Launched this week

LiveReview
Free, Risk-Aware Code Review: Auto Approve Low-Risk Changes
348 followers
Free, Risk-Aware Code Review: Auto Approve Low-Risk Changes
348 followers
Most AI review tools flag issues. LiveReview promises production results: fewer incidents, fewer rollbacks, less senior reviewer load. Every PR is risk-scored. The lowest-risk 30-50% are safely auto-approved; the risky ones go straight to the engineers who should see them. The approach is inspired by Meta's highly successful internal AI review system, where production incidents fell 50x and rollbacks 3x. LLM + incident-trained ML + code-graph analysis. Free and self-hostable.







Free Options
Launch Team

AWS Startup AdvisorPersonalized AWS guidance that meets you where you’re already building
Promoted
Does Cognitive Coverage also run on the PRs that get auto-approved, or only on the ones routed to a reviewer?
@naw103 Hi Nick, thanks for checking LiveReview out! Cognitive coverage is available on every new review, whether auto approved or not.
Does anyone on your own team actually take the quiz before merging?
@leoheo It's not an enforced thing (I feel it's too much to ask), but I do take a look at it whenever I'm shipping something complex. Not for usual fixes, etc.
The slide view is something we use even more extensively from comprehension perspective.
Congrats on the launch. Can we customise some particular kind of diffs so that they go to the reviewer despite having lower risk score?
@muhammedrasin Do you have a particular example in mind?
We do have customization for increasing the importance of various dimensions such as correctness, security, performance, cloud costs, etc.
You can also specify employee levels, so interns, etc always get reviewed (until their level increases).
We are also planning "keyword based" assignment -- so if particular trigger words there it'll goto reviewers.
But if you're thinking some other way of doing this -- let me know, happy to support.
This is marvellous effort towards making review a religious practice for large organisation and the most important thing which I like the most is that user spend less time reviewing still focussing wider code level review. Loved git lrc back in days. Can't wait to try this. Congrats on launch!!!
@thinkharshh Thanks a lot, Harshit. And exactly right -- it's all about optimizing for the engineer's attention!
@lucasjpols Thank you, Lucas, for the support!
@lucasjpols Thanks Lucas <3
Very nice, congrats on the launch!
@nathan_tarbert Thank you for the support :)
@nathan_tarbert Thanks Nathan <3
how does an incident get linked back to a PR? ours show up days after the deploy, in Sentry or in a saturated db pool, and rarely point at one commit. do you read Sentry/PagerDuty or do we tag reverts by hand?
@raphael_millet2 We have both UI and API webhooks for marking production incidents/reverts. So both are possible, depending on your exact setup (happy to work with you and configure it). We do want to develop sentry/pagerduty native connections as well (on the way).