verification

Agents can critique and retry their own work. The signal is knowing how Reflexion's verbal feedback loop operates, when self-critique genuinely helps versus when it is theater, and what makes it real.

The runaway loop gets all the attention. The failure that actually ships is the agent that declares victory on step 4 with half the work missing. The signal is a finish tool the harness can reject, and a completion check that reads the artifact instead of taking the model's word for it.

Code migration is a high-value agentic task with a strict correctness bar: the migrated code has to still work. The signal is grounding in the real repo, transforming in verifiable chunks, and gating on tests, never one huge LLM rewrite.

The 2025-2026 AI-fluency screen. Interviewers look for a concrete daily workflow, a real verification discipline, and a story where the AI was wrong. Vague enthusiasm fails; here is what passes.