Company profile · 3 min read
Chiron: math feedback while the student is still writing
iPad math-learning app using handwriting understanding and symbolic feedback.
Cofounder of Lazyweb (a16z Speedrun). Previously grew subscriptions and built native ads at Duolingo. Writes First1000 (90,000+ subscribers).
Published · Updated
Chiron is trying to make math feedback happen while the student is still writing.
What it does
Chiron describes itself as “Grammarly for Math”: an iPad app that understands handwritten mathematics and gives feedback as the student works. The YC profile says the product uses symbolic logic rather than relying only on a language model to assess the student’s reasoning.
The buyer fit is specific: students, parents, tutors, and schools that want feedback on working, not just an answer at the end.
| Fact | What the public source says |
|---|---|
| Buyer | Math learners, tutors, teachers, and education teams |
| Product | iPad whiteboard, handwriting understanding, symbolic checking, live feedback |
| Technical claim | The company says it converts strokes to LaTeX and evaluates work against a problem’s ground truth |
| Founder context | The Booth brothers are Oxford math graduates with a decade of tutoring between them |
Why it is interesting
The product is built around a real learning distinction. A student can get the final answer right for the wrong reason, or make a small mistake that a generic tutor misses. Chiron’s pitch is that the system should see the working and point to the mistake while the student is still in the flow.
That is a better product decision than “add an AI tutor.” The buyer can ask whether the app supports the kinds of handwriting, algebra, and error patterns the student actually struggles with.
The founders’ background is unusually aligned. The About page says James and Max Booth are Oxford math graduates and have tutored for more than ten years. That explains the product’s emphasis on active practice. It is not evidence of learning outcomes.
What I would resolve
The public sources say Chiron uses symbolic analysis, handles many kinds of math, and gives fast feedback. A parent or teacher still needs to know which levels and topics are supported, how the app handles ambiguous handwriting, and whether the feedback teaches or simply corrects.
The App Store availability and pricing path should be checked before recommending it to a school. The source packet links an App Store listing, but this profile does not infer current access or school procurement.
Short version: Chiron fits a learner or tutor who wants to inspect the work, not just generate a solution. The product earns attention by treating math as something to practice.
Sources checked — 2026-09-19
Cohort context
Chiron is listed in Spring 2025. In our 2026-09-18 directory snapshot, 4 of 143 listed companies in that cohort have YC’s primary industry label Education (2.8%). This is a current-directory comparison, not an original intake count or a performance ranking. Nine-cohort dataset.
Public website snapshot
Observed 2026-09-19T16:15:34.533Z in raw homepage HTML. This records visible metadata and advertised links, not agent execution or product quality.
| Signal | Homepage observation |
|---|---|
| Product description metadata | Observed |
| Canonical link | Not observed in this response |
| H1 or H2 heading | Observed |
| Typed structured data | Not observed in this response |
| Docs/developer link | Not observed in this response |
| Pricing link | Not observed in this response |
| llms.txt link | Not observed in this response |
| Markdown alternate | Not observed in this response |
Public observations · Collection method. Missing links here do not establish that a capability or file is absent elsewhere.
About the author
Cofounder of Lazyweb (a16z Speedrun). Previously grew subscriptions and built native ads at Duolingo. Writes First1000 (90,000+ subscribers).
I cofound Lazyweb and publish Mudpie. This is an owner-written publication, not an independent testing organization. Research notes distinguish observations, sourced reporting and editorial judgment.
First1000 ↗ · X ↗