Finding It Challenging to Maintain Software Created with Coding Agents? | Hacker News Reader

Finding It Challenging to Maintain Software Created with Coding Agents?

9 pointsnlpnerd8 comments

We do have in place proper PRDs and system designs and implementation plans that we feed to the agent.

I'm an MLE and SWE, so it's not like I can't read code or don't know any proper practices. What is different though are that

Since we are not spending 6-8 hours a day working with the code base unlike pre-coding agents, we lack the indepth knowledge and intuition that helps us narrow down root cause when bugs arise, or know how to best extend the current code base to support a new feature

Because of the productivity from coding agents, the size of the code base and sophistication of the app relative to number of developers has also increased. Each developer now needs to maintain context and understanding over a greater surface area and number of micro services. Over time this makes reviewing extension to the app and code base increasingly more difficult cognitively.

Anyone else dealing with this too? Is it just a problem with our engineering processes? What works for you?

I feel this one. I've shipped more lines of code in last six months than in last 20 years combined and I've not written a single line of code by hand, I think I have'nt written any code since Thanksgiving of 2025, I think I am not alone in thinking that that's when ground shifted and there was no gong back anymore. I also think PR Reviews are not adding any value anymore, I mean the velocity of code is too much for a human to eyeball code, it just cant be done. I am curios to see what industry will come up with, all these AI code reviews seem oximorons to me TBH.

I'm about to try Matt Pocock's skills for more rigorous agentic engineering now that my code base is climbing towards 100kloc, but can't yet testify to their effectiveness. People I trust swear by them: https://github.com/mattpocock/skills

My first statement would be that surely the challenge you are experiencing is pretty similar to what Ford has reported around its recent AI adoption.

https://news.ycombinator.com/item?id=48674446

Well...we didn't sack anybody if you were wondering. I feel like Ford's issues is mainly overestimating AI's capabilities. Whereas our case is more of a need for re-engineering processes to be more AI-native.

If you cannot maintain it, the agent has to maintain it.

If the agent cannot maintain it, you are lost.

That's kind of stretching things. It's not that software cannot be maintained but the cognitive load of building and maintaining software seems to be now backloaded to the maintaining part and people need to be aware of this.

It will get much worse before anyone wakes up to this problem.

Yeah

Reply on news.ycombinator.com