AI coding tools can now write features, edit multiple files, debug code, run commands, and generate tests.
But while researching how developers use these tools, I keep seeing the same question:
Are AI coding tools actually saving us as much time as they should?
The models are becoming more capable, but developers still seem to spend significant time managing context, checking changes, watching usage limits, choosing models, and explaining the same project information again.
I’m trying to understand whether these are widespread problems or just isolated experiences.
Long AI coding sessions can sometimes lose direction.
The AI may forget earlier decisions, misunderstand project conventions, suggest previously rejected approaches, or require the developer to explain important context again.
This makes me wonder:
Should project knowledge disappear when a chat session ends?
Would it be useful if the development environment could preserve relevant architecture decisions, coding conventions, previous bugs and fixes, failed approaches, current tasks, and next steps?
Writing code is only one part of development.
An ideal agent workflow might look more like:
Understand → Plan → Edit → Run → Test → Fix → Verify
But how autonomous should that process be?
Should the agent complete the entire loop independently, ask before risky actions, or wait for approval at every major step?
Developers now have access to many models, but choosing between them can become another task.
Should developers always choose models manually, or should the development environment select an appropriate model based on task complexity, quality requirements, privacy, speed, and budget?
Usage limits are another concern. Some developers report difficulty predicting how quickly their allowance is being consumed.
Would real-time usage visibility, spending limits, local model support, or BYOK actually improve the experience?
For complex development work, which approach is better? Specialized agents could improve focus and review quality, but they could also increase cost, complexity, and coordination overhead.
I want to understand what developers actually prefer.
I created a short 2–3 minute survey about real experiences with AI coding tools.
It covers:
Survey: https://forms.gle/aNwYASCHYqVYcjwg7
No personal information is required.
If you don't want to fill out the survey, I'd still love to hear your answer in the comments: What is the single biggest thing in your current AI coding workflow that wastes your time?
And the opposite:
What does your current AI coding tool already do so well that you would never want to lose it?
I'm interested in both positive and negative experiences.
The goal isn't to prove that current tools are bad. It's to understand what developers actually need next.