Which course does AscentIQ cover?

IB Mathematics: Applications and Interpretation SL, completely — every topic in the syllabus, calibrated against real past papers and mark schemes. We cover one course properly rather than several superficially. Additional IB courses are on our roadmap; the Math AI SL depth is the standard we'll hold them to.

How does the marking actually work?

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.

Can the AI get the maths wrong?

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.

Do I have to write by hand?

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.

What do I need to use it?

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.

What's in the free trial?

Seven days of full access — every topic in the Math AI SL syllabus, unlimited generated exercises, and per-mark feedback on the work you write out. No card required to start — we'll ask for one on day 7 to continue.

What does "founding cohort" mean?

Founding cohort is open now and stays open based on demand, for as long as we're in this early stage of the platform. Founding members pay a reduced rate and keep it for as long as their subscription stays active, and they have direct input into what gets built next.

Subscriptions are annual and renew once a year. You can turn off renewal at any time from your account and keep access until the term ends.

IB Math AI SL · Topic 2

Functions

The spine of Applications and Interpretation. Six model families, one repeating cycle examined everywhere: choose a model, justify it, find its parameters, state a reasonable domain, and interpret predictions back into context.

What the syllabus covers

Six assessed sections, SL 2.1 to 2.6 — less algebra than AA, far more interpretation.

SL 2.1Straight linesSlope–intercept, general and point–slope forms; gradient; parallel lines m₁ = m₂; perpendicular lines m₁ × m₂ = −1.

SL 2.2Functions, domain and rangeNotation such as f(x), v(t), C(n); the function as a mathematical model; the inverse as the undo operation, reflected in y = x.

SL 2.3Graphing skillsSketching from information given or a context; transferring graphs from the GDC screen to paper; graphing sums and differences with technology.

SL 2.4Key features of graphsMaxima and minima, intercepts, horizontal and vertical asymptotes; intersections of two curves found with technology.

SL 2.5The model familiesLinear mx + c; quadratic with axis, vertex and zeros; exponential growth/decay k·aˣ + c with its horizontal asymptote; direct/inverse variation; cubic; sinusoidal a·sin(bx) + d.

SL 2.6The modelling processChoose a model in context, fit its parameters, state a reasonable domain, justify the choice from data shape and curve properties, then read predictions back out.

How it is examined

Modelling chains are Paper 2's signature — one real-world scenario unfolding over five or six connected parts.

Real papers open with extended sinusoidal models — a Ferris wheel's height over time, tides in a harbour — where you must find the parameters before you may use them.
Marks are reserved for interpretation sentences: what the asymptote means, whether the domain is reasonable, why this model fits this data.
Parameter-hunting questions expect the working that produced them, not just the values.
The formula booklet gives exactly two things for this topic: the three forms of a straight line with the gradient formula, and the axis of symmetry x = −b/2a. Everything else — quadratics solved, exponentials fitted, sinusoids constructed — is examined as GDC fluency plus interpretation.
Command terms distinguish three kinds of graph question: 'sketch' wants shape and key features freehand, 'draw' wants an accurate curve on labelled axes, 'plot' wants points marked precisely — and examiners mark the difference.
Transferring a graph from the GDC screen to paper is an explicitly listed skill: shape, labelled axes and intercepts, not a copy of pixels.

A marked question, mark by mark

A sinusoidal model built from a context, marked the way the scheme would mark it.

Drill the full modelling cycle, marked

Generated exercises across all six SL 2.x model families, marked line by line — including the interpretation sentences that static question banks can't teach because their answers are already printed.

Start free trial

New to the codes? M1, A1, R1 explained →

Sinusoidal models · SL 2.5 / 2.6

Seed 5C13

Water depth in a harbour is modelled by D(t) = a sin(bt) + c metres, with t in hours. The depth oscillates between 3 m and 9 m with a period of 12 h.

(a)Find the values of a, b and c.
(b)Interpret the meaning of c in this context.

Your work

a = (9 − 3)/2 = 3

c = (9 + 3)/2 = 6

b = 2π/12 = π/6

Marks awarded

M1Mark awarded. Amplitude taken as half the range and axis as the midpoint — correct use of the model's structure.
A1Mark awarded. a = 3, b = π/6, c = 6 all correct.
R1Mark not awarded. c reported as a number only — never linked to the mean water depth about which the tide oscillates.

Where marks are actually lost

The interpretation layer is where this topic is decided.

Choosing a model family from the scatter alone, without justifying it from the context or the data's behaviour.

CostAppropriateness is a marked judgement, not a formality.

Predicting far outside the observed data with no comment on the domain.

CostExtrapolation without a reasonable-domain statement loses the communication mark attached to it.

Reporting regression or model parameters without saying what each represents in context.

CostA parameter named correctly is a mark; a bare number is not.

Sketching from memory instead of transferring key features from the GDC screen.

CostShape, intercepts and labels are individually assessed — a generic curve earns none of them.