Validating agentic behavior when “correct” isn’t deterministic
How to build the “Trust Layer” for Github Copilot Coding Agents without brittle scripts or black-box judgements by using dominatory analysis.
Student Researcher (former), Microsoft Code | AI. I am a PhD student at UW focused on improving the reliability and maintainability of LLM agents, using best practices from traditional software engineering.
How to build the “Trust Layer” for Github Copilot Coding Agents without brittle scripts or black-box judgements by using dominatory analysis.