Most people are not learning AI.

They are collecting AI tools.

One day ChatGPT. Next day Claude.

Then Gemini. Then NotebookLM.

Then some new video model.

After 30 days, they know 40 names and still do not have one workflow they use every week.

That is the problem.

AI is easier to learn when you follow the right order.

Not tools first. System first.

I am Alex, welcome to ShortCu8 by Innov8.

Lets Dive Deep 🐰

Use this 30-day order:

That is the roadmap.

Not "become an AI expert forever."

Tools will change.

Models will change.

The real skill is learning how to work with them.

Do not start with 100 prompt templates.

Start with the basics.

Learn these five things:

Tokens

AI does not read text exactly like humans.

It breaks text into chunks called tokens.

This matters because long files, long chats, and long prompts all use context.

Context window

This is the model's working memory.

If the task needs a lot of background, you need to give the right context or use a tool built for sources.

Hallucination

AI can sound confident and still be wrong.

So for facts, numbers, citations, prices, laws, and current events, verify.

Temperature

Lower temperature is better for stable factual work.

Higher temperature can help with creative variation.

Most normal users do not need to obsess over this, but knowing it exists helps.

Model selection

Stop asking:

Ask:

Use a simple cheat sheet:

Claude = writing, coding, careful reasoning
ChatGPT = general work, images, tools, coding help
Gemini = research, long context, Google workspace
NotebookLM = source-based learning
Grok = X/social research

Goal for Week 1:

Know what tool to open and why.

Prompting is not magic words, It is giving a clear brief.

A good AI prompt usually has:

Bad:

Make this better.

Better:

Rewrite this product description for a small business owner.
Keep it under 120 words.
Use simple language.
Remove hype.
Make it sound clear, local, and trustworthy.

That is not a trick.

It is a brief.

Now add context.

Context is where most AI work improves.

Create one reusable assistant for your work.

Example:

Create an assistant for my freelance work.

It should understand:
- my services
- my usual clients
- my tone
- my pricing rules
- examples of past work
- how I write proposals and follow-ups

This can live in:

This is where most people fail.

They watch tutorials.They save threads.

They make zero things.Do not do that.

In Week 3, create five small outputs.

Output 1: One document

Example:

Create a 1-page client onboarding checklist.

Output 2: One spreadsheet

Example:

Create a sheet to track monthly AI subscriptions.
Columns: tool, plan, price, renewal date, keep/cancel.

Output 3: One image

Example:

Create a clean Instagram post idea for a local cafe's weekend offer.

Output 4: One video edit

Example:

Take this clip and suggest 5 edits for a Shorts version:
hook text, crop, caption space, cut points, and CTA.

Output 5: One simple tool or workflow

Example:

Build a simple client follow-up tracker with name, service, last message, next step, and due date.

The point is not perfection.

The point is output.

You learn faster by making something ugly than by watching another tutorial.

Goal for Week 3:

Have a small AI portfolio folder with real outputs.

Now you stop using AI randomly.

Create one workspace where your repeated AI work lives.

Your AI OS can include:

For a freelancer, an AI OS could look like:

clients/
proposals/
invoices/
past-work/
prompts/
services.md
pricing.md
follow-up-template.md

Then define one repeated workflow.

Example:

That is an AI OS.

A place where the work repeats cleanly.

Goal for Week 4:

Make AI part of your weekly work, not a random tab you open when you panic.

Use this:

That is enough for 30 days.

Do not add 25 tools. Do not subscribe to everything.

Do not try to become an automation agency on day 3.

Learn the order.

Build the reps.

Avoid these:

The model names will keep changing.

Your working system matters more.

You will not master all of AI in 30 days.

But you can stop being confused in 30 days.

You can learn the basics.

You can build useful context.

You can set up one AI OS that supports your work.

That is the practical version of mastering AI.

Not knowing everything. Knowing what to do next.

Now go build something great.

We read every reply - just reply to this email and let us know how we can improve !

#AD1

Last week, Viktor wrote a campaign brief, built a landing page, opened a pull request, generated a board-ready PDF from live Stripe data, and sent a follow-up email to a churned customer. All from Slack. Same colleague that also pulls your reports and monitors your dashboards. 5,700+ teams. 3,000+ integrations.

Start free. $100 in credits →

#AD2

We are living in volatile times. While you cannot control the state of international affairs, you can position your portfolio accordingly.

Liquid is one of the fastest growing trading platforms, allowing users to trade stocks, commodities, FX, and more 24/7/365 from their phone and computer.

Trade 24/7 on Liquid