Define governance rules once and enforce them everywhere. Out-of-the-box guardrails for compliance, security, and cost control across all your agentic applications.
Automatically detect and redact sensitive personal information before it reaches your LLM. Protect SSNs, credit cards, addresses, and custom data patterns.
Prevent prompt injection attacks and unauthorized instructions. Protect your agents from malicious inputs attempting to override their behavior.
Control which LLM providers and models your agents can use. Enforce compliance requirements like Azure OpenAI only or on-premise models.
Set budget limits, rate limits, and performance thresholds. Prevent runaway costs and ensure your agents meet SLA requirements.
Write custom policies once and they automatically apply across all frameworks
import eevee as ev
# Create a custom policy
@ev.policy("block_competitor_mentions")
class CompetitorFilter:
def on_input(self, context):
competitors = ["CompanyX", "ProductY"]
if any(comp in context.input for comp in competitors):
return ev.block("Competitor mention detected")
return ev.allow()
# Apply to all agents automatically
agent = ev.load("agent", "sales_assistant")
# Policy runs without code changes