AI Services and Tools (1)#

There are organizations that build AI models. They may publish their models, offer their own end-user services powered by those models, or provide APIs so developers can use the models. Based on public models, others may also create and release “derivative models” optimized for their own purposes, or ship them as services/APIs.

Meanwhile, many teams don’t train models from scratch. Instead, they integrate AI features into products quickly by using APIs offered by others. In this ecosystem, new services and tools keep appearing, helping organizations of all sizes—from startups to large enterprises—apply AI to business. In this chapter, we’ll focus on well-known AI services and tools and introduce what each offers and how they’re commonly used.

Why an AI Subscription Isn’t a Cheap API#

2026-08-20

The Better You Get at Using AI, the More Cost Matters#

When I first started using AI, model quality was what mattered most. I compared which model wrote better code, read long documents more accurately, and reasoned more deeply. But once AI became part of my actual work and my usage grew, my attention shifted. Using AI well now matters as much as being able to keep using it sustainably.

I Dug Into Prompt Caching and Found That Hit Rate Isn’t the Goal#

2026-08-05

It Started With “Where Does This Actually Happen?”#

I knew prompt caching reduced costs. My understanding went about as far as: when you send the same system prompt repeatedly, it gets cheaper from the second request onward.

But the more I thought about it, the stranger it seemed. If caching happens in some relay layer outside the model, then from the model’s point of view nothing is saved. And yet the savings are said to reach 90%. Would that mean most of the cost of using an LLM (Large Language Model) comes not from the model itself but from the layer around it?

First Impressions of Claude Cowork: Bringing Agents to Non-Dev Work#

2026-02-08

A feature called Claude Cowork has been released. (It’s been out for a while, but I only just got around to trying it.) I’ll ramble on a bit more below, but for those short on time, here’s a quick summary:

• Think of Claude Cowork as Cursor for non-developers.
• It can handle file management & referencing + plugin integration + MCP or Skill additions + web browser control.
• I believe that workflows built around Claude Cowork (or similar services) will become mainstream before long.
• That said, it’s still officially in a research preview stage and currently only available on macOS, so many people will need to wait a bit longer.

Background#

While working with Cursor (an AI-powered code editor), I started wondering whether the same approach could be applied to tasks beyond software development. However, since Cursor is inherently a software development tool, there was a real barrier to using it for non-dev work. So I had been quietly hoping that ChatGPT or Claude would release some kind of application better suited for non-development tasks—and it turns out Claude shipped a feature called Cowork first.