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.
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.
31 AIIt 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.
30 AIHow 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."
29 AIWe 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.
28 AIWhose 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.
27 AIAsking 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?
26 AIThere'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?
25 AIWhat 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.
24 AIEnglish 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.
23 AIIs 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.
22 AIWhat 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.
21 AIWhy 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.
20 Customer ServiceConnecting 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.
19 AIGPT 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.
18 AIReflections 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?
17 Customer ServiceIntercom, 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"?
16 AdvertisingHow 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.
15 Customer ServiceFAQ 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.
14 AdvertisingThis 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.
13 AIWhat 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.
12 AdvertisingWhat 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.
11 AIWhat 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.
10 AdvertisingThe 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.
09 AIWhat 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.
08 Customer ServiceWhy 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.
07 Customer ServiceWhat 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.
06 Customer ServiceThe 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.
05 Customer ServiceStop 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.
04 Customer ServiceThe 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.
03 Customer ServiceAn 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.
02 Customer ServiceWhy 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.
01 Customer ServiceWhat 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.