Kyvvu

Policy · critical

Limit LLM calls per task

Loop control: cap model inference calls at 50 per task to prevent runaway analysis loops, excessive cost, and cascading failures.

The policy

A few lines of YAML in your repository.

Part of Internal AI starter and Financial services: DORA and MiFID II. Assign the pack, or copy this policy into a manifest of your own.

Verdict
Critical: the step is blocked before it runs, and an incident is opened.
Checked
Before every step, against everything the agent did earlier in the task.
Rule
execution_max_steps
- name: "Limit LLM calls per task"  description: |    Loop control: cap model inference calls at 50 per task to prevent    runaway analysis loops, excessive cost, and cascading failures.  rule_type: execution_max_steps  params:    kind: step.model    max_steps: 50  severity: critical  enforcement_point: step_execution
Not legal advice. This policy is Kyvvu's interpretation of DORA and MiFID II. It isn't reviewed or endorsed by a regulator, and using it doesn't on its own make you compliant: it gives you technical controls, and a record that they ran, to support your compliance work.

How the rule works

execution_max_steps: Checks that the task has not exceeded a maximum count of the given action kind.

  • kind: step.model. Action kind to count.
  • max_steps: 50. Maximum number allowed per task.

In these packs

From Kyvvu's open policy library at github.com/Kyvvu/manifests, Apache 2.0.

Next

Watch it decide.

In your browser

Try it in the playground

The policy is loaded. Add the steps your agent takes and watch the engine decide, step by step.

On your machine

Five minutes, no account

kyvvu try runs a demo agent against the bundled baseline. Then assign this pack from the dashboard or the CLI.

For security teams

See it on your agents

A 30-minute demo on the agents you actually run, with the policies that fit them.