his piece tackles a problem that’s becoming more relevant as AI tools spread into everyday work: how do you check the quality of something an AI produced, when there’s no answer key to grade against?

Research administration is risk-averse on purpose. The work navigates federal regulations, sponsor-specific terms, institutional policies, and audit trails that survive personnel changes by years. RAs have been trained well, and the training has stuck: when in doubt, slow down; when the rule is unclear, ask; when the answer is unverifiable, do not submit. That posture is not a deficit to be retrained. It is an asset the institution already has, and it should be respected as such.

The blog post explains the shift from prompt engineering, carefully wording individual requests to get better AI responses, to context engineering, which focuses on designing the entire information environment an AI uses to produce results.