Build & integrate

How Your Agent Calls IRIS

IRIS enforces Cedar policy before every LLM call executes. Replace one import — keep the rest of your code.

Drop-in LLM clients

IRIS ships governed wrappers for major SDKs. Cedar evaluates every request in-process.

Anthropic

# pip install iris-security-sdk[anthropic]
# client = anthropic.Anthropic()
from iris_anthropic import IrisAnthropic

client = IrisAnthropic(
  passport=passport,
  user_work_authorization="us-citizen", # for frontier-restricted models
)
response = client.messages.create(model="claude-sonnet-4-6", ...)

OpenAI

from iris_openai import IrisOpenAI
client = IrisOpenAI(passport=passport)

Gemini / Vertex AI

from iris_gemini import IrisGemini
from iris_vertexai import IrisVertexAI

LangChain & CrewAI

# pip install iris-security-sdk[langchain]
from iris_langchain import IrisCallbackHandler

# pip install iris-security-sdk[crewai]
# CrewAI agents use IrisAgent.guard on tool calls

Verify enforcement is wired

iris enforce --agent support-agent --dir .
iris explain # how the proxy works

Use @agent.guard() to evaluate non-LLM API calls against Cedar policy.

from iris import IrisAgent

agent = IrisAgent(
  name="support-agent",
  owner="you@company.com",
  compliance=["colorado-ai-act"],
  is_high_risk_ai=True,
)

@agent.guard(tool="zendesk-api", action="read")
def fetch_ticket(ticket_id: str) -> dict:
  return zendesk.get(ticket_id)

@agent.guard(tool="openai-api", action="call", data_classification="pii")
def generate_response(ticket: dict) -> str:
  return client.complete(ticket)

HITL and delegation

High-risk actions can require human approval. Pass hitl_approved=True after iris hitl approve. Cedar evaluates acting_for_user and consent fields for delegation. See HITL & Delegation.

What happens on violation

Environment behavior

export IRIS_ENV=production # fail closed
export IRIS_ENV=dev # warn only

Model suspensions

When a provider or government suspends a model, update governance/directives/active.yaml. IRIS hot-reloads and auto-routes to your fallback. See Model Governance.