Methodology
How the OPAL Score is built.
Transparent weights, SME-realistic exposures, and public Zurich Singapore product lines — designed for founders, insurers, and MAS-aligned AI risk practice.
Five pillars
Each category is scored 1–10 from your 12 intake signals, then blended with deterministic baselines. Weighted aggregate → OPAL Score 0–100 vs industry benchmark.
- cyber30%
- liability25%
- property20%
- employer15%
- business interruption10%
Exposure banding
LLM-suggested SGD exposures are capped by revenue tier (e.g. under_250k cyber ≤ SGD 80k) and scaled by headcount for employer and business interruption. We never invent Fortune-500 loss figures to look impressive.
Model pipeline
OpenAI returns structured JSON; OPAL normalizes scores and exposures; Zurich public-line matcher attaches directional product families. Confidence starts as intake_only and improves when you rescore from Settings.