# A content engine that writes 90% of Coderhouse

By Valentin Galfré · 2025 · Platform and AI · https://galfrevn.com/work/coderhouse

Role: Staff Engineer, technical lead for platform engineering and AI.

Coderhouse is one of Latin America's largest edtech platforms, with 500k active students. Since September 2025 I lead its platform engineering and AI initiatives, and the biggest piece of that is the system that now produces most of the platform's educational content.

## Story

- **Problem.** Producing educational resources for hundreds of courses was slow and manual, and infrastructure had to hold up under peak demand of tens of thousands of concurrent students.
- **Solution.** I designed and shipped multi-agent AI systems that generate resources across text, images and audio, with structured outputs and evals so quality is measured rather than assumed. In parallel I defined a distributed infrastructure architecture built for resilience and high availability.
- **Outcome.** Thousands of educational resources are generated automatically every day, and the platform serves 50,000+ concurrent users through peak demand. Engineering standards around reliability, maintainability and performance were adopted organization-wide.
- **Impact.** The AI systems power 90% of the platform's content production.

## How a resource gets made

A brief comes in: a course, a lesson, what the student needs to walk away with. A planner agent turns it into a structure. Writer, illustrator and narrator agents produce text, image and audio in parallel. Nothing is published until it passes evals that score it against the brief.

## What it took to trust it

The hard part of a system that writes most of what a platform publishes is not generation. It is knowing when the output is good without a person reading every piece. Structured outputs made every result checkable. Evals made quality a number that trends instead of an opinion that varies.

> **Bar.** A model earns its place the way any dependency does. It has to be measurably better than the alternative, and it has to stay that way.

The infrastructure underneath had to hold the same standard: designed for peak demand, resilient by default, observable enough that a regression is a ticket for one team and not a meeting for five.

## Around the work

## Links

- [Coderhouse](https://www.coderhouse.com)