Anna Neumann, Holli Sargeant, Jatinder Singh
Generative artificial intelligence (GenAI) is increasingly operated by natural language instructions (prompts). Across the pipeline, stakeholders designate various forms, e.g. end-user guidelines, developer specifications, or system prompts, as prompt governance instruments. These textual artifacts are intended to shape model behaviour by specifying constraints, priorities, and compliance rules. Policymakers and regulators have begun to treat system-level instructions as accessible prompt-based GenAI intervention points, assuming they function (directly or indirectly) as behavioural control. Yet whether these instructions operate reliably and predictably enough across contexts to support such governance frameworks remains underexplored. Towards this, we systematically evaluate (i) how researchers discuss and treat system-level instructions in the literature, focusing on large language models (LLMs) as they isolate language effects; (ii) how policymakers position system-level instructions as governance objects, incorporating analysis of two policy frameworks (US Exec. Order on Preventing Woke AI, and EU General-Purpose AI Code of Practice); and (iii) whether misalignments between these perspectives warrant closer inspection of the viability of governing AI through natural language. We identify a fragmented literature advancing varying and contradictory claims about what goals system-level instructions can achieve, which we distil into a typology of claims. Further, we show how divergent claims complicate policy approaches that treat system-level instructions as stable, interpretable control mechanisms. We argue that given such misalignments, careful consideration must be given to prompt governance approaches. Our findings have broad implications, extending from a LLM policy context to the use of natural language as control mechanism in technical systems more generally.