GPT 5.6 Luna

Write a briefing for a non-technical executive explaining why their company's spending on AI is hard to predict, and what they can do about it. Cover at least three distinct causes. Plain prose only — no headings, bullet points, or markdown formatting. Write exactly 205 words.

AI spending is difficult to predict because it combines uncertain demand, evolving technology, and usage-based pricing. Unlike traditional software, where a company may buy a fixed number of licenses, AI costs often rise with the volume and complexity of requests. A popular service, longer documents, more frequent analysis, or richer outputs can quickly increase consumption. The technology itself also changes rapidly. New models, tools, and hardware can make an existing approach cheaper, but may require new subscriptions, integration work, staff training, or migration. Forecasts can therefore become obsolete before a budget cycle ends. In addition, AI projects often begin as experiments. Some deliver value and expand quickly; others are stopped after modest spending. It is hard to know which outcome will occur in advance. Infrastructure creates another source of uncertainty. Running AI internally can produce variable costs for computing, storage, electricity, and specialized staff. External providers reduce some operational burdens but introduce price changes, service tiers, and contractual dependencies. Compliance, security, and data preparation can add unexpected expenses. Executives can improve control by separating experimentation from production budgets, setting spending limits and alerts, and tracking cost per business outcome rather than usage alone. Require pilots to define success measures and stopping rules. Negotiate clear pricing terms, review model choices regularly, and maintain alternatives among suppliers. Finally, report AI costs monthly alongside adoption, performance, and realized benefits so forecasts improve with experience.