Learn: a lesson a day
Five-minute lessons that build on each other. Spot the made-up number, fix the request that caused it, and learn what works. Anything you miss comes back until it sticks.
Free while in early access
Speak the language of AI. Five minutes a day.
Short lessons that feel like a game, a simulator where you direct an AI agent and catch its mistakes, and a coach for the AI work you really do.
- 48bite-sized lessons
- 16real work cases
- 10–160adaptive test score
Try one · catch the AI's mistake
An AI wrote this for your CEO. What do you do before sending it?
"Q3 churn hit 12% — 3 of our 40 accounts left. That is more than double the 5% industry average."
How it works
Learn it. Practise it on an AI agent. Get coached on the real thing.
Simulate: direct an AI agent
Real jobs done by an AI agent — with the mistakes agents really make planted in them. Brief it, decide what it's allowed to do, and catch what's wrong before it reaches anyone.
Coach: on your real work
Paste a conversation you had with ChatGPT, Claude or Copilot. See what you checked, what you didn't and what you shouldn't have shared — and the lesson that fixes each gap.
Prove it: one score
A 20-minute test that adapts to your level. One score from 10 to 160, broken down into four skills, that you can share. Retake it every two weeks and watch it climb.
Streaks that count practice, not visits
XP only for right answers and real work
Weekly leagues, and leagues for your team
Review aimed at your weakest skills
What you'll learn
From your first request to work you can trust
Four sections, 16 units, about five minutes a lesson. Each section builds on the one before.
Section 1
Ask for what you want
- What makes a good request
- Give it the background
- Set the reader, length and format
- Hand off the work, keep the judgment
Section 2
Keep it to the facts
- Stick to your sources
- Get the numbers right
- Turn messy notes into clear answers
- Watch for hidden instructions
Section 3
Check before you send
- Spot made-up facts
- Quick checks that catch mistakes
- Know when to trust it
- Review it like an editor
Section 4
Make it repeatable
- Write instructions you can reuse
- Break big jobs into steps
- What never to paste into AI
- Turn a one-off into a routine
If you use AI at work
Sound familiar?
Now
Every week you type the same request into ChatGPT, worded a little differently each time.
With Tokolingo
You write it well once, then reuse it every week with your files and standards built in.
Now
The answer sounds right, so you send it — without really knowing what it got wrong.
With Tokolingo
A quick check flags anything your own files don't back up, before it goes out.
Now
Someone asks how you made it, and the honest answer is: I kept tweaking until it looked right.
With Tokolingo
You have clear written steps you can share with your team, improve, and rerun in ten minutes.
Your first real task · about 30 minutes
Bring a real task. Leave with three things.
The finished work
Your actual status update, research summary or report, with every claim checked against your own files. You know what’s safe to send before you send it.
Steps you can reuse
Five short answers that make it work: what to attach, what to ask, what good looks like, what to check, and what never to paste. Pick a day and it’s ready for you again next week.
Proof it’s working
Your score before and after, and every run timed against doing it by hand — so you see the hours saved and the mistakes caught before they went out.
Start with the task that eats most of your week
- A status update
- A research synthesis
- A report for executives
- A spec or a brief
- A digest someone else reads
- An analysis of numbers
Real work, step by step
Try it first. Learn exactly what you need.
No studying up front. You try the real task, and whatever goes wrong decides the lesson you get next.
- 01
Cold run
about 5 minutesDo the job with no help at all.
Five minutes shows exactly where you struggle — no guessing — and that decides the one lesson you get next.
- 02
Repair
We highlight what the material doesn't back up.
A score tells you how you did. A highlight on your own words tells you what to change — and each one links to the lesson that fixes it.
- 03
Warm run
The same job again, with hints, a coach and a worked answer.
This is where the real document gets made, and where you see whether the fix worked. Revise and resubmit as often as you like.
- 04
Keep it
10 secondsSave your steps and pick when you'll need them again.
This is what you still have next Monday. Everything before it proves the steps work; this makes them come back when you need them.
Feedback on your own words
See exactly what to fix
A score tells you how you did. Highlights on your own sentences show what to change — and which claims you shouldn’t send.
The team resolved most blockers this week1 and the migration is nearly done2.
Sign-ups are up to 1,240 this month, from 9803.
- 1. Your notes don’t say how many. If it was two of seven, that isn’t “most”.
- 2. No date given. “Nearly done” is what it said last week too.
- 3. Both numbers match the sign-up dashboard. Safe to send.
Good AI work is more than a prompt
Five parts. Only one of them is the prompt.
AI gets better at understanding prompts every year. The other four parts don’t get easier, and they’re where work actually goes wrong.
- Sources
What gets attached every time — and what deliberately doesn't?
Without it you paste whatever is nearest, and the AI fills the gaps with guesses.
- Instruction
The prompt you send, every time.
A vague request gets a confident answer in the wrong shape, and you fix it by hand.
- Done
What must be true of the output before you'd accept it?
Decide this before you look, or you'll end up accepting whatever came back.
- Check
What do you verify before any of this leaves the building?
Skip it and the invented number goes out with your name on it.
- Owner
Who is accountable, and what never goes in?
Nobody owns it, so nobody catches it — and confidential text leaks by habit.
01
02
03
04
05
Beyond the daily path
7 deeper paths and 36 longer lessons
When something goes wrong on a real task, you get the longer lesson that fixes it — about eight minutes, then straight back to work.
- AI Foundations for Professionals
- Prompt Craft: From Vague to Precise
- Verify & Trust AI Output
- Automate Your Week
- Directing AI Work
- AI-Powered Product Thinking
- AI for Marketers
Plus guided walkthroughs, on real material
8 screens · 14 min
Raw notes to product bets
Three contradictory user interviews and forty minutes before a roadmap review. Produce a memo where every claim traces back to a quote.
6 screens · 12 min
Audit a shaky report
An AI-drafted investor update with invented numbers in it. Find them, prove they are wrong, and rewrite it before it reaches the board.
5 screens · 10 min
Weekly status in ten minutes
Scattered team updates into a status email your VP will actually read, ending with the prompt you reuse every Monday after.
Looking at this for a team? Team groups are free: a shared league, and a dashboard of who practised and what their real work saved. See how teams work.
FAQ
Questions, answered
Your first lesson is five minutes away
Take a quick placement to find your level, then start the path and watch your score climb.
Start learning