AI engineering

AI accelerates the work. It does not own the decision.

I use GitHub Copilot in VS Code for production engineering and OpenAI Codex for independent work. Repository instructions, reusable prompts, structured handoffs, and custom tools make the work repeatable—not automatic.

Operating principle

Generated output is a draft, not a decision.

Applied, not ornamental

Useful across the delivery path.

AI is most valuable when it is grounded in the codebase, contracts, constraints, and evidence already present.

Codebase inspection
Story decomposition
API-contract and data-path validation
Feature-flagged spikes
Security remediation
Infrastructure automation
Runbook and documentation generation

Review loop

A disciplined path from context to confidence.

01Inspect the relevant context
02State assumptions and open questions
03Decompose the work and its risk
04Generate or modify code
05Test behavior
06Inspect dependencies
07Review security and standards
08Assess maintainability and architectural fit
09Document changes and remaining uncertainty

Example: feature-flagged UI spike

Turn an underspecified integration into testable work.

For a production UI integration spike, I broke an ambiguous story into explicit steps and open questions. AI helped inspect API shapes, exercise parameter combinations, and validate data paths involving APIs and Azure Blob Storage before implementation.

The value was not a burst of generated code. It was faster clarification, broader validation, and a smaller set of unknowns entering implementation.