In Part 2, we looked at the range of model capability. Now let’s make it practical. After more than 100 hours of testing, I have developed a fairly simple approach. I choose the product, model, and reasoning setting based on the type of work I am doing (not cost - yet). 🧠 Heavy Logic, Planning and Structure, for work such as: - Business proposals - Strategic frameworks - Complex planning - Coding - Difficult analysis - Multi-step problem solving - Assignments where maintaining context is critical - Consistency of theme or storyline For these applications, I want stronger reasoning, even if it takes longer. Product: ChatGPT Model: GPT-5.6 Sol Setting: High reasoning and for my book editor skill, Pro. Product: Claude Model: Claude Opus 5 Setting: High effort, with extended thinking when needed For these assignments, creativity in the delivery is secondary. My priorities are logic, structure, context integrity, planning, and getting the framework right. I rarely go higher, but keep in mind, most of what I do is front office business execution: strategy, project management, process refinement, education and training, and Cowork automation. I use Fable 5 rarely. I am not primarily using Claude to build sophisticated production applications. ✍️ Writing and Everyday Communication, for: - Blog posts - Creative writing - Emails - Business communication - Social posts - Editing and rewriting I usually want a capable model that leaves a little more room for creativity and variation. Product: Claude Model: Claude Sonnet 5 Setting: Standard/default effort Product: ChatGPT Model: GPT-5.5 Instant Setting: Instant I still use GPT-5.5 for this type of work while it remains available to me. The Interesting Exception: Image Creation Image creation breaks my normal rule. Why? I need the LLM to understand: - What I am trying to communicate - The audience - Composition and hierarchy - Style and mood - The creative objective So I need reasoning. But I also want the system to have enough freedom to interpret the brief creatively.

In Part 4, we talked about dialing model capability up or down. 📌 Now let’s practice it. My shorthand is: Find the floor, then move back up one level. That means you reduce the reasoning or effort level until you can see the model starting to miss the mark. Then you move back up to the lowest setting that still produces the quality you need. That gives you a practical balance between: - Output quality - Speed - Cost - Available usage or capacity - The amount of correction you have to do yourself Practice This: - Choose an assignment you already understand well. - Do not use something completely unfamiliar. - You need to be able to recognize when the output gets weaker. Good practice assignments include: - A business proposal - A project plan - An app framework - A book chapter outline - A training lesson - A process improvement plan ✅Step 1: - Use the model map from Part 3 to choose your product and model. - Start with the model you believe is appropriate for the work. ✅Step 2: - Run the assignment using a relatively high reasoning or effort setting. - Your goal is to create the first strong version of the plan, framework, proposal, or structure. - Save the result. This becomes your quality baseline. ✅Step 3: Once the main thinking is complete, reduce the reasoning or effort level one step. For example: High reasoning → Medium reasoning Or: High effort → Medium effort If the work is now very clear, and the product allows it, you can test reducing it two levels. ✅Step 4: Ask the model to continue the work. For example: - Expand one section - Rewrite part of the proposal - Create a summary - Draft an email from the plan - Turn the framework into a checklist - Create social posts from the article - Refine the tone - Format the output for easier reading This is where the test begins. You are no longer asking the model to do the hardest thinking from scratch. You are asking it to continue from an established structure.

✨ The Quirk: People may enjoy an AI-written story just as much, or even more, than a human-written one… Until they’re told it came from AI. The writing was not necessarily the problem. The label was. What’s Going On: In a recent study, cited by Cambridge University, participants could not reliably tell human and AI-written stories apart. Here is what's interesting, when participants read stories without labels, AI content was often rated as higher quality and more absorbing. But stories believed to be AI-written received lower ratings, even when the actual writing was the same. Why This Matters: A label can make people value identical writing differently, because they often judge AI before they judge the words. Labels can quietly shape our judgment before we evaluate the actual work. AI fluency means learning to separate the quality of an outcome from our assumptions about how it was made. Source: Sears, S., & Skolnick Weisberg, D. (2026). “Bot or not?” Judgment and Decision Making.

Big piece of the puzzle https://www.linkedin.com/posts/the-agentic-era-demands-context-engineering-share-7492242800122519552-b8gX/?utm_source=social_share_send&utm_medium=ios_app&rcm=ACoAAAH19S8Bpi006pGjc2bVQqx0H10uoVuMMzg&utm_campaign=copy_link

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!