Let AI improve the system, but keep people in control
AI models are not yet truly improving themselves, but AI can already help improve software systems. The useful setup is a repeatable loop where AI builds, watches results, checks quality, suggests changes, and repeats while a person still chooses the product direction. Strong and checks are essential because they protect the code from breaking as changes pile up.
Even a working with AI benefits from a steady cycle: design, review, build, verify, integrate, collect feedback, and repeat. Making live changes on the fly is risky because it can create chaos, especially as a product grows. Connecting the codebase to a project management tool like Linear and to a gives AI clearer boundaries and better context.
Monitoring and feedback should compare the product’s behavior against the original . stores and telemetry give the system evidence for deciding what to improve next.
Key points
- AI can help run a loop of building, monitoring, judging, proposing changes, and repeating.
- A person should still control the product direction and final decisions.
- and checks are needed to keep the codebase stable.
- A design, review, build, verify, integrate, and feedback cycle is safer than live improvisation.
- Project management, a , monitoring, , and telemetry give AI better context for useful improvements.