Policy pack · Operational
Internal AI starter policy pack
General-purpose responsible-AI policy set for organizations deploying AI agents without a specific regulatory requirement. Provides sensible defaults for tool allowlisting (fail-closed), execution and cost limits, destructive operation gates, and infinite loop prevention.
What's in it
8 policies, 5 of them blocking.
Critical policies block the step before it runs. High, medium and low ones let it run and open an incident.
| Policy | Checked | Severity | Rule |
|---|---|---|---|
| Agent must have a name | At registration | high | field_not_empty |
| Agent must document its purpose | At registration | high | field_not_empty |
| Agent must designate an owner | At registration | high | field_not_empty |
| Tool calls must be in the declared allowlist | Before every step | critical | step_name_in_allowlist |
| Limit LLM calls per task | Before every step | critical | execution_max_steps |
| Token budget per task | Before every step | critical | usage_budget |
| Destructive operations require human approval | Before every step | critical | step_requires_gate |
| Prevent infinite LLM loops | Before every step | critical | max_consecutive_same_type |
Version 1.0.2. Source: manifests/operational/internal-ai-starter.yaml.
Assign it
One command, no redeploy.
Assign it from the dashboard or the CLI. Running agents pick up an assignment within the policy refresh window, five minutes by default.
- Policies
- 8, of which 5 are checked before every step.
- Version
- 1.0.2
$ kyvvu list-manifests$ kyvvu assign-manifest --agent-id <agent> --repo-id <repo> \ --manifest manifests/operational/internal-ai-starter.yamlAbout this pack
Suitable as a starting point for internal deployments. Layer with compliance manifests (EU AI Act, GDPR, etc.) as regulatory requirements emerge.
Runtime policies in this pack
- Tool calls must be in the declared allowlist (critical)
- Limit LLM calls per task (critical)
- Token budget per task (critical)
- Destructive operations require human approval (critical)
- Prevent infinite LLM loops (critical)
From Kyvvu's open policy library at github.com/Kyvvu/manifests, Apache 2.0.
Next
Run the whole pack in your browser.
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.