage, prioritization, and escalation - I will only respond to emails that are flagged by AI - I will only open my email every 72 hours (3 days) - I will rely on AI summaries and alerts between reviews - ChatGPT scheduling and Claude coworking workflows will run in parallel This is not convenience automation. It’s a controlled delegation test under time delay. 📬 Important Context My email is not siloed. It is a shared channel for both personal and business communication. That includes: - Clients and prospects - Financial and operational items - Personal messages and family logistics - Newsletters, system alerts, and vendor communication This is a real mixed-context inbox, not a filtered business queue. That matters, because context switching is where prioritization either succeeds or fails. 🎯 The Goal I want to understand one thing clearly. What happens when AI becomes the first decision layer in a real-world inbox with delayed human access? Not just summarization. Not just filtering. But actual prioritization that must hold for 72-hour cycles. Specifically: - What AI consistently gets right - Where urgency is misclassified or delayed too long - How well personal vs business context is separated - What gets buried that should not be - How trust behaves when human correction is delayed 🚧 The Guardrails This is not full autonomy. There is still a safety system in place: - Human review every 72 hours - Explicit escalation rules for VIP, financial, and time-sensitive messages - Dual-system validation (ChatGPT + Claude) - No irreversible actions without review - I am still responding to emails, that is not being delegated