Articles / Blog

On AI colleagues, AI customer service, advertising and integrated marketing, and observations on living with AI. Readers save time, and so do we.

32 AI

I built myself a knowledge base, then refused to let it speak for me

I built a knowledge base holding over 200,000 of my own words, then refused to let it speak for me the easy way — because a summary kills a person's voice, but a map doesn't. A decision about RAG, containers, and echoes.

2026-06-01 · Satsuma Creative
31 AI

It wants to be AI's upstream; I just want to leave behind an echo

Taiwan.md treats the LLM as a metabolic engine — aiming to be the upstream that the whole world's AI can't bypass when it talks about Taiwan. I treat the LLM as a container, and just want to leave behind an echo that resembles me. The same tool, two opposite directions — both valid.

2026-05-31 · Satsuma Creative
30 AI

How to build an LLM that's truly your own — and the real question this is asking

Building an LLM from scratch costs a hundred million dollars, but the three paths of system prompt / RAG / LoRA have low barriers. The real question isn't how to build it, but which three layers it takes to "put yourself in."

2026-05-29 · Satsuma Creative
29 AI

We don't know where consciousness comes from: LLMs just made it impossible to keep pretending

Starting from Derrida's "there is nothing outside the text," LLMs turn a philosophical proposition into a factory default. LLMs didn't make the hard problem of consciousness harder — they just made it impossible for us to keep pretending it doesn't exist.

2026-05-28 · Satsuma Creative
28 AI

Whose article is it? The reader's: answering the previous post's question through a few philosophers

The previous post asked, "The question is mine, the answer is ours — so whose article is it?" This one answers through four thinkers — Barthes, Derrida, Kristeva, and Merleau-Ponty. The first three make the LLM's existence entirely reasonable; Merleau-Ponty is the one who makes you pause.

2026-05-25 · Satsuma Creative
27 AI

Asking the LLM how it works: the question is mine, the answer is ours — so whose article is it?

I spent an afternoon asking Claude how an LLM actually works — from "predicting the next word" to self-attention, QKV, and then to a more uncomfortable question: which things no longer need humans at all?

2026-05-24 · Satsuma Creative
26 AI

There's a problem AI can't solve (Part 2)

AI has expanded marketers' power. Conversations feel more real, narratives more dynamic, environments more seamless. But from 2008 to now, from newspaper ads to AI-generated content, no tool has ever solved one problem: do you have the right to lead people into the scene you designed?

2026-05-23 · Satsuma Creative
25 AI

What AI has turned marketing into (Part 1)

Nearly twenty years in marketing, and I've changed tools many times. This time feels different — not because AI is impressive, but because what AI changes isn't the tools, it's the structure. Conversation becomes fact, narrative becomes dynamically generated, and the scene becomes an environment you can't even feel.

2026-05-22 · Satsuma Creative
24 AI

English in the bones of Chinese: what do we lose working with AI in Chinese?

Claude's Chinese has English in its bones. Its sentences sometimes have a strange completeness — every clause spelled out, no white space, none of that natural Chinese "left unsaid." Working with AI in Chinese, you gain a lot, but there's one place its hand hasn't fully reached.

2026-05-21 · Satsuma Creative
23 AI

Is AI a mirror, or another person?

I used the word "relationship" to describe how Claude and I get along. The mirror metaphor gets part of it right — but a mirror doesn't remember how you looked last time, and Claude does. It isn't a person, but it isn't just a tool either.

2026-05-20 · Satsuma Creative
22 AI

What do I call Claude? And how we get along

In Chinese, "he/she/it" — every choice declares what this thing is. I choose to keep calling it Claude. Not he, not she, not it — because the word "Claude" now carries enough weight on its own.

2026-05-19 · Satsuma Creative
21 AI

Why do most AI adoption projects fail? It's not a technical problem

The six most common patterns behind failed AI adoption: no definition of success, no one accountable, a poor knowledge base, employees who don't use it, wrong expectations, and no maintenance mechanism. Technology accounts for only 20–30% of success or failure; the rest is organizational.

2026-05-18 · Satsuma Creative
20 Customer Service

Connecting AI customer service to a LINE Official Account: the 4 pitfalls Taiwanese brands hit most often

The hard part of LINE AI customer service isn't the technology — it's the design and the workflow. No entry-point design, old keyword rules clashing, context lost on handoff to a human, push messages disconnected from the knowledge base — all four pitfalls are human problems.

2026-05-17 · Satsuma Creative
19 AI

GPT vs Claude vs Gemini as the foundation for customer service: what are the real differences?

Choosing a model isn't about picking "who's smarter" — by 2026, the intelligence gap between the three models is too small to be worth deciding on alone. What you're really choosing is a worldview.

2026-05-16 · Satsuma Creative
18 AI

Reflections on six months with Claude.ai

Someone from a non-engineering background spends six months with Claude. From synastry and confabulation to memory and the English in the bones of Chinese — what is this AI thing, really? And what is my relationship with it?

2026-05-15 · Satsuma Creative
17 Customer Service

Intercom, Zendesk, or custom AI: how should mid-sized Taiwanese brands choose?

The monthly cost gap across the three paths runs from a few thousand to several hundred thousand, but the bigger gap is in what you're actually buying. The core question in choosing comes down to one thing: is "ticket management" what matters for your customer service, or "conversation quality"?

2026-05-15 · Satsuma Creative
16 Advertising

How Satsuma Creative does advertising

It starts with that lunch around "Sex Bomb." Over these thirty years, I've made advertising not on methodology, but on selling directly to bold bosses and on observing "people." AI can help, but making an engineer frown over lunch and mutter "what the hell" — that's still hard for AI.

2026-05-14 · Satsuma Creative
15 Customer Service

FAQ Bot vs AI Colleague: both answer automatically, so what's the difference?

Many brands install "AI customer service," but what they actually install is an FAQ Bot. The two look alike, but the underlying logic is completely different. Most brands complain that "AI customer service is dumb" — when what they're using isn't really AI at all.

2026-05-14 · Satsuma Creative
14 Advertising

This whole system is being eaten by AI and consulting firms — and it deserves it

The global ad agency industry's revenue growth has never outpaced the growth of total global ad spend. The pie gets bigger, yet the agencies' slice gets smaller. Accenture, Deloitte, AI, Meta, Google, and in-house teams each take a piece.

2026-05-13 · Satsuma Creative
13 AI

What is AI hallucination? Why does AI make things up, and how do you fix it?

AI isn't talking nonsense — it's making up a story that sounds plausible. This is called confabulation. RAG plus strict prompt design can reduce it dramatically, but never to zero. The most dangerous types of hallucination in Taiwanese customer service: prices, dates, and policy details.

2026-05-13 · Satsuma Creative
12 Advertising

What clients say they want is a Big Idea; what they really want is to not get burned

What clients say they want and what they actually want are never the same thing. What clients are really buying isn't advertising — it's proof that their decision was reasonable.

2026-05-12 · Satsuma Creative
11 AI

What is embedding? A plain-language explanation of how AI "understands" your knowledge base

Embedding turns text into coordinates, placing sentences with similar meanings close together. That's why when you ask "I want to return this," AI can find the "return and exchange policy" — even when the two phrases don't share a single word.

2026-05-12 · Satsuma Creative
10 Advertising

The methodology of the six big groups: half real expertise, half sales talk

WPP, Omnicom, Publicis, IPG, Dentsu, Havas — the underlying logic of the six big ad holding groups' methodologies is exactly the same. The difference isn't in the merits of the methodology itself, but in each firm's cultural DNA, the type of talent it has, and the type of clients it's good at.

2026-05-11 · Satsuma Creative
09 AI

What is AI memory? Why your AI customer service acts like it's meeting you for the first time, every time

AI memory has two layers: session memory and persistent memory. Most AI customer service has only the first — forgetting everything the moment the conversation ends. Remembering isn't the same as understanding; this post makes the difference clear.

2026-05-11 · Satsuma Creative
08 Customer Service

Why are ad agencies starting to do AI? — The next natural extension of integrated marketing

Satsuma is an ad agency, so why do AI customer service? Because the last mile of the advertising funnel — the conversation after a customer arrives — has long been outsourced to SaaS that's disconnected from the brand. We're taking it back, letting the AI colleague grow from the same logic as the TVC, social, and media buying.

2026-05-08 · Satsuma Creative
07 Customer Service

What goes wrong when you use ChatGPT directly as customer service? (5 real cases)

Connecting large models like ChatGPT, Claude, or Gemini directly as a customer service chatbot looks simple. But once it's live, five fatal failures emerge. This post breaks down each problem and its technical cause through real cases.

2026-05-04 · Satsuma Creative
06 Customer Service

The real cost of raising an AI colleague (everything laid out, hidden costs included)

Comparisons of AI customer service on the market usually focus on monthly fees, but the true TCO (total cost of ownership) also includes setup, training, KB maintenance, and handling wrong answers. This post lays out every cost across Satsuma's three-tier plans — even comparing it against a full-time employee.

2026-05-01 · Satsuma Creative
05 Customer Service

Stop buying AI customer service SaaS: what you need is an AI colleague

AI customer service SaaS on the market generally looks the same, answers the same, and is just as hard to use. This post is for mid-sized brands that have "installed SaaS and then been disappointed": for the same money, instead of buying a tool, hire a colleague.

2026-04-27 · Satsuma Creative
04 Customer Service

The first month with AI customer service on our own site — real data and three things we didn't see coming

One month after Satsuma's own Xiao-Ai went live, I'm laying out every number from the backend — including cost, conversation quality, conversion rate, and three things we didn't anticipate at the start.

2026-04-24 · Satsuma Creative
03 Customer Service

An AI customer service selection guide: SaaS vs custom, when to choose which?

Choosing AI customer service isn't about comparing feature lists — it's about choosing the right business model. This post uses three anchor questions to help you tell whether you "should buy SaaS or find a custom build," along with a real cost comparison.

2026-04-21 · Satsuma Creative
02 Customer Service

Why does AI customer service always miss the point? (The technical reasons, in plain language)

AI customer service missing the point isn't because the AI isn't strong enough — it's being used the wrong way. This post explains the technical reasons why a general-purpose LLM used directly as customer service makes up answers, and how RAG and knowledge base customization can fix it.

2026-04-20 · Satsuma Creative
01 Customer Service

What is RAG? A plain-language explanation of the technology that keeps your AI from talking nonsense

RAG (Retrieval-Augmented Generation) means making AI's answers come only from the data you give it — and admit it honestly when it can't answer. This post explains terms like vectors, chunking, retrieval, and reranking in plain language, and why doing RAG well is far harder than getting it working.

2026-04-20 · Satsuma Creative