Why we bet on Convex

When we were building the AI web app builder experience for cto.new, one question kept coming up: what backend should we bet our user experience on?

We Built an AI SRE Agent in Two Days

We wanted a full-time SRE — but we're a small startup with limited resources. The ideal: a fully autonomous system that finds and fixes production issues without human involvement.

50 days of cto bench

We shipped cto bench because our friends kept asking for it. They wanted to know which models our users preferred for real software engineering tasks.

The results were often surprising.

Choosing an AI sandbox provider in 2026

Going into 2026, it’s time for an upgrade, and that means handing off our sandbox infrastructure to one of the many startups that have sprung up to specialise in this part of the stack.

Making tokens affordable

For now, LLM inference is quite expensive. It’s getting cheaper, but your near unrestricted access to the frontier of AI on a daily basis costs someone, somewhere quite a lot of money.

cto.new 2025 wrapped

Thanks for using cto.new in 2025! It’s been an incredible almost 3 months since we launched. We’re making thousands of PRs every day, we’ve used more than 300 billion frontier model tokens, shipped to over 10,000 codebases, and we’re just getting started.

Using Cursor IDE with cto.new as Your Background Agent

Cursor is an incredible IDE for local, AI-assisted development, but there's a pricing problem - especially when it comes to background agents. The solution? Connect cto.new via MCP server. This approach lets you offload heavy lifting to a free, world-class coding agent right from your primary, local IDE experience, without adding bloat.