Pre-call enforcement

Most cost controls are retrospective: dashboards, alerts, and provider spend limits that notify rather than block. By the time a human reads the alert, the spend exists. Enforcement placed before the call is the only point in the lifecycle where the answer can be "no" — everything later is accounting.

An agent with a $50 monthly envelope has spent $50. Its next call triggers the pre-call check, which finds a budget with a block action and raises an error inside the application instead of sending the request. The provider never sees the call and nothing is billed.

By where the check executes (in-process before the request, at a proxy, or after ingestion) and by its failure mode — Capsera's check fails open, so an unreachable control plane degrades to unenforced rather than to an outage.

What is pre-call enforcement?

Pre-call enforcement is a budget check that runs before an LLM request is sent to the provider, so an over-budget call is stopped before it costs anything rather than reported after it has. It is the only point in the request lifecycle where the answer can be "no" — everything later is accounting. Capsera runs this check in-process, so it needs no proxy in front of your traffic.

How do I enforce hard spending limits on agents in production?

Create a budget scoped to the agent, team, or organisation, set its action to block, and let the pre-call check refuse requests once the limit is reached. Because the check runs inside your process before the provider call, the request is never billed. Provider-side spend limits are not a substitute: OpenAI's project limits are notification-only, and a limit that alerts after the fact cannot bound a runaway loop.

• Per-agent budget — A per-agent budget is a spending envelope scoped to one named agent, rather than to the API key, project, or account the agent shares with everything else.
• Runaway agent loop — A runaway agent loop is an agent retrying or re-invoking itself without a terminating condition, generating LLM spend continuously until something outside the loop stops it.
• Agentic spend governance — Agentic spend governance is the practice of attributing, budgeting, and enforcing LLM spend at the level of the agents that generate it, rather than at the level of API keys or accounts.