Back to all episodes

Code Review That Actually Runs Your Code — Evan Marshall (ito.ai)

May 19, 2026

Evan Marshall, CTO of Ito, joins Agents Hour to argue that the bottleneck of code development has moved to QA — and the tools to automate it don't exist yet. Ito is a code review tool that runs your code. It intercepts every PR, spins up the impacted user flows in an isolated sandbox, and posts videos, screenshots, and run logs back to the GitHub timeline as proof. The team is fourteen people, mostly engineers. Evan has been a professional programmer for fifteen years and previously worked at Demox Labs and Rev. With model gains flattening after Opus 4.5, the harness around the model is where value gets created. Evan shares details of Ito's "carriage" — a workflow of swarmed agents inside deterministic boundaries, designed so the system benefits from agents getting smarter without compounding probabilistic errors. He explains why bigger organizations aren't hitting the 10x code velocity the X timeline promises, and what the validation layer needs to look like before they can.

Guests in this episode

Evan Marshall

Evan Marshall

ito.ai

Episode Transcript

0:00

Cold open: It's the harness

0:26

Meet Evan and Ito

1:30

Unit tests vs the integration layer

2:11

From scraping to QA

2:59

What's a harness?

3:42

What's a carriage?

5:51

Sandboxes and task decomposition

7:16

Claude Code, Opus, and Terminal Bench

9:01

Live demo: code reviews that run your code

13:57

The enterprise gap

15:08

Audience Q: Playwright integration

16:30

How to try Ito