HackerTrans
TopNewTrendsCommentsPastAskShowJobs

evanmarshall

7 karmajoined 8 lat temu
Building Agentic QA, ito.ai

Submissions

Show HN: Ito – Code reviews that run code

ito.ai
10 points·by evanmarshall·26 dni temu·8 comments

comments

evanmarshall
·9 dni temu·discuss
I want OpenBSD on blu-ray
evanmarshall
·25 dni temu·discuss
Yes, but the tests and evidence won't include screenshots, it'll be more curl requests and logs.
evanmarshall
·25 dni temu·discuss
The tooling hasn't caught up yet to code gen speeds. If we generate code at AI speeds, we need verification at AI. Bottlenecks move. If code gen was 50% of the time and now it's 0% (it's not), you only get 2x faster. Lots of people are building tools (myself included) to solve this verification problem at scale.
evanmarshall
·25 dni temu·discuss
It uses code diffs + descriptions + issues as the base test plan (acceptance criteria + regression). You can then interact with it to shape it more towards what you want.
evanmarshall
·25 dni temu·discuss
Our first POC was slow, expensive, and bad quality. It takes a lot of effort to build the infrastructure, memory layers, QA code gen fixtures and more to get it working reasonably well.
evanmarshall
·25 dni temu·discuss
Static code analysis is great but it misses a lot. Agents that read code make guesses about how code would execute, Ito makes a guess and then verifies it with runtime evidence.
evanmarshall
·26 dni temu·discuss
Cloud agents + workflows in the future. Escaping single player mode on a machine. Cursor has background agents. I build Ito.ai to do code reviews that actually run code. There's many more but the future is escaping your local machine.