Companies are no longer using AI as an experiment, they are now at a point where they view AI spending as a serious financial risk. That is why Anthropic created a budget alert feature into Claude Enterprise. This new feature includes model access control, along with warning messages when the team will exceed their budget. Vendors never create such features for customers that have historically spent money wisely.

The release came at the end of a year of companies going over their budgets. According to Axios, many executives are now asking themselves if they're actually making money with all of their high-priced AI investments. An AI consultant told Axios that one client spent roughly half a billion dollars in a single month after failing to set usage limits on employee AI licenses. Uber burned through its entire 2026 budget for AI coding tools in four months. Its chief operating officer then said the costs are getting harder to justify.

Enterprise budgets contain "cushion" that no small business has. The impact of one bad quarter for an enterprise will be absorbed by a well-crafted memo (policy) and then the company moves forward. That is not true for a 12-employee firm. If the AI costs for small businesses were treated similarly to those for Uber's (a large company), they would create payroll pressures for a 12-employee firm.

Agentic AI Broke The Cost Model Everyone Was Using

A chat-based AI had an inherent "spending" governor. People could only spend time typing. Agents removed this governor. An AI agent (as opposed to a human) working on a multi-step process can use tokens while you are sleeping, if the first attempt fails, continue to try until the process........

© Forbes