Discussion

Search code, repositories, users, issues, pull requests...

antihero: And what stops it making total garbage that wrecks your codebase?

MrDarcy: Looks cool, congrats on the launch. Is there any sandbox isolation from the k8s platform layer? Wondering if this is suitable for multiple tenants or customers.

jawiggins: Oh good question, I haven't thought deeply about this.Right now nothing special happens, so claude/codex can access their normal tools and make web calls. I suppose that also means they could figure out they're running in a k8s pod and do service discovery and start calling things.What kind of features would you be interested in seeing around this? Maybe a toggle to disable internet connections or other connections outside of the container?

jawiggins: 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 anythingb) you can configure a review agent with any prompt you'd like to make sure any specific rules you have are followedc) you can disable all the auto-merge settings and review all the agent code yourself if you'd like.

upupupandaway: Ticket -> PR -> Deployment -> Incident

QubridAI: This is the right abstraction the real unlock for coding agents isn’t “better chat,” it’s persistent orchestration around the PR loop.

knollimar: I don't want to accuse you of being an LLM but geez this sounds like satire

conception: What’s the most complicated, finished project you’ve done with this?

jawiggins: Recently I used to to finish up my re-implementation of curl/libcurl in rust (https://news.ycombinator.com/item?id=47490735). At first I started by trying to have a single claude code session run in an iterative loop, but eventually I found it was way to slow.I started tasking subagents for each remaining chunk of work, and then found I was really just repeating the need for a normal sprint tasking cycle but where subagents completed the tasks with the unit tests as exit criteria.

hmokiguess: the misaligned columns in the claude made ASCII diagrams on the README really throw me off, why not fix them?| | | |

kristjansson: > to make sureyou'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.

jawiggins: Fair, it's something like a semantic enforcement rather than a hard one. I think current AI agents are good enough that if you tell it, "Review this PR and request changes anytime a user uses a variable name that is a color", it will do a pretty good job. But for complex things I can still see them falling short.

jawiggins: Should be fixed now :)

denysvitali: FWIW, a "cheaper" version of this is triggering Claude via GitHub Actions and `@claude`ing your agents like that. If you run your CI on Kubernets (ARC), it sounds pretty much the same