# Sick of waiting for agents to run and then having to debug

> Source: <https://news.ycombinator.com/item?id=49141048>
> Published: 2026-08-02 04:18:24+00:00

I am an engineer and i spend so much of my time vibe coding using claude and its been great because I am able to get a lot done but its also incredibly frustrating.

I spend so much time waiting for the agents to complete running, during which time i end up moving to another task. The context switching is so tedious. For more complex tasks, I would like for it to happen without my input. I try to give it multiple steps of instructions and let it to run and it works to an extent but it doesnt work when i have to periodically test things on a separate environment (like on a pre production environment with multiple settings). I would like for it to run its own tests, look at the logs and verify that its working and then get to the next step or retry. Kind of like a feedback loop that keeps getting monitored at all hours of the day.

Are others running into this issue? And have you found any solution?

Comments URL: [https://news.ycombinator.com/item?id=49141048](https://news.ycombinator.com/item?id=49141048)

Points: 1

# Comments: 1
