Developer argues AI coding quality concerns reflect testing gaps, not AI limits
A software engineer claims proper spec-driven development and test discipline can maintain or reduce bugs while AI agents double output.
What to know
- AI coding agents can double developer output while maintaining or reducing bugs if paired with spec-driven development, automated test-driven development, and human end-to-end testing.
- The critical step is having AI review requirements and technical designs for gaps and edge cases before implementation, which the author says sharply reduced bugs in their code.
- Manual testing remains a bottleneck; this step has seen only modest productivity gains and is why output increased 2–3x rather than 10x.
i-kh.net author Software engineer and writer
How it unfolded 1 development · click the chart to see its coverage articlesposts
-
1
Developer outlines quality management strategy for AI coding agents
An engineer publishes detailed analysis on i-kh.net arguing that AI-assisted coding does not inherently lower quality if proper management practices are applied. The piece presents a layered defensive approach combining spec-driven development, test-driven development, and human validation.
“Sure, AI helps you output more code, but won't the quality suffer? It certainly will if you just blindly merge the PRs and send them off to prod. But if you take a thoughtful, layered approach to managing quality, I find that it's possible to not just keep the number of bugs stable but actually reduce it—while still increasing the output by 2-2x.”
— i-kh.net author -
I agree that agents can produce decent code. In general, I don’t find agentic code beautiful but neither is most of the code I write. The code for ingesting CSV files into my ETL pipeline doesn’t have to be beautiful, it just has to work.I think the bigger issue (like many things in software engineering) is a management issue. Once upon a time, I…
2 more of the top 3 · 24 posts in this stretch
-
I think it’s much more simple than that. It comes down to caring.I’ve had a long discussion with a coworker on a long drive.What we came to realize is the difference in our attitude towards writing code.I approach it as craft. Even when I’m doing 100% of my coding with an agent these days. I still care about the result to be of high quality and…
-
I wonder if the definition of "code quality" needs to be updated? Consider DRY: There's a lot of cases where, if I was writing by hand, I'd prefer a succinct abstraction that's easier to type and reduces repetition - all good things right? Most developers, myself included, would gladly accept the complexity and runtime cost of a good abstraction…
-
What people are saying 21 voices from 1 site · best of 24 · verbatim
- Sep 21
-
> So the best planning and implementation skills I’ve seen usually follow this pattern:> Instruct the agent to think through the test scenarios and test cases based on the requirements, Write the test cases, Write the implementation, Test the implementation against the test cases and fix any issues that come up, Maybe backfill any remaining…
-
This is the same story we got about code quality we got before, but with AI added.
-
> It's asking somebody who writes code to now read and debug others code.Writing code has always involved reading and debugging your own code, at an absolute minimum, even if you did everything solo. In any remotely serious collaborative effort, it also involved code review and collaborative debugging; people use issue trackers and assign…
-
This entire discussion can be summarized as:LLMs have speed development up so much, the difference between engineers and programmers is becoming too obvious to ignore.
-
The issue that I have with this "skill issue" argument is that it is essentially "screw you, got mine". Whether it is teaching programming or going up to making software, it has always been an intractable problem to bring experience, heuristics and intuition to words, something teachable, transferrable. Ok, senior engineers with 30+ years of…
- Sep 20
-
> I see AI introduce all sorts of bugs all the time in my personal projects that I would never introduce, and would never think to test for, especially around anything graphical.This is referred to in the need for E2E testing and E2E testing not being a substitute.Code review is definitely the biggest challenge of AI-driven development IMO. I…
-
I agree. When you write your own code, you know what your intention was when writing it. Furthermore, as you gain experience and mature you know in the back of your mind that every mistake during code writing costs disproportionately more to fix later on. You only get that feeling by owning the code. AI cannot do that. It can't have skin in the…
-
If you can explain how to reproduce a bug, you can ask the AI to debug the code and it usually works, in my experience. If not, you can ask it to add logging or other tools for better observability.
-
I completely agree. It 100% matches my experience. The C++ code I maintain now is higher quality, more maintainable, higher performance, less buggy, and faster to modify now using Claude Code.However it doesn't happen automatically. I spent a lot of time experimenting with Claude Code to figure out the right way to use it.It's a tool. Learn how to…
-
> It's asking somebody who writes code to now read and debug others code.That's exactly right. Open source projects are currently drowning under LLM generated PRs, where those who used to write code are simply punting that work to AI, but still expecting others to review it. It's not okay to expect such a free lunch. If you moved the labour of…
-
I'm quite happy with the process I've stumbled into:1) Plan the hell out of everything. Aggressively have multiple agents weigh in on that plan, in sequential waves. Don't skimp here.2) Have subagents review every code commit.3) Create tests for EVERYTHING. If something breaks you want it discovered immediately. Not just unit tests - use golden…
-
A recent HN article (below) concluded that asking agents to do TDD wasn't particularly helpful. I hope there is more research on this because TDD will be slower, use more tokens and results in more code to review.
-
I think the answer is not to debug the code, but, when possible, to debug the outputs. The code may be considered to be a black box much of the time. (This is much more true for my hobby projects than my work projects.)
-
> It's asking an author to suddenly become an editor.I think that’s right, and what is needed. It still gives a significant speed up for coding, while still keeping the output human maintainable.There is the idea that the agent will just produce binary code directly at some point. I don’t know if it ever comes to that but for now I’m in the ‘I’ve…
-
> It's asking somebody who writes code to now read and debug others code.This has been a big part of the job for anyone on a team for at least 20 years. I do agree that it’s the hardest and worst part of the job, and has now become the majority of the job for anyone who isn’t vibe coding. So, that sucks.
-
I think this is a bit of a simplistic mental approach. I've certainly seen a lot of "The engineer owns the outcome, AI is just a tool, don't release anything you don't vouch for."However, I just don't think that's realistic. It's asking an author to suddenly become an editor. It's asking somebody who writes code to now read and debug others…
-
I am getting really good results from claude. We have a 22-year old legacy system. The system is stable, but had issues as all legacy systems do. Claude has been great for modernizing the codebase, updating dependencies, auditing security, and rapidly adding new features. It has worked well with existing code style and patterns. Sometimes it is a…
-
A sibling comment talks about needing a lot of setup and context for agents to produce good code. That’s both true and bizarre.If the compiler that I write produces lousy code, I get bugs that I fix until it doesn’t.And that is the most annoying thing about this revolution. It’s obviously powerful and transformative and I use in my job all the…
-
I'd say step 0 is know your audience.I'm happily vibing my own toy projects, but would prefer if the tech in hospitals is not vibe coded.And I don't think it's plausible that the gap between those two is "well you just need to use it right".
-
Ah, the "skill issue" argument again. Same crap aswhen everyonewas worshiping Musk 5-6 years ago, this time it's dario and altman with a claude/chatgpt mask. Crash can't come soon enough.
-
I think there's a lot of setup and context required for an AI agent to consistently write good code. Once the agent has these guard rails in place I usually get great quality- far better than what I would write in most cases.I think where things get dicey is being able to write in any language. I write and review code in many languages and…