Show HN: Optio – Orchestrate AI coding agents in K8s to go from ticket to PR

Post by SR2Z » Thu, Mar 26, 2026, 3:11 AM UTC

kristjansson wrote: post #14

jawiggins wrote: post #5

Earlier quoted context omitted.

There are a few things: a) you can create CI/build checks that run in github and the agents will make sure pass before it merges anything b) you can configure a review agent with any prompt you'd like to make sure any specific rules you have are followed c) you can disable all the auto-merge settings and review all the agent code yourself if you'd like.

> to make sure you've really got to be careful with absolute language like this in reference to LLMs. A review agent provides no guarantees whatsoever, just shifts the distribution of acceptable responses, hopefully in a direction the user prefers.

Post by 59nadir » Thu, Mar 26, 2026, 5:37 AM UTC

SR2Z wrote: post #21

kristjansson wrote: post #14

Earlier quoted context omitted.

> to make sure you've really got to be careful with absolute language like this in reference to LLMs. A review agent provides no guarantees whatsoever, just shifts the distribution of acceptable responses, hopefully in a direction the user prefers.

I mean, having unit tests and not allowing PRs in unless they all pass is pretty easy (or requiring human review to remove a test!). A software engineer takes a spec which "shifts the distribution of acceptable responses" for their output. If they're 100% accurate ( snort ), how good does an LLM have to be for you to accept its review as reasonable?

Post by verdverm » Thu, Mar 26, 2026, 5:58 AM UTC

Post by smokeyfish » Thu, Mar 26, 2026, 6:22 AM UTC

pianopatrick wrote: post #24

I wonder, based on your experience, how hard would it be to improve your system to have an AI agent review the software and suggest tickets? Like, can an AI agent use a browser, attempt to use the software, find bugs and create a ticket? Can an AI agent use a browser, try to use the software and suggest new features?

Post by AbanoubRodolf » Thu, Mar 26, 2026, 6:53 AM UTC

59nadir wrote: post #23

SR2Z wrote: post #21

Earlier quoted context omitted.

I mean, having unit tests and not allowing PRs in unless they all pass is pretty easy (or requiring human review to remove a test!). A software engineer takes a spec which "shifts the distribution of acceptable responses" for their output. If they're 100% accurate ( snort ), how good does an LLM have to be for you to accept its review as reasonable?

We've seen public examples of where LLMs literally disable or remove tests in order to pass. I'm not sure having tests and asking LLMs to not merge things before passing them being "easy" matters much when the failure modes here are so plentiful and broad in nature.