debug-like-expert

Systematic debugging uses hypothesis-driven investigation: observe symptoms, form testable hypotheses about root causes, run controlled experiments to isolate variables, and verify fixes rigorously. This methodical approach replaces trial-and-error with evidence-based problem solving across multi-language codebases.

Root-cause analysis requires evidence gathering through logging, tracing, and environment inspection to test competing hypotheses. Minimal reproduction isolates the problem, controlled experiments eliminate variables, and domain-expertise loading surfaces context-specific patterns that reveal why standard steps missed the issue.

Research applies when you lack context about the problem domain or error category; testing applies once you've formed a specific hypothesis worth verifying. Efficient error resolution balances research phases—loading domain expertise—with controlled verification patterns, minimizing rework and downtime.

Yes. This approach handles multi-language codebases and AI workflows by using hypothesis-driven investigation, minimal reproduction, and rigorous verification regardless of whether issues stem from code logic, configuration, or AI component interactions.

Logging, tracing, and environment inspection are core strategies for collecting evidence. These techniques capture execution flow, state changes, and environmental context, enabling you to reconstruct what happened before an error and pinpoint where assumptions broke down.