Quickstart: Govern Your First AI Action in 5 Minutes

ARQERA evaluates any action against 7 mathematical governance laws and returns an instant verdict: PROCEED, ESCALATE, or BLOCK — with a tamper-proof evidence trail.

---

1. Get Your API Key (1 min)

Sign up at arqera.io, then create an API key:

1. Go to System > API Keys
2. Click Create API Key
3. Name it (e.g., quickstart), select sandbox environment
4. Copy the key — it starts with ak_ and is shown only once

export ARQERA_API_KEY="ak_your_key_here"

Every new account gets 1,000 free governance evaluations/month and a $10 API credit.

---

2. Evaluate Your First Action (2 min)

curl

curl -s -X POST https://api.arqera.io/api/v1/ara/governance/evaluate \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $ARQERA_API_KEY" \
  -d '{
    "action": "email.send",
    "description": "Send a welcome email to a new user"
  }' | python3 -m json.tool

Python

import os, requests

result = requests.post(
    "https://api.arqera.io/api/v1/ara/governance/evaluate",
    headers={"X-API-Key": os.environ["ARQERA_API_KEY"]},
    json={
        "action": "email.send",
        "description": "Send a welcome email to a new user",
    },
).json()

print(f"Verdict: {result['verdict']}")       # "proceed"
print(f"Laws checked: {len(result['evaluations'])}")  # 7

TypeScript / Node.js

const res = await fetch(
  "https://api.arqera.io/api/v1/ara/governance/evaluate",
  {
    method: "POST",
    headers: {
      "Content-Type": "application/json",
      "X-API-Key": process.env.ARQERA_API_KEY!,
    },
    body: JSON.stringify({
      action: "email.send",
      description: "Send a welcome email to a new user",
    }),
  }
);
const result = await res.json();
console.log(`Verdict: ${result.verdict}`);         // "proceed"
console.log(`Laws checked: ${result.evaluations.length}`); // 7

---

3. Understand the Response

{
  "verdict": "proceed",
  "action": "email.send",
  "explanation": "All 8 governance laws passed.",
  "duration_ms": 12,
  "evaluations": [
    { "law_id": "audit_conservation",  "law_name": "Audit Conservation",  "result": "pass", "reason": "Action produces an auditable trace" },
    { "law_id": "budget_conservation", "law_name": "Budget Conservation", "result": "pass", "reason": "Within budget allocation" },
    { "law_id": "evidence_gravity",    "law_name": "Evidence Gravity",    "result": "pass", "reason": "Evidence chain maintained" },
    { "law_id": "least_action_path",   "law_name": "Least Action Path",   "result": "pass", "reason": "Optimal path selected" },
    { "law_id": "safety_dominance",    "law_name": "Safety Dominance",    "result": "pass", "reason": "No safety concerns" },
    { "law_id": "monotonic_truth",     "law_name": "Monotonic Truth",     "result": "pass", "reason": "Truth invariant maintained" },
    { "law_id": "bounded_autonomy",    "law_name": "Bounded Autonomy",    "result": "pass", "reason": "Within autonomy bounds" }
  ]
}

Verdict	Meaning	Your Code Should
proceed	Safe to execute	Execute the action
escalate	Needs human approval	Queue for review
block	Policy violation	Reject and log

---

4. Try Different Risk Levels (1 min)

Low risk — typically proceeds:

curl -s -X POST https://api.arqera.io/api/v1/ara/governance/evaluate \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $ARQERA_API_KEY" \
  -d '{"action": "data.read", "description": "Read dashboard metrics"}' \
  | python3 -c "import sys,json; print(json.load(sys.stdin)['verdict'])"

High risk, no approval — typically escalates or blocks:

curl -s -X POST https://api.arqera.io/api/v1/ara/governance/evaluate \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $ARQERA_API_KEY" \
  -d '{
    "action": "data.delete",
    "description": "Delete all user data for GDPR request",
    "context": {"risk_level": "high", "is_irreversible": true, "has_approval": false}
  }' | python3 -c "import sys,json; print(json.load(sys.stdin)['verdict'])"

High risk, with approval — proceeds when authorized:

curl -s -X POST https://api.arqera.io/api/v1/ara/governance/evaluate \
  -H "Content-Type: application/json" \
  -H "X-API-Key: $ARQERA_API_KEY" \
  -d '{
    "action": "data.delete",
    "description": "Delete all user data for GDPR request",
    "context": {"risk_level": "high", "is_irreversible": true, "has_approval": true}
  }' | python3 -c "import sys,json; print(json.load(sys.stdin)['verdict'])"

---

5. Integrate Into Your App (1 min)

Wrap governance into a one-liner:

import os, requests

def govern(action: str, description: str, **context) -> str:
    """Returns 'proceed', 'escalate', or 'block'."""
    r = requests.post(
        "https://api.arqera.io/api/v1/ara/governance/evaluate",
        headers={"X-API-Key": os.environ["ARQERA_API_KEY"]},
        json={"action": action, "description": description, "context": context},
    )
    r.raise_for_status()
    return r.json()["verdict"]

# Before any AI action:
verdict = govern("ai.generate", "Summarize Q1 report", estimated_cost_usd=0.05)

if verdict == "proceed":
    run_ai_task()
elif verdict == "escalate":
    queue_for_approval()
else:
    log_blocked("Policy violation")

---

Troubleshooting

Error	Fix
401 Unauthorized	Check X-API-Key header (case-sensitive)
403 Forbidden	Key may be expired or revoked — create a new one
429 Too Many Requests	Free tier limit reached — check Retry-After header
422 Validation Error	Missing action field in request body

---

Next Steps

Resource	Link
Full API Reference	Governance Evaluate
Python SDK	Python SDK docs
TypeScript SDK	TypeScript SDK docs
Rate Limits	Rate Limits
Evidence & Audit	Evidence Guide
EU AI Act Compliance	Compliance Guide