The fastest way to lose a customer isn't bad service. It's a slow response. I've seen businesses spend thousands on marketing, only to lose leads because no one followed up for hours—or sometimes even days. In most cases, the first company to respond earns the opportunity. That's why I believe every growing business should have a system that: ✅ Responds instantly ✅ Books appointments faster ✅ Keeps every lead organized ✅ Reminds customers automatically Technology doesn't replace great customer service—it makes it more consistent. Question: What's your average response time to a new lead? Do you think it's costing you jobs?

I have a joke at work. I call it "the other 80%." Since I started using AI for documents, code, and other projects, I've noticed it scaffolds so fast — and so densely — that it's created a strange paradox around the old 80/20 rule. This joke applies to plenty of other things too, but let's stick with AI. What does it mean? a) It's amazing how quickly you can get almost there the 80%, yet how slowly you actually get there. Hence "the other 80%." b) After scaffolding, it feels like you're 80% done. In reality you may be closer to 20%. What you made may look wonderful and seem wonderful, but hold it up to a quality, context, and clarity lens and often it's more sizzle than substance. c) By the time you've reviewed, updated, and simplified everything, you're drained (but satisfied) — and your tokens are gone. 🙂 **Have I solved it?** Not exactly. But here are a few patterns that are helping: **1) Create lots of skills.** Skills travel better than memory. My rule now: anytime I have to haggle with the AI more than once or twice over the same thing — a missing font, the wrong tone in a document, an ugly table — I stop and say "record what you just did to fix that into a skill, so you know better next time." **2) Create lots of support docs.** AI is great at this. If you're reading this here then you probably already know about markdown. When I'm working on something, or building a spec for an app, I'll tell it at frequent intervals to update the docs and the skills. That keeps those files relevant and lets the AI capture the small details as it goes. **3) Build help and instructions into the thing itself.** When I scaffold, so much gets created that it overflows my mental model, fills me with doubt, and slows me down. Now, if I'm building an app, my pages get little "?" bubbles with the what and how of a given thing. For example, at work right now I'm analyzing phone data for abandoned calls — accounting for short abandons, filtering out internal calls, outbound, extension-to-extension, voice mails. Who can remember all that detail a month from now? Build it in. Then as you iterate, your own notes show up in easy-to-find places. If you're having AI build slide decks, ask it to populate the notes fields so later you can re-absorb your original intentions.

Since I started using Claude Cowork more regularly, I noticed something strange: My creative writing seemed to suffer. The ideas were still there. The information was accurate. The structure was often better. But the writing felt more formal, organized, and buttoned up. It did not always sound like me. So I asked Claude Cowork: “Why does my creative writing seem to suffer in Cowork compared with Chat?” The answer helped me realize that I was not necessarily using the wrong AI. I was using the wrong environment for that stage of the work. Chat is Dory. 🐠 It follows ideas wherever they go. It: explores, wanders, changes direction, and occasionally stumbles into something unexpectedly good. That makes Chat especially useful for brainstorming, finding your voice, testing language, and developing an idea before you know exactly where it will end. Cowork is Spock. 🖖 It wants the facts, the files, the instructions, and the desired outcome. It is, more structured, logical, organized, and focused on completing the assignment. In other words: Chat is often better for finding the voice. Cowork is better for turning that voice into finished work. Neither one is better. They are simply better at different stages of the process. My current approach is simple: - Use Chat to discover what I want to say. - Use Cowork to organize, refine, research, and complete the work. The mistake was expecting Spock to think like Dory. In Part 2, I will look at why Chat and Cowork feel so different from a feature and product-design perspective.

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!

If you've ever hit that dreaded message — "Your session limit is used up. Come back later." — you know how inconvenient it is, especially when you're on a deadline. Here's what's going on and how to avoid it. How limits work: Claude calculates your usage in 5-hour sessions. You get a lot of room, but the newer models also burn through it faster. Recently the default model was set to Fable, which is a new, very capable model — it's also the one that consumes credits the fastest. A simple rule of thumb: - If you don't use Claude much, just leave it on Fable. It's the smartest option and the most effective use of your limited time in the app. - If you use Claude a lot — building a document, deck, or project — be more deliberate. Save Fable for the hard thinking (new ideas, solving a tricky problem) and use a lower model for the routine work. - If you're running a project that already works well on a lower model, keep it there. It's working, and the newest model may not add much value while using more of your allowance. Where to change this: In the Claude interface, look for the model selector.. This is where you control which model runs and how much effort it puts in — and those choices directly affect how fast you hit your limits. How I learned this the hard way: Last week I started a task without realizing Fable was the default. My session ran out fast, and I was locked out until it reset. Not ideal. My approach now: For everyday work, Sonnet and Opus handle most things well. When I'm building something bigger, I bookend with Fable — use a newer model to brainstorm and rough out an outline or draft, switch to Opus for the dozen rounds of refinement (a good use for cheaper revisions), then switch back to Fable at the end to audit the result and check it met the original goal. I know this sounds like a lot of managing for a tool that's supposed to make our jobs easier — and it does! If your work is mostly quick and transactional, set it to Fable and forget it. But if you're building decks, running projects, or designing flyers, it's worth knowing how this works so you don't get locked out right when you need it most.