Score wording risk
Detect subjective thresholds, undefined terms, and source gaps.
OracleMangle scores event questions for ambiguous wording, weak source rules, and resolution-risk patterns before they enter automated research workflows.
Detect subjective thresholds, undefined terms, and source gaps.
Use numeric scores to queue manual review before automation continues.
Stripe provisions API keys and tier limits automatically after payment.
curl "https://api.oraclemangle.com/health"
curl -H "X-API-Key: YOUR_KEY" \
"https://api.oraclemangle.com/v1/stats"
curl -H "X-API-Key: YOUR_KEY" \
"https://api.oraclemangle.com/v1/score?question=Did%20the%20company%20make%20a%20significant%20AI%20announcement"
import requests
API_KEY = "YOUR_KEY"
RISK_THRESHOLD = 0.25
resp = requests.get(
"https://api.oraclemangle.com/v1/score",
headers={"X-API-Key": API_KEY},
params={"question": "Did the supplier materially breach the SLA this quarter?"},
timeout=20,
)
resp.raise_for_status()
signal = resp.json()
if signal["dispute_risk"] > RISK_THRESHOLD:
queue_manual_review()
else:
continue_workflow()
Questions, billing changes, and key rotation requests: [email protected].