---
title: "Spend Limits: Enforceable Ceilings on AI Cost at Three Scopes"
slug: "spend-limits"
date: "2026-08-24"
tag: "Application"
summary: "LLM spend caps now exist at three scopes — the whole workspace, a single agent, and one person on one agent — each with its own reset period, an enforcement mode that blocks or alerts, and near-limit alert thresholds. Enforcement is server-side."
author: "ibl.ai Engineering"
linkedin: |
  Every organization running AI at scale hits the same question, usually after the invoice: what stops one runaway agent from spending the quarter's budget in a weekend?

  Per-seat SaaS answers it by charging you a fixed amount per person whether they use it or not. That's not a spending control — it's a floor. You've capped the downside by guaranteeing the cost.

  We shipped the other answer this week: enforceable spend limits at three scopes on ibl.ai.

  → Workspace-wide. One ceiling covering everything every agent and every user consumes.
  → Per agent. Each agent gets its own cap, and the tenant view lists every one of them in a single table with spent and remaining.
  → Per user, per agent. One heavy user can be limited without lowering the ceiling for everyone else.

  Each limit carries a reset period (day, week, month, year), near-limit alert thresholds, and — the part that makes it a control rather than a dashboard — an enforcement mode. Block Requests refuses new work once the ceiling is hit. Alert Only lets the work continue and tells the administrators. Enforcement runs server-side, so it holds no matter what client is calling.

  And before you set a number, the workspace tab shows you what you have actually spent this month and all time, so the ceiling is grounded in real usage rather than guessed.

  The reason this shape is even possible: on ibl.ai you own all the code and the data. Usage-based billing you can actually cap is what you get when the meter is running inside your own perimeter instead of on a vendor's per-seat price list.

  #iblai #AgenticAI #EnterpriseAI #FinOps #AICost
---

Spend limits are now a first-class control on the platform. An administrator can put an enforceable ceiling on LLM spend at three scopes — the whole workspace, a single agent, or one person on one agent — and decide, per limit, whether reaching it stops the work or simply raises an alarm.

The three scopes stack. A request has to clear every limit that applies to it, so the tightest one governs.

## A cap on a single agent

![The Billing panel on the This Agent sub-tab, showing the enable toggle, a monthly usage strip with spent, percent used, and remaining figures, the spend limit field, the reset interval, the enforcement mode, and the alert thresholds](/images/updates/spend-limits-agent.webp)

Every agent now has a **Billing** panel in its settings. A cap is an amount, a reset period — **Day**, **Week**, **Month**, or **Year** — and a decision about what happens when the amount runs out.

Once a cap is saved, the panel shows spend against it every time you open it: a progress bar that runs blue, turns amber at 80% of the limit, and goes red once it is passed, alongside the spent, percent-used, and remaining figures.

**When the Limit Is Reached** is the consequential field. **Block Requests** refuses new chat and training requests until the period resets — a hard stop. **Alert Only** lets the work continue and alerts administrators instead. Enforcement is server-side, so a blocked request fails for every client, with a distinct error code that can be told apart from a provider rate limit.

**Alert At (% of Limit)** takes a comma-separated list of percentages, `80, 95` by default, and fires under either mode. That is what gives an administrator time to act before a hard block lands on someone mid-conversation.

## A cap on one person

![The Per User sub-tab, showing an Add User Limit button above a table of per-user caps with User, Limit, and Status columns](/images/updates/spend-limits-per-user.webp)

The **Per User** sub-tab holds explicit limits for named people on this agent. Each row shows the person by email, their limit written as amount and period, and a status toggle that saves immediately.

![The New User Limit modal, with the platform-user search above the spend-cap fields](/images/updates/spend-limits-new-user-limit.webp)

Adding one starts with a search across real platform accounts rather than a free-text field, so a limit can never be attached to a name that does not exist. A per-user limit narrows one person's share of the agent's budget — their spend still counts toward the agent's own cap.

## A ceiling on the whole workspace

![The Spend Limits tab on the organization's Billing page, showing the workspace-wide cap with its usage strip, spend limit, reset interval, enforcement mode, and alert thresholds](/images/updates/spend-limits-workspace.webp)

The organization's **Billing** page grew from one tab to three. **Spend Limits** is the widest scope: one ceiling covering everything every agent and every user spends.

Before a limit exists, this tab shows what the workspace has actually spent — this month and all time — so the number you pick is grounded in real usage rather than guessed at.

## Every agent's cap in one table

![The Agent Limits tab, showing an agent search above a table of every agent with a spend cap, listing Limit, Spent, Remaining, and Status](/images/updates/spend-limits-agent-limits.webp)

**Agent Limits** is the cross-agent view: every agent in the workspace that has a cap, with what it has spent and what is left, in one table. The status toggle turns a cap off without deleting it, and searching for an agent that has no cap yet offers to set one.

![The Manage popup opened from the Agent Limits table, showing that agent's own Billing editor inside the dialog](/images/updates/spend-limits-agent-limits-manage.webp)

**Manage** opens that agent's full Billing editor in place — both sub-tabs, per-user limits included — so an administrator can work through every agent in the workspace without navigating into each one.

## Documentation

- [Agent Settings: Billing](/docs/os/agent-settings/billing) — the per-agent and per-user scopes
- [Organization Settings: Billing](/docs/os/organization-settings/billing) — plan and credits, the workspace-wide limit, and the cross-agent table

The same surfaces ship in the ibl.ai SDK, so a product built on the platform can mount the spend-cap editor directly, along with a learner-safe usage indicator that shows people how close they are to a limit without ever showing them dollar amounts.