AI Philosophy

How I use AI as a development tool.

I use AI to move faster on the mechanical and exploratory parts of development. The decisions that carry real risk — architecture, security, correctness — stay with me.

Where AI Does The Heavy Lifting

  • Researching unfamiliar APIs, libraries, and implementation patterns.
  • Drafting boilerplate, test scaffolding, documentation, and examples.
  • Comparing refactoring options before final implementation decisions.
  • Handling repetitive tasks so I can spend more time on higher-risk work.

Where I Step In

  • Security-sensitive code, authentication, permissions, and data handling.
  • Business rules that depend on real stakeholder context and constraints.
  • Architecture decisions with long-term maintenance costs.
  • Ensuring compliance and regulatory requirements such as GDPR, HIPAA, and others.

My review standard

AI-generated code gets the same scrutiny as anything a developer on the team writes — effectively, it is advanced code-completion. Every output has to clear three questions before it ships.

Correctness

Does it actually solve the requirement, handle edge cases, and behave correctly under realistic conditions?

Maintainability

Will another developer understand it later? Does it fit the project’s existing patterns and constraints?

Risk

Does it introduce security, performance, licensing, privacy, or operational problems?

The bottom line

Tools change how fast the work gets done. They do not change who is accountable for it. That accountability is mine, and I do not hand it to a model.