Kyvvu

Policy · high

Limit resource calls per task for robustness

EU AI Act Article 15(3) requires that high-risk AI systems be resilient against errors, faults, and inconsistencies. Capping step.resource calls at 50 per task prevents runaway loops, potential abuse, and cascading failures.

The policy

A few lines of YAML in your repository.

Part of EU AI Act, high risk. Assign the pack, or copy this policy into a manifest of your own.

Verdict
High: the step runs, and Kyvvu records a warning and opens an incident.
Checked
Before every step, against everything the agent did earlier in the task.
Rule
execution_max_steps
- name: "Limit resource calls per task for robustness"  description: |    EU AI Act Article 15(3) requires that high-risk AI systems be resilient    against errors, faults, and inconsistencies. Capping step.resource calls    at 50 per task prevents runaway loops, potential abuse, and cascading    failures.    Applies to: ALL risk classifications.  rule_type: execution_max_steps  params:    kind: step.resource    max_steps: 50  severity: high  enforcement_point: step_execution
Not legal advice. This policy is Kyvvu's interpretation of the EU AI Act. 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.

Why it matters

Applies to: ALL risk classifications.

How the rule works

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

  • kind: step.resource. 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.