AI Can Write Code. But 'Trying Things Out' Still Feels Scary
Source: Dev.to
Introduction
Recently, while working on my personal projects, I’ve noticed something. I have many ideas I want to try, and thanks to generative AI I can write code much faster than before. Yet overall development speed hasn’t improved as much as I expected. This disconnect led me to start building DevLoop Runner.
The Current AI‑Assisted Development Experience
Tools like Claude Code and Cursor provide an excellent experience:
- You can build through conversation.
- They assist your thinking.
- The implementation quality is high.
However, when I continued with personal development I hit a limitation. The workflow typically looks like this:
- Give one instruction.
- Wait for a response.
- Review the output.
- Move to the next instruction.
The wait times accumulate in small chunks, and it’s surprisingly difficult to work on something else during those intervals. As a result:
- Work progresses only sequentially.
- You still spend the same amount of time glued to the screen.
It feels as if AI has merely replaced the person typing, while the overall development workflow remains unchanged.
Psychological Cost of Personal Development
When working on personal projects we often hesitate to spend time on development that might not pay off:
- “I want to build this prototype, but I’m not sure if it’ll work.”
- “If it fails, I’ll feel like I wasted my time.”
These concerns lead us to unconsciously abandon ideas we actually want to try. The result:
- We only choose safe implementations.
- “Experimentation” and “adventure” disappear.
This isn’t a technical problem—it’s a psychological cost problem.
A Parallel‑Execution Idea
Humans think. AI can run in parallel, behind the scenes. What if we could:
- Run Issues A, B, C, D simultaneously.
- Leave them for a while.
- Review all the PRs together later.
Then:
- Merge if good.
- Revise if work is needed.
- Simply close if it doesn’t work out.
Even if an experiment fails, there’s no regret. This approach would let us include “small experiments” and “playful implementations” more freely.
DevLoop Runner Overview
There are tools where AI autonomously drives development, but I wanted something slightly different. With DevLoop Runner:
- Start from a GitHub Issue.
- AI handles requirements, design, implementation, and testing.
- Results are delivered as a Pull Request.
Key Features
- Choose when to check. Review at the design stage before implementation, or wait for the final PR.
- Delegate parallel execution. Humans focus on review and decision‑making; AI handles the heavy lifting.
The most valuable aspect isn’t raw speed; it’s making it less scary to try things out. Write an Issue for a prototype, let AI implement it automatically, and if it doesn’t fit, just close it. No need to bet your time and mental energy on implementations that might fail. This psychological safety can significantly change how personal development works.
Who Might Benefit
- You’re using AI coding tools, but things aren’t as fast as expected.
- Issues keep piling up, and you’re carrying everything yourself.
- You have ideas you want to try but can’t take the leap.
If any of this resonates, the concept of “trying things in parallel” is worth experiencing at least once.
Getting Started
DevLoop Runner is still evolving and requires initial setup (e.g., GitHub tokens). If the direction sounds interesting, try creating an Issue and let the AI handle the rest.
Now that AI can write code, what needs to change next might not be development speed, but development courage.
Humans think. AI runs in parallel. It’s okay to fail. I’m gradually experimenting with this style of development.
DevLoop Runner: https://devloop-runner.app/