Prompt Literacy at Work

A substantially more capable model was released 17 days ago, and the practical question in most organisations changed shape. Until March the question was whether these systems were good enough to be worth learning. Few organisations are still asking it. What replaces it is harder, because it concerns people. This paper defines prompt literacy as five things done in sequence. State a goal, supply the context the system cannot infer, constrain the task, specify the form of the output, and verify the result against something other than how the result reads. The first four are teachable in an afternoon. The fifth is where professional responsibility sits, and it is the part that no amount of prompting technique addresses. The framing matters because the market has fixed on the phrase prompt engineering, which implies that the skill is technical and belongs to specialists. The failure I observe in these organisations is well-constructed prompts producing confident output that nobody checked, which is a question about accountability dressed up as a question about technique.