Articles

AI Thinking

Latest AI Trends: General-Purpose Agents Today, How They Work, How to Learn, and What’s Next

General-purpose AI agents are rapidly spreading, and AI is evolving from a “chat partner” into a true “work executor.” In this article, I summarize the latest trends (general-purpose agents and the shift from vibe coding to vibe working), explain how agents work with clear diagrams—covering **harnesses**, **context**, and **SKILLS/MCP**—and share practical ways to learn and use AI (including the “1B-token rule,” daily usage habits, and prompt tips). I also discuss what’s coming next: AI becoming the unified interface for operating everything, and why **voice input** will matter more.

Read more
AI Thinking

How to Use AI Without Losing Yourself: What to Delegate vs. What Not to Delegate

After using AI every day, I realized it had quietly started to “invade” the core of my thinking. In this article, I share real failures—letting AI write blog posts that felt like “whose words are these?” and shaping a product concept that was logically consistent but not truly mine. Based on that experience, I clarify what you should *not* delegate to AI (your values, intention, and personal core) and what you *can* delegate (idea sparring, exploring methods, and execution). A practical mindset for using generative AI without losing your own direction.

Read more
AI struggle story

How to Improve Business Processes with AI: Design “Where to Use vs. Not Use” LLMs Using Deterministic vs. Non-Deterministic Work

The key to AI-driven process improvement isn’t simply “embedding AI into operations,” but deciding **where to use AI—and where not to**. Because LLMs are inherently **non-deterministic**, placing them in parts of a workflow that should be deterministic can lead to unstable quality, unexpected behavior, and added complexity. This article explains a practical approach: map your end-to-end business flow, separate deterministic vs. non-deterministic steps, and select improvement targets using **effort (time cost) × implementation difficulty**—with a concrete example and a simple difficulty matrix to find quick wins.

Read more
AI struggle story

AI Is a Brilliant New Hire Who Knows Nothing—Here’s How I Give Instructions

AI outputs go wrong mainly due to missing context. This article explains how to provide task-critical information clearly, work within token limits, and treat prompting like onboarding a smart new hire—practical tips you can apply daily.

Read more
AI Thinking

I “Hired” an AI Tax Accountant, CEO, and Strategist—And My Business Finally Moved

In January 2026, I launched a sole proprietorship focused on AI product development and AI-driven business transformation. From taxes and invoices to landing pages and infrastructure, I faced endless questions—so I turned ChatGPT into an “AI expert team” (tax accountant, CEO, strategist, and more) and moved forward through trial and error. This post shares the workflow, what worked, what failed, and how an AI team can help solo founders get past the first hurdles.

Read more