IB Mathematics: AA SL · AI SL · AI HL
Write it by hand.
Marked like the real IB.
AscentIQ generates a fresh exam-style exercise every time — never from a bank — then reads your handwritten solution and awards marks the way an IB examiner does. M1, A1, R1, with a reason for every single one.
Full access for 7 days. No card required.
Sequences & series
Seed 4Q81
A gym opens with 2 members in its first week. Membership grows by 5 members each week.
- (a)Find the number of members in week 10.
- (b)Justify why an arithmetic model is appropriate here.
Your work
u₁₀ = 2 + (10 − 1)(5)
= 2 + 45
u₁₀ = 47 members
Marks awarded
- M1Mark awarded. Correct method: substituted n = 10 into the formula.
- A1Mark awarded. Correct value: 47.
- R1Mark not awarded. No justification given for the choice of model.
Why this isn't a question bank
You only solve a question once.
After that, you're remembering it.
Work a question, get it wrong, understand why — and that question is spent. Come back to it next week and you aren't doing the maths, you're recalling what you wrote. What builds the skill is the same structure with different values, again, until the method is the thing you reach for. Past papers run out. Textbook exercises run out. A generated exercise doesn't.
Static question banks
Spent after one attempt
A finite set with worked answers. Once you've seen a question it's spent — attempting it again measures how well you remember the answer, not whether you could still find it.
General AI chatbots
Confidently wrong arithmetic
They'll happily invent a number that looks right. In a subject where the arithmetic is the answer, a confident wrong value is worse than no answer at all.
AscentIQ
Computed, never generated
Every exercise is built from a seeded mathematical object, so the numbers are computed, never generated. Ten attempts at one archetype means ten genuinely different problems.
- exam archetypes
- 282exam archetypes
- IB Maths courses
- 3IB Maths courses
Each one mapped to its course's IB syllabus — and seeded, so it never repeats itself.
How it works
From blank page to marked paper.
01
Pick a topic
Choose your course and a topic from its syllabus. AscentIQ builds a new exercise on the spot — the numbers, the context, and the mark scheme are generated together.
02
Work it out on the board
Write on the whiteboard as you would in the exam — that's where method marks are awarded, step by step. Or type final answers only, for a quick check.
03
Get marked in seconds
Your work is read line by line and marked against the IB scheme. Each mark is awarded or withheld with a reason you can act on.
Marks awarded
- M1Mark awarded. Correct method: substituted n = 10 into the formula.
- A1Mark awarded. Correct value: 47.
- R1Mark not awarded. No justification given for the choice of model.
04
See what to do next
Your mastery map updates immediately. It shows which topics are exam-ready, which need work, and what to practise tomorrow.
A score you can't game.
Most progress trackers average your scores, which means enough easy questions will eventually show green. AscentIQ caps a topic at 75% until you've taken full marks on an exam-level question in it — and weights the score by how much of the topic you've actually covered. Scores also decay if you stop practising, because knowledge does.
What's inside
Built for the IB exam. Calibrated to it.
The core
An examiner, not a grader
Generic AI marking gives you a percentage and a pat on the back. AscentIQ awards individual IB marks — Method, Answer, Reasoning — against the same scheme a real examiner uses, including GDC methods where the scheme permits them. You see exactly which marks you earned, which you lost, and the specific reason for each. Follow-through is respected: one early slip doesn't cost you the whole question.
Generation
Never the same exercise twice
Exercises are built procedurally from a seed, not pulled from a bank. Ask for the same archetype ten times and the underlying object is regenerated each time — new values, same examinable structure.
Handwriting
Whiteboard and OCR
Write your solution the way you will in the exam. AscentIQ reads your handwriting line by line, and corrects only what the scanner damaged — your own mistakes stay yours, and get marked as such.
Tutoring
AI Tutor
The tutor doesn't open mid-question. It opens once your work is graded, and walks through exactly where a mark was lost and why — so there's no shortcut to lean on before you've actually tried.
Guidance
AI Coach
Open it any time for a read on where you actually stand — what's improved, what's slipped, and what's worth doing next.
After the trial
From your numbers to a plan.
Every exercise you complete adds to a topic-by-topic picture of where you stand: which marks you lose, and where. We're building an asynchronous tutoring method on top of that picture — follow-up based on your own results, at your own pace. It's still in development. If you try AscentIQ for 7 days and want to continue, tell us and we'll get back to you by email.
Or write to renzo@ascentiq.io
Built for classrooms too
- Roster your class with invite codes — students join in seconds.
- Cohort analytics with drill-down to every student's mastery map.
- Review and override any AI-graded mark before it counts.
Are you a school? Institutional access is arranged directly — get in touch.
Who built this
Built by an IB Maths specialist, for the IB Maths exam.
AscentIQ was designed and built by Renzo Diaz, who has spent years teaching IB Mathematics. The Math AI SL archetypes were mapped from the syllabus, past papers, and examiner reports by hand — 293 individual method marks annotated one at a time — and every course added since is held to the same standard. That's why the marking behaves like an examiner's rather than a chatbot's, and why the platform adds courses one at a time instead of ten superficially.
renzo-diaz.comQuestions
Before you start.
IB Mathematics: Analysis and Approaches SL, Applications and Interpretation SL, and Applications and Interpretation HL — exercises generated for each course's syllabus and marked against the IB mark scheme. Analysis and Approaches HL isn't available yet; it's on our roadmap. We add courses one at a time rather than several superficially.
Your work is transcribed, then evaluated against the exercise's mark scheme one mark at a time. Each Method, Answer, and Reasoning mark is awarded or withheld with a written reason. Follow-through is applied, so an early error doesn't automatically cost you the marks that depend on it.
The maths isn't generated by AI. Every number in every exercise is computed deterministically before the AI is involved — the AI only writes the wording around values it's been given, and is blocked from producing numbers of its own.
You don't have to, but the whiteboard is where the marking is worth most. Writing out formula, substitution, and answer lets each method mark be awarded or withheld on its own. Typing takes final answers only — quicker, but there's no working to mark, and nothing to review afterwards.
A tablet with a stylus is the best experience — the whiteboard is built for it. A laptop or desktop works fully too. We wouldn't recommend a phone: the whiteboard needs more room than a phone screen gives it.
Seven days of full access — every chapter of your course, unlimited generated exercises, and per-mark feedback on the work you write out. No card required to start.
If you'd like to continue afterwards, leave your details at ascentiq.io/continue or write to renzo@ascentiq.io, and you'll hear back by email — including about the asynchronous tutoring we're building on top of your results.
It's a tutoring method built on your results in the exercise mode — where your marks are lost, which topics are slipping, what to work on next — followed up at your own pace, without having to coordinate a live session. It's still in development, so there's no fixed format yet. If you'd like to hear how it will work, write to renzo@ascentiq.io.
Find out where you actually stand.
Seven days of full access. Every chapter, every mark explained.
Start your trial