How to set token budgets and spending limits for AI agents.
A spending limit an agent cannot exceed sits in the path its calls take. How to set caps by organisation, team and agent, with a named approver.
- Topic
- AI cost
- Product
- Novie Control
- Format
- Guide
- Reading time
- 4 min
To set a spending limit an AI agent cannot exceed, put the cap in the path its model calls take, where it can stop a call before the call is paid for. Set a ceiling for the organisation, an allocation for each team, and a cap for each agent and each person, in dollars per period. Decide what happens at the cap before it is reached, and name the person who approves an increase.
Token budget, spending limit, cap
A token budget is the number of tokens an agent may use, per task or per period. A spending limit is the same idea in dollars. A cap is the point at which something happens: the call stops, slows, steps down to a cheaper model, or waits for a person.
Set limits in dollars. Tokens are priced differently by every model and every provider, and differently again for input, output and cached tokens. A limit of a million tokens means one amount on a small model and many times that on a frontier one. Dollars are what the budget is written in, so they are what the cap should hold.
Why agents overspend
A person using a chatbot spends in small, visible steps. An agent spends on its own, at machine speed, and nobody is watching the meter at three in the morning. The usual causes are ordinary.
- Loops. An agent retries a step that keeps failing, and every retry is a paid call.
- Context that grows. Each turn carries the whole conversation, so the cost per step rises as the task goes on.
- The default model. A workflow built on the largest model during a demo keeps using it in production for work a smaller model would do.
- Agents calling agents. One request fans out into many calls across several models, and the total is visible nowhere.
Agents also use far more than a person does for the same job. The FinOps Foundation reported in May 2026 that reasoning and agentic workloads consume five to thirty times more tokens per task than the equivalent chat interaction.
Why caps became a board topic this year
In June 2026, Uber capped spending on AI coding tools at $1,500 a month per employee for each tool, after its chief technology officer said the company had used its full-year AI budget in about four months. Uber confirmed the cap, TechCrunch reported.
At the end of July, the Financial Times reported internal Amazon presentations describing AI projects that overran their budgets. The largest cost $1.8 million, 860 percent over its allocation, and the overspend went unnoticed for about five months, according to TechRadar's account of the report.
These are not isolated. In research by the cost-management firm Mavvrik among 396 enterprises, reported by CIO Dive in August 2026, a third of companies had imposed emergency spending freezes after AI costs surprised them. KPMG's Q2 2026 AI Pulse Survey found 36 percent of large US enterprises had direct token or usage controls in place.
Where to set limits
- The organisation ceiling. The total AI spend the business has approved for the period. It should be impossible to exceed without a decision.
- The team allocation. Each team's share of the ceiling, owned by its lead.
- The agent and person cap. A limit per agent, and per person for tools that spend on an individual's behalf, so one runaway process cannot spend a team's month.
- The task limit. A token budget per run, so a single task that goes wrong stops after a known cost.
What happens at the cap
Choose the behaviour per agent, by asking what breaks if it stops.
- Stop. Right for experiments and for agents whose work can wait until tomorrow.
- Slow. Queue new runs until the period resets. Right for batch work.
- Step down. Route the next calls to a smaller model. Right where a cheaper answer is better than none.
- Ask. Pause and send the request to the named approver. Right for agents in a customer or revenue path, where stopping costs more than the overage.
Increases: who approves, and how fast
Every increase has a named approver, a reason and an expiry. A temporary uplift for a month-end run should end at month end on its own. Approval should take minutes, because a cap that takes a week to lift will be routed around, and the workaround is the next ungoverned agent.
A one-page policy
- The ceiling: the organisation's AI spend for the period, and who set it.
- The allocation: each team's share, and the lead who owns it.
- The caps: per agent, per person and per task, in dollars.
- The default at the cap: stop, slow, step down or ask, set per agent.
- The approver: who can raise each cap, and the expiry every increase carries.
- The review: when the limits are reset, and who reviews the overruns.
How Novie Control does it
Novie Control is live. Every dollar visible. Every budget governed. Every call optimised. Every agent governed. Caps hold before spend is committed, at organisation, team and project level, with a named human on every increase. Every AI dollar is traced to the team, the project and the owner at the moment it is spent. Each call is routed to the model that should take it, so a cap can step down to a cheaper model before it stops anything.
Sources
- TechCrunch, Uber caps employee AI spending after blowing through budget in four months (2 June 2026)
- TechRadar, Amazon quietly burned $1.8 million on an AI coding project that went horribly wrong (4 August 2026), reporting the Financial Times
- CIO Dive, Surprise AI costs threaten enterprise implementations (6 August 2026), reporting Mavvrik research
- KPMG, AI Quarterly Pulse Survey Q2 2026 (24 June 2026)
- FinOps Foundation, Token Economics: The Atomic Unit of AI Value (10 May 2026)