Docs • Introduction

Calibrated probabilities for real-time decisions

Reality Signal™ turns raw model scores into true probability + uncertainty, so you can safely automate, reroute to stronger models, reprompt, or escalate — and keep reliability stable as your system evolves.

Who this is for

AI engineers building decision systems: agents with side effects, routing layers, compliance and fraud triage, or any workflow where “confidence” must map to real risk.

What Reality Signal does

For each model prediction, send a score (or richer features). Reality Signal returns prob_true, uncertainty, and a recommended boolean decision computed against your threshold.

Why it matters

Raw scores aren’t probabilities. Miscalibration creates hidden cost: you automate when you shouldn’t, or you over-escalate when the system could safely handle the case.

How it works

1) Assess

Call /decide with a score or feature payload. You receive a calibrated probability and uncertainty plus a decision_id.

2) Act

Route based on prob_true + uncertainty: automate, reprompt, reroute to a stronger model, or escalate to a human.

3) Feedback

When the outcome is known, send /feedback with the decision_id. Reality Signal learns from real-world outcomes and monitors drift.

A minimal integration

In the simplest setup, you send a single score. (If you send a features dictionary instead, Reality Signal uses a feature-based calibration mode.)

POST /decide
bash
curl -X POST https://sowl-api.jollysand-1b9ed42e.swedencentral.azurecontainerapps.io/decide   -H "x-api-key: YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{
  "score": 0.82
}'
Response
json
{
  "decision_id": 123,
  "prob_true": 0.62,
  "uncertainty": 0.08,
  "decision": false,
  "threshold": 0.70
}
If decision is false, route the case (reprompt / reroute / escalate). If true and uncertainty is within your guardrail, automate.
POST /feedback
bash
curl -X POST https://sowl-api.jollysand-1b9ed42e.swedencentral.azurecontainerapps.io/feedback   -H "x-api-key: YOUR_API_KEY"   -H "Content-Type: application/json"   -d '{
  "decision_id": 123,
  "feedback": 1
}'
Feedback is 0 or 1 (ground truth). Reality Signal links it back to the original decision via decision_id.

Key concepts

Schema lock-in

Your environment locks its calibration mode based on the first successful calls. Score-only requests select score-based calibration; feature payloads select feature-based calibration. If you need to switch schemas, use the reset workflow.

Economic threshold override

If you configure decision economics (cost vs loss), Reality Signal can derive an optimal probability threshold automatically — so your automation policy matches business impact.