KYC / compliance triage

Approve obvious passes automatically, route borderline cases to stricter checks, and send high‑uncertainty decisions to compliance review.

Overview

Problem

Compliance pipelines often suffer hidden costs: either you over‑escalate (too many manual reviews) or you under‑escalate (miss risky cases).

Reality Signal

Convert a score into p_true + uncertainty and a boolean decision.

Policy

Auto‑pass when p_true is high and uncertainty is low. If uncertainty is high, escalate to compliance. Otherwise run additional checks or reroute to a stronger model.

Architecture

Base model produces a score for the decision you care about.
Send the score to /decide.
Use p_true + uncertainty to route safely.
When the true outcome is known, call /feedback to improve calibration.

Routing actions: automate, reroute, reprompt, or escalate.

1) Decide + triage

Call /decide with your model’s score. Route based on calibrated probability and uncertainty.

Request

bash

curl -X POST https://api.realitysignal.ai/decide \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "features": { "score": 0.82 }
  }'

Response

json

{
  "decision_id": 123,
  "p_true": 0.62,
  "uncertainty": 0.08,
  "decision": false
}

Use p_true + uncertainty as routing signals.

2) Feedback from final decision

When ground truth is known, send /feedback with the decision_id so calibration improves over time.

Feedback (cURL)

bash

curl -X POST https://api.realitysignal.ai/feedback \
  -H "x-api-key: YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "decision_id": 123,
    "feedback": 1,
    "force_retrain": false
  }'

Reference implementation

Python

python

import requests

API_URL = "https://api.realitysignal.ai"
HEADERS = {"x-api-key": "YOUR_API_KEY"}

def rc_decide(score: float):
    r = requests.post(f"{API_URL}/decide", json={"features": {"score": score}, headers=HEADERS)
    r.raise_for_status()
    return r.json()

kyc_score = 0.86
rc = rc_decide(kyc_score)

if rc["p_true"] >= 0.90 and rc["uncertainty"] <= 0.10:
    approve()
elif rc["uncertainty"] > 0.20:
    send_to_compliance_review()
else:
    run_additional_checks()

Policy knobs: raise the pass threshold for stricter regimes; lower it for faster onboarding with more downstream checks.