Why prompt engineering was the wrong abstraction

The claim

For a couple of years, the dominant advice for getting good results out of AI was about wording: phrase the instruction better, assign the model a role, give it a few examples, ask it to think step by step. Some of that genuinely helps. None of it was ever going to be the discipline that made AI reliable inside a real business, because it was solving the wrong problem.

What prompt engineering assumes

The premise underneath most prompting advice is that the model already has what it needs somewhere inside it, and the job is just to ask correctly: find the phrasing that unlocks the right answer. That premise holds for a certain kind of task: self-contained, general-knowledge, the kind of thing a competent stranger could do with no background on your business. Summarise this. Rewrite that. Explain a concept. Phrasing genuinely moves the needle there.

Where it breaks

Most business tasks aren't that. They depend on facts a general-purpose model has no way to know: what already happened with this specific customer, what this company's policy actually says once you account for the exceptions, what "acceptable risk" means for this particular deal given its history. No amount of clever wording supplies information that was never in the prompt to begin with. You can ask a model to "be thorough" as many ways as you like; it still won't know about the conversation that happened last Tuesday unless someone tells it.

What the demos actually show

The context-brief demos on this site's Work page hold the instruction constant on purpose ("reply to the customer," "write the investigation brief," "write the clause review," "write the hiring recommendation memo," "write the handover summary for the incoming nurse") and vary only the material behind it, across three levels of curation. The quality gap between the least and most curated version in each demo is enormous, and none of it comes from wording. The instruction never changes. What changes is what the model has to reason from.

The actual skill

Once phrasing stops being the main lever, what's left is judgement: deciding which information applies to this situation, which earlier decisions are final, what to leave out, and how to turn vague instructions like "be professional" or "be careful" into concrete rules someone could check. That's a different skill from writing a good prompt. It's closer to editing, or to the judgement a good manager uses when briefing a new starter: knowing what matters here, not how to word the request.

Where this leaves prompting

Prompt phrasing is still a useful skill. It was just never the answer to reliable, repeatable AI use in a business. The problem was never the wording; it was what the model had to work with. That's a curation problem, not a phrasing one, and it needed its own name.

How context gets designed walks through exactly that judgement, worked through on a single support ticket.