Raghav Jalan

Jaipur, India

All work

2 of 6

PAI Learn

A teacher that asks before it answers.

Role
Co-founder & technical lead
Status
In development, co-founder, 2026
Platform
Installable web app
  1. Child types
  2. Input screenClaude Haiku
  3. Rules enginePicks the kind of help: a prompt, a hint, a stronger hint, or a fresh explanation
  4. Claude SonnetWrites only within those limits
  5. Answer-leak checkEvery reply is checked before a child sees it
  6. Child

In short

Who it’s for
A young child learning maths, and the parent who wants them to truly understand it.
What was hard
“I don’t understand” can mean very different things, and most tools respond to all of them the same way.
What I decided
Understand before teaching: a rules engine chooses the kind of help, the AI writes only within those limits, and every reply is checked before a child sees it.

The person who once taught in my school is now the person I’m building with.

In 2020, Shariq Khaleel came to my school to run a workshop. I was one of the students in the room.

I didn’t know then that it was the start of something. He became my mentor, and we stayed in touch as I taught myself to build software. Over the years, the student in the audience slowly became someone who could build what he imagined.

In 2026, we started PAI Learn together. Shariq leads education and product from Doha. I lead engineering and AI from Jaipur.

The idea comes from years Shariq spent working with children. He kept seeing the same thing: a child would look unable to learn something, and then make progress the moment the explanation, the pace or the activity changed. The hard part was never explaining. It was working out which change that child needed.

So PAI is designed to understand a child before it teaches them. We’re starting with maths for younger children. When a child says “I don’t understand fractions,” one child might think 1/4 is bigger than 1/3 because 4 is bigger than 3. Another might understand perfectly and just need more time. PAI asks first, makes a careful guess, watches what happens, and changes course if it got the child wrong.

Building that safely is my job. PAI isn’t a chatbot let loose on children. A rules engine decides what kind of help comes next: a prompt, a hint, a stronger hint, or a fresh explanation. The AI writes only within those limits, and a second model checks every reply before a child sees it, so it never simply hands over the answer. It’s tested by more than 850 automated checks, and by red-team tests that actively try to make it fail.

We’re honest about where we are: PAI Learn hasn’t launched yet. Our next step is to put the first version in front of a small group of children, with their parents’ permission, and find out whether it really helps.

There’s something I find quietly remarkable about this one. The person who once stood in front of my class is now the person I’m building a company with.

“PAI isn’t a chatbot let loose on children.”

How it works

Installable web app (React, TypeScript, Vite) on AWS: Node.js on Lambda, PostgreSQL with pgvector, separate sign-in for students, parents and operators, all defined as code. AI runs through Amazon Bedrock. Claude writes within the rules engine’s limits, and a second Claude model screens what a child types and checks every reply for answer leaks.

  • React, TypeScript and Vite
  • Node.js on AWS Lambda
  • PostgreSQL with pgvector
  • Amazon Bedrock (Claude)
  • Playwright

The proof

automated tests
850+

850+ automated tests, Playwright at phone, tablet and desktop sizes, and red-team suites against the real models.

What I learned

In a product for children, what the AI is not allowed to do matters as much as what it can do.

An idea that won’t leave you alone?