Launched this week
Ito
AI code review that runs your code
879 followers
AI code review that runs your code
879 followers
Ito is an AI code review tool that runs your app before it reviews the code. For every pull request, Ito spins up an ephemeral environment, validates impacted flows, and returns runtime evidence so teams can catch bugs that static analysis and model-only reviewers miss. Instead of guessing from diffs, Ito shows what actually broke, where it happened, and why it matters before the PR reaches production.
Ito
Grayson here, one of Ito's cofounders.
I love that the hard part of Ito is often overlooked: generalizing the ability to run code is the difficult problem. Everyone assumes it's a "deciding what to test" problem (which is definitely hard too!). But the challenge of standing up an actual application is insanely hard. Get that wrong and the smartest agent in the world clicks around a broken login page.
Internal teams at DoorDash or Ramp have spent quarters of engineering time trying to build this internally because they know it's important. Most teams cannot, and shouldn't have to.
That is why runtime review didn't exist until now. Nobody wanted to build the unglamorous layer, and you cannot fake it by bolting a sandbox onto a static reviewer.
That layer is where most of our engineering was spent prior to launch, and it's the reason the reviews surface verifiable bugs instead of suspicions. Just wait to see what else we do :)
Move AI
@grayson_cooper1 What else are you going to do? I hope reply to this so you get an engagement bump. :)
Ito
@philsalesses Reliably getting an app built allows us to explore: smoke testing, demos for your how to guides & support articles, issue reproduction (datadog, posthog, etc), coding agents, design / ux feedback, performance testing, security testing, etc
The world is our oyster, but the customers will guide us
Really interesting approach! How does Ito handle cases where the app environment can't be fully reproduced because of private services, credentials, or production-only dependencies?
Ito
@monir_ If teams are unable or unwilling to provide those details, Ito will stub / mock things it doesn't have and provide that evidence back to users. Here's an example
@monir_ @grayson_cooper1 To add to this, you can configure the app environment with access to credentials & private services through the settings.
It's a neat approach that is differentiated from and complimentary to the standard AI review tools. We use it and it has surfaced bugs other tools missed on multiple occasions.
The team moves fast too and is very responsive to feedback. They are a pleasure to work with.
@daniel_kokotov Thank you!
The "complementary, not competing" framing is exactly how we think about it too. Static review tools are great at reading code; we wanted something that would go run it. Hearing that it's surfaced bugs other tools missed, more than once, is the single best signal we could ask for.
And the feedback loop goes both ways — a lot of what's shipped recently came straight from users telling us what wasn't working. So please keep it coming. It's a pleasure working with you too.
I like the ephemeral env per PR idea - less guessing from a diff
Hi, I'm Barron Caster, Co-Founder of Ito AI.
The thing I love most about Ito: gives me confidence to ship fast as a non-engineer. I've fully taken over our marketing site and don't have to bother engineers to check my code.
Vibecoding our entire marketing site & infra (design, content, performance improvements, SEO, etc)
Knows entire context of our codebase so nothing gets left behind. Can request specific tests if I want them (e.g. focus on mobile usability of the blog)
Videos of everything working for every change (and feature demo videos coming soon)
Now the whole team is shipping faster.
Easy to try and see how Ito can help your team: app.ito.ai?ph
Averi
@barroncaster congrats on the launch! ito seems like the perfect partner product to the revolution of vibe coding for those of us who aren't engineers.
Hi, I'm Geoff, a software engineer on the Ito team. 👋
The thing I love most about Ito: it actually runs the code. 🚀 Every PR I open comes back with a test plan that was
executed, not just read.
⚡ Automates the manual testing I used to do by hand — click through the flow, check the edge cases, confirm nothing else broke. That's hours back every week.
🐛 Catches bugs I would have missed. Real runtime failures that linters and static analysis structurally can't see,
because they never execute anything.
🤖 Makes agentic loops genuinely feasible. When an agent writes the code, something has to verify it actually works
Ito is that step, so I can let the loop run longer and trust what comes out the other end.
Getting to build this as an engineer who also uses it every day has been the most fun I've had on a product. 🎉
Easy to try and see how Ito can help your team: app.ito.ai
Can I run it on my local machine?
@mohsen_bashirzadeh cloud only for the moment!
Ito
@mohsen_bashirzadeh Is the goal that you have control of the testing, because you can do that from the PR description which we already take into account :)
@grayson_cooper1 Because of security.