| ▲ | behat 2 hours ago | |
> They want extension to their agent. If a project tells me I have to use their interface or agentic setup, it's 95% not going to happen Yes, there’s definitely friction there. It may be that the right form factor is that you trigger Relvy’s debugging agent via Claude code / Cursor . Our early users are heavy on needing to look at the raw data to be able to review the AI RCA, so a standalone set up makes sense. Also, the dominant usage pattern is background agentic execution triggered by alerts, and not manual. | ||
| ▲ | verdverm 2 hours ago | parent [-] | |
Yup, we are moving up the ladders of abstraction and will have our agentic team interfaces that include agents triggered outside of human input. It does not change things. As soon as I need to go into the code or to the agent to fix the problem, I'm back to copy and pasting, or switching to view, between multiple interfaces. That's the kind of stuff we loathe Runbooks are great and all, but actions need to be taken and I'm not going to give all the vendor interfaces to the internal systems. They can be subagents in my system which already has the tools and permission gates needed, access to code and git for IaC changes, etc... It seems like the way to go now, it's easier to get moving and show off an experience and the vision, but it's definitely not the operational way in prod for a lot of reasons, security being a paramount one. I also do not discount that your SaaS can be easily replaced by an open sourced subagent team in the next couple of years. | ||