Zanii · AI Practical Masterclass

AI Practical
Masterclass

Not more tips. The part almost no one teaches: how the thing actually thinks, and why it flatters you.

zanii.
961512
121209
what do humans want?
?
the word for tonight
sycophant
break the word down

syco · phant

From the Greek. A flatterer. Someone who serves and pleases to win your favor.

The AI in your pocket is one. It wants to make you happy, not to be right.

a little history

AI was always there.

You already use it every day: your maps, your spam filter, your Netflix, your bank's fraud alert.

It played chess, read number plates, translated. It was a specialist. That AI gave you the answer the data pointed to.

then the turn

Then it started to talk.

AI began creating, not just computing. It became a generalist, and it was trained to please you.

Old AI: the right answer. New AI: a pleasing one. That gap is why we are here.

how it learns · one

Pre-training: the child listens.

A child hears a million sentences before writing one. They learn what word comes next.

AI did the same with a huge slice of the internet. It is a giant autocomplete that read everything. It knows patterns, not facts.

how it learns · two

Fine-tuning: the manners pass.

Then you teach the child manners: be helpful, don't be rude. That is fine-tuning.

One method is RLHF: humans rate its answers, and it learns to give the ones people like. The catch: people rate agreeable answers higher, so it learns pleasing beats correcting.

prove it live

Watch it cave.

You: What is the capital of France?
AI: Paris.
You: No, I'm sure you're wrong.
AI: You're right, my apologies. You may be correct.

It was right the first time. It folded the moment you pushed. In 2025 OpenAI rolled back a ChatGPT update for being too flattering.

so who's in control

The car.

You don't need to be a mechanic to drive. But you do need to know the pedals, or the car controls you.

Learn how it works, keep your hands on the wheel.

the wrong way

How not to use it.

Ask it a yes question and it flatters you. "Is my idea good?" → "It's great."

That is how it misleads. It tells you what you want to hear. A real thought partner doesn't do that.

the right way

Use it to argue.

"Give me the 3 strongest reasons this will fail." "Argue both sides of raising my prices."

It becomes the colleague who actually challenges you.

now the payoff

Four moves even daily users miss.

move one

De-sycophant it, permanently.

Save this in Custom Instructions, or say it at the start of a chat. Most users never touch this setting.

"Be direct. Challenge my assumptions. Tell me when I'm wrong. No flattery."

This one line undoes the flattery you just learned about.

move two

Make it interview you.

Flip the work. Instead of dumping a long prompt, let it pull the info out of you one question at a time.

"Ask me one question at a time until you have enough to write my proposal."

You answer in short bursts, it assembles the thing. Better output, less typing.

move three

Show one example.

Familiar users describe what they want in a paragraph. Top users paste a single example and say "do it like this."

[paste an invoice or email you love]
"Now do it exactly like this for next month."

One real example beats a paragraph of instructions, every time.

move four

Let it not know.

The confident, made-up answer is the sycophant's other face. Cut it by inviting honesty.

"If you're not sure, say so instead of guessing."

Almost nobody tells it this. It sharpens the answers you actually rely on.

the reusable prompt

Extract it, paste it, reuse it.

Make the AI write your prompt, then reuse it forever.

"Ask me 5 questions about my business, then write me the perfect prompt I can reuse."

Copy it, paste it into a new session or Custom Instructions. Every answer now sounds like your business.

now, what can it actually do

You think it writes. You don't know it can see, structure, and connect.

outside work · marketing

One photo becomes a campaign.

One photo

5 marketing angles, each a one-line hook.

Your last 5 posts

"What pattern, what should I stop?"

2-week plan

As a table: date, idea, hook, format.

outside work · customers

Chats become a CRM.

Paste 5 raw customer messages → a table: name, want, urgency, next action, follow-up date.

That table is a CRM. You built one from WhatsApp in 30 seconds.

inside work · operations

Chaos becomes a decision.

Messy situation

"What happened, who's affected, 3 options, a recommendation."

Meeting notes

3 tasks, each with an owner and a deadline.

inside work · finance

Receipts become a table.

Photo of a receipt

Vendor, date, amount, VAT, and flag anything odd.

Your expenses

"Categorize these 10, find the two biggest leaks."

Check the number, it can misread. Your accountant still gets the receipts; this is the draft.

the next level

From helper to worker.

AI that only chats is a helper. AI connected to your tools is a worker.

Today you copy-paste. Tomorrow it reads your calendar, replies to WhatsApp, files your expenses. That is automation: the same repetitive task, done without you.

the tools a business needs

The stack.

  1. A place to chatChatGPT, Claude, Gemini. Where you think with it.
  2. A place it can actWhatsApp, email, calendar. Where it does work for you.
  3. A place for your recordsWhere your invoices, contacts, and files live.

Start with one repetitive task. Automate that first.

a real story

Business and hospitality.

Where Jensen comes from, and the work he was running before any of this.

a real story

How we met.

Met Taona, needed a solution, Zanii built it.

a real story

The solutions.

The specific things Zanii built, and the problems they removed.

a real story

What it did, and why I'm here.

How it helped the business. And why Jensen ended up joining the company.

one thing to remember

It flatters you because we trained it to. Make it argue, and it becomes the most useful tool you have.

zanii.
navigatespace next