Lewati ke konten utama

Tata Kelola AI untuk Era Agentic

Bungkus klien LLM Anda. Tentukan kebijakan di dasbor. Setiap tindakan -- mulai dari panggilan model hingga operasi domain kustom -- dikendalikan secara otomatis.

main.py
from controlzero import Client
from controlzero.integrations.openai import wrap_openai
import openai

cz = Client(policy_file="controlzero.yaml")
client = wrap_openai(openai.OpenAI(), cz)

# Every LLM call is now governed by your policy
response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello"}],
)

Cara Kerja

1

Bungkus Klien Anda

Instal SDK dan bungkus klien LLM Anda dengan satu baris. Sejak saat itu, panggilan LLM dikendalikan secara otomatis.

pip install controlzero
2

Tentukan Kebijakan di Dasbor

Buat aturan yang mengendalikan model, alat, dan aksi kustom yang boleh digunakan agen Anda. Kebijakan tersinkronisasi ke SDK secara otomatis.

3

Rilis dengan Percaya Diri

Every LLM call and custom action is checked against your policies before execution. Violations are blocked and logged. No code changes needed.

Dibangun untuk AI di Produksi

W

SDK Pembungkus Otomatis

Bungkus klien OpenAI, Anthropic, atau LangChain Anda hanya dengan satu baris. Setiap panggilan LLM diperiksa secara otomatis terhadap kebijakan di dasbor sebelum dijalankan. Tidak perlu mengubah kode logika bisnis Anda.

C

Aksi Kustom

Tidak terbatas pada tata kelola LLM. Tentukan konvensi aksi Anda sendiri untuk vector store, basis data, API, alat MCP, atau operasi khusus domain apa pun. Gunakan enforce() untuk mengendalikan setiap aksi dengan pemeriksaan kebijakan.

P

Mesin Kebijakan

Define granular, composable policies in the dashboard. Specify allowed actions, target resources, conditions, and effects. Policies are encrypted, cached locally, and cryptographically signed.

A

Jejak Audit

Every policy decision is recorded with full context -- the requested action, the matching rule, and the outcome. Gain complete, searchable visibility into how your AI agents operate.

Berfungsi dengan Stack Anda

Python -- Pembungkus Otomatis
from controlzero import Client
from controlzero.integrations.openai import wrap_openai
import openai

cz = Client(policy_file="controlzero.yaml")
client = wrap_openai(openai.OpenAI(), cz)

# Use normally -- all calls governed by your policy
response = client.chat.completions.create(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello"}],
)
Python -- Panggilan Guard
from controlzero import Client

cz = Client(policy={
    "rules": [
        {"allow": "data:read", "reason": "Reads are permitted"},
        {"deny": "trade:*", "reason": "Trading is blocked"},
    ]
})

# Guard any tool call against the loaded policy
result = cz.guard("data", method="read", args={"source": "vectorstore"})
print(result.decision)  # "allow"

result = cz.guard("trade", method="execute", args={"asset": "AAPL"})
print(result.decision)  # "deny"
Node.js
import { Client } from "@controlzero/sdk";

const cz = new Client({
  policy: {
    rules: [
      { allow: "llm:generate", reason: "LLM calls permitted" },
      { deny: "filesystem:write_file", reason: "Writes blocked" },
    ],
  },
});

// Guard before executing
const decision = cz.guard("llm", { method: "generate" });
console.log(decision.effect); // "allow"

cz.guard("filesystem", { method: "write_file", raiseOnDeny: true });
// throws PolicyDeniedError

Siap mengendalikan agen AI Anda?

Mulai gunakan Control Zero dalam waktu kurang dari lima menit.

Mulai