5-Minute Quickstart

Getting Started

Create your account, register your first agent, and run a policy check in under 5 minutes.

Prerequisites

Node.js 20+

Required for the TypeScript SDK. Check with node --version

DRD Account

Free tier includes 5 agents, 1,000 events/day, and 100 API calls/min.

Step 1

Create an Account

Step 2

Create a Workspace

Workspaces are the top-level organizational unit in DRD. They contain agents, policies, events, and content registrations. Each workspace has its own API keys and billing.

terminal

curl -X POST https://api.drd.io/api/v1/workspaces \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"name": "Production", "slug": "production", "plan": "pro"}'

// Response
{
  "ok": true,
  "data": {
    "workspaceId": "ws_01HQ3X9M2KYZ...",
    "name": "Production",
    "slug": "production",
    "apiKey": "drd_ws_sk_live_Abc123...",
    "plan": "pro",
    "createdAt": "2026-01-15T10:30:00Z"
  }
}

Step 3

Register an Agent

Every AI system that interacts with DRD must be registered as an agent. Registration assigns a unique Decentralized Identifier (DID) and generates agent-scoped API credentials.

terminal

curl -X POST https://api.drd.io/api/v1/agents \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "name": "content-moderator",
    "type": "automation",
    "description": "Automated content moderation pipeline",
    "capabilities": ["content.scan", "content.flag"],
    "metadata": { "model": "gpt-5.2", "version": "2.1.0" }
  }'

// Response
{
  "ok": true,
  "data": {
    "agentId": "agt_01HQ3XBN4RTYP...",
    "did": "did:drd:agt_01HQ3XBN4RTYP",
    "name": "content-moderator",
    "status": "active",
    "apiKey": "drd_agt_sk_Xyz789...",
    "trustScore": 50,
    "createdAt": "2026-01-15T10:35:00Z"
  }
}

Step 4

Install the SDK

Install the @drd/sdk package from npm to integrate governance checks into your agent.

terminal

npm install @drd/sdk

Step 5

Run Your First Policy Check

Policy checks evaluate whether an agent action is permitted under your governance rules. The evaluation engine returns an allow/deny decision with detailed reasoning.

quickstart.ts

import { DRD } from '@drd/sdk';

const drd = new DRD({ apiKey: process.env.DRD_API_KEY });

// Evaluate an action against all active policies
const result = await drd.guard('content.publish', {
  contentType: 'text/markdown',
  wordCount: 1200,
  containsPersonalData: false,
});

// result:
// {
//   decision: "allow",
//   policyId: "pol_01HQ3XCK9MWQN...",
//   reasoning: "Action permitted by policy 'Content Publishing Rules'",
//   evaluatedRules: 3,
//   latency: 8,
// }

if (result.allowed) {
  await publishContent(result.context);
  await drd.report('content.published', { wordCount: 1200 });
}

await drd.shutdown();

Environment Variables

Store your credentials securely in environment variables. Never commit API keys to source control.

.env

DRD_API_KEY=drd_ws_sk_live_Abc123...
DRD_WORKSPACE=ws_01HQ3X9M2KYZ...
DRD_AGENT_KEY=drd_agt_sk_Xyz789...

Next Steps

API Reference

Full endpoint documentation with request/response schemas

Explore endpoints

SDK Guide

Deep dive into guard(), report(), and error handling

Read the guide

Agent Governance

Policies, enforcement tiers, and approval workflows

Learn more

Trust Badges

Earn "PROTECTED BY DRD" certification for your agents

Get certified

curl -X POST https://api.drd.io/api/v1/workspaces \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{"name": "Production", "slug": "production", "plan": "pro"}' // Response { "ok": true, "data": { "workspaceId": "ws_01HQ3X9M2KYZ...", "name": "Production", "slug": "production", "apiKey": "drd_ws_sk_live_Abc123...", "plan": "pro", "createdAt": "2026-01-15T10:30:00Z" } }

curl -X POST https://api.drd.io/api/v1/agents \ -H "Authorization: Bearer YOUR_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "name": "content-moderator", "type": "automation", "description": "Automated content moderation pipeline", "capabilities": ["content.scan", "content.flag"], "metadata": { "model": "gpt-5.2", "version": "2.1.0" } }' // Response { "ok": true, "data": { "agentId": "agt_01HQ3XBN4RTYP...", "did": "did:drd:agt_01HQ3XBN4RTYP", "name": "content-moderator", "status": "active", "apiKey": "drd_agt_sk_Xyz789...", "trustScore": 50, "createdAt": "2026-01-15T10:35:00Z" } }

import { DRD } from '@drd/sdk'; const drd = new DRD({ apiKey: process.env.DRD_API_KEY }); // Evaluate an action against all active policies const result = await drd.guard('content.publish', { contentType: 'text/markdown', wordCount: 1200, containsPersonalData: false, }); // result: // { // decision: "allow", // policyId: "pol_01HQ3XCK9MWQN...", // reasoning: "Action permitted by policy 'Content Publishing Rules'", // evaluatedRules: 3, // latency: 8, // } if (result.allowed) { await publishContent(result.context); await drd.report('content.published', { wordCount: 1200 }); } await drd.shutdown();