Quickstart
Evaluate a Decision
Every call runs the deterministic pipeline (intercept → classify → enforce → score → decide → execute → prove) and returns ALLOWED, BLOCKED, or MODIFIED with a signed attestation.
Install
# Python
pip install eve-coreguard
# Node
npm install eve-ai-governance
Python
from eve_coreguard import CoreGuardClient
client = CoreGuardClient(
api_key="eve_sk_...",
base_url="https://api.eveaicore.com", # or http://localhost:8000
)
result = client.evaluate(
tenant_id="bank_001",
proposed_action={"type": "loan_approval", "amount": 250000, "currency": "USD"},
model_output={"decision": "approve", "confidence": 0.91},
context={"credit_score": 580, "debt_to_income": 0.52, "employment_verified": False},
policy_set="lending_v1",
)
if result.blocked:
print(result.decision.action) # BLOCKED
print(result.risk.score, result.risk.level)
for v in result.policy_violations:
print(v.policy_id, v.description)
REST API
POST /v1/decisions/evaluate
curl -X POST https://api.eveaicore.com/v1/decisions/evaluate \
-H "Authorization: Bearer eve_sk_..." \
-H "Content-Type: application/json" \
-d '{
"tenant_id": "bank_001",
"proposed_action": { "type": "loan_approval", "amount": 250000 },
"model_output": { "decision": "approve", "confidence": 0.91 },
"context": { "credit_score": 580, "debt_to_income": 0.52 },
"policy_set": "lending_v1"
}'
# -> { "decision": { "status": "ALLOWED" | "BLOCKED" | "MODIFIED" },
# "risk": {...}, "attestation": { "hash": "...", "algorithm": "..." } }
Verify a record offline
# Anyone can recompute the evidence hash and confirm the signature
# without an account and without trusting EVE.
pip install "eve-coreguard[verify]"
Optional cryptography extra enables offline Ed25519 / ECDSA evidence verification. Try it in the browser on the Verify page.
EVE CORETM