As AI models continue to evolve, they are beginning to give us different products for different kinds of use cases. The three products I find most useful are: - Chat - Work - Code There are also specialized products for things such as design, research, and working with source material—including tools like Claude Design, Gemini Notebook. But for today, let’s stick with the three horsemen: Chat, Work, and Code. Each AI company is known for its models. The large, well-known models—ChatGPT, Claude, and Gemini—are commonly referred to as frontier models and are generally associated with closed, cloud-based systems rather than open-source models running locally. Please refer to the "Frontier AI Ecosystem Matrix" to see what OpenAI, Anthropic, Google, Microsoft, xAI, and Perplexity call their respective models and products. For this series, I will use the follow product naming convention: - Chat - (Co)Work - Code(x) The parentheses are simply my shorthand to cover the names used by ChatGPT and Claude. Please note that these are not official industry terms. They simply save me from repeatedly writing “Work or Cowork” and “Code or Codex.” LOL! Here is the easiest way I have found to explain the difference between the products: Chat: What question can I answer for you, right now? (Co)Work: What can I take off your plate? Code(x): What can I build for you? The goal is not to create a perfect technical definition. It is to give you a simple way to recognize which type of AI product may be the best fit for the task in front of you. In Part 2, we will look more closely at Chat, (Co)Work, and Code(x) product features, how each product is actually used and where the lines between products overlap. In Part 3, we will work through a few practice exercises to help solidify the use cases for each product. If you have any questions, please ask in the comments below. Make it a great AI day!

We are kicking off the new "Learn with Your Whole Heart" chapter of AI Bits & Pieces, and you get to help decide what we create next, enter for a chance to win, and help us give back. Cast your vote below. 👇 How the Giveaway Works: ✅ Everyone who votes or adds a comment will be entered to win. ✅ Each person receives one entry per giveaway. ✅ Claude will randomly select one winner from all eligible participants. 🎁 The winner will receive a $25 Amazon eGift Card. ❤️ AI Bits & Pieces will also donate $25 to one of our approved charities. You can learn more about the organizations we support, here: Our Charities: Learn with Your Whole Heart A winner and charity will be selected on Sunday, July 26th at 6pm EDT, and announced sometime on Monday, July 27, 2026. Cast your vote below. 👇

My Claude Cowork inbox triage reads a fresh task file every run. No memory of yesterday, by design, so the reports never drift. This week, that design had a cost. Two calendar items looked like accidental duplicates. - One was two event registration links landing as separate calendar entries. - The other was two client meetings back to back, one of them titled PLACEHOLDER. I confirmed both, in chat: stating, "all four were real, nothing to merge or delete." The next morning, the same two questions came back. Same wording. As if I'd never answered. The challenge was that if I gave it memory of the chats it would stop the repeat questions, but it would also break the fresh-read design that keeps the reports from drifting in the first place. So the fix was simpler: Write the confirmed exceptions into the task file itself, as a standing list it checks before asking anything. How it works now, step by step: - I confirm something, in chat, once - That confirmation gets written into the task file as a standing exception - Every future run checks that list first, before flagging anything - If it matches, the item is reported as settled, not raised as a question Cowork can: ☑️ Read a fresh task file every run ☑️ Check any exception already written into it ☑️ Skip anything already settled Cowork cannot: ❌ Remember what I told it yesterday ❌ Learn a new exception on its own

🏈 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.

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.