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

Researchers gave advanced AI models a version of the classic Stroop test, where the model has to ignore the obvious answer and follow the actual instruction. For example, imagine seeing the word BLUE printed in red ink. A human is supposed to say the ink color, not read the word. That sounds simple, but it tests whether you can slow down, ignore the automatic response, and stay focused on the task. The AI models did well when the test was short and simple. But as the task got longer and more demanding, performance dropped sharply. Some models reportedly fell from above 90% accuracy to near failure. 🌀 The Practical Point AI often fails when the job requires it to keep resisting the obvious answer over and over again. That is the face-plant. AI can look brilliant when the task is: “Answer this one question.” But it can struggle when the task becomes: “Follow this rule carefully, keep following it, ignore distractions, do not drift, and do that 100 times in a row.” That matters in real life because many business tasks are not one-shot answers. They are consistency tasks. Review every invoice the same way. Apply the same policy every time. Check every contract against the same rule. Follow the workflow without improvising. Stay inside the guardrails even when the next item looks familiar. 🌀 Short-Story Angle AI can explain the Stroop test. AI can probably write a college essay about the Stroop test. But when researchers asked AI to actually take the Stroop test, it eventually wandered off like a substitute teacher who lost the lesson plan. The lesson is simple: AI does not just need intelligence. It needs attention. And in business, attention is often where the money is. To read the full article, click here. A classic brain test exposed AI's biggest weakness Date: June 10, 2026 Source: PNAS Nexus

Welcome to the Out of The Box Series, where I test how far curiosity and AI can take you in 30, 60, or 90 minutes using today’s best no-code and low-code tools. No setup. No training. Just pure exploration, right out of the box. 🎬 This Episode: ChatGPT Scheduled Tasks ChatGPT now has a Scheduled feature, and I wanted to see how practical it really is for everyday work. Not a complex automation build. Not a workflow platform. Not a technical setup. Just simple reminders, recurring tasks, research requests, and monitoring activities created in plain English. The result? ✅ ChatGPT finally makes basic automation feel easy enough for everyday use. 🧪 The Challenge Can ChatGPT help you create useful scheduled tasks and reminders without code, workflow builders, triggers, or integrations? That was the test. ⏱️ The 2-Minute Playbook (Literally) 1. Open ChatGPT 2. Select Scheduled from the menu 3. Describe what you want ChatGPT to do and when 4. Set the timing 5. Save Each scheduled task runs automatically and places the result in your “Recent” chats for review. 📋 Example Scheduled Tasks “Every morning at 8:00 AM, send me a summary of the top AI business news.” “Remind me every weekday at 7:30 AM to write my AI Bits & Pieces post.” “Every Friday at 4:00 PM, remind me to review my sales pipeline.” “Watch for new AI strategy jobs paying over X dollars and notify me when one appears.” 💡 Bits & Pieces Pro Tips Start simple. Do not try to build a full automation system on day one. Start with one useful reminder or recurring task. Be specific. Instead of saying, send me news. Try, “Every morning at 8:00 AM, send me the top 5 AI business news stories with one sentence on why each matters.” Use it for things you already forget or tend to procrastinate. Sales follow-ups. Weekly reviews. Content reminders. Market updates.Research checks. That is where Scheduled becomes useful fast. ✅ Out of The Box Takeaway Awesome feature with one catch. You are limited to five scheduled tasks or reminders. 😣