Alex Sandruk
Published Updated
AI code review needs verification loops
Why AI code review should end in a check against the real system, not a confident comment thread.
Writing
Practical notes on AI engineering, platform work, and operator-grade delivery systems. Start here for the reader path; continue into related posts, tags, and About before using hiring pages.
Alex SandrukPublished UpdatedAI human distillation
A short note on using AI to compress human context without sanding off judgment, voice, and uncertainty.
Alex SandrukPublished UpdatedVerification loops for AI agents
An AI agent's claim is useful only after it is tied to a check the real system can pass.
Alex SandrukPublished UpdatedDecision records for AI agents
How lightweight decision records keep agent work recoverable without turning every chat into a source of truth.
Alex SandrukPublished UpdatedGitOps does not end at push
In a multi-machine agent workflow, pushing to origin is only the first half of keeping work recoverable.
Alex SandrukPublished UpdatedRuntime flight recorder for agent work
A note on keeping agent runtime inspectable without pretending Git is the whole memory system.