Risk scoring

A risk score on
every single Reaction.

Per-Action governance tells you what a write did. Quadrazene scores the whole run. A composite 0-100 from six weighted factors, so compliance can find the 25 runs worth investigating without scrolling past hundreds of green ones. Cross a threshold and the run routes itself to a human.

Six factors, weighted and summed

What goes into the score.

Each factor contributes a bounded amount. The sum lands the Reaction in a band. Weights are data, not code.

Classification

0-30

Data sensitivity of the System touched: public → internal → confidential → restricted.

Side effects

0-30

What the atoms actually do. Writes, payments, outbound comms, and their risk class.

Reversibility

0-20

Payments and outbound communications dominate. Reads barely register.

Novelty

0-10

How rarely this Formula has run versus the tenant median. First-time runs score higher.

Trust events

0-20

Filter activity, weighted: block ×8, redact ×4, warn ×1.

Guardrail bypass

0-20

Write overrides, skipped HITL, disabled policies. Anything that loosened the rails.

low 0-29medium 30-59high 60-84critical 85-100

Risk Center

Find the runs worth looking at.

quadrazene.app/admin/risk
quadrazene v0.2.1
Quadrazene
ReactorComposeRecipesInboxGovernanceRecords
⌘K
Reactions · 30d
847
Medium
63
High
12
Critical
3
Top high-risk runs
78Actionsprocess-customer-defectawaiting-hitl
67Actionsrelease-credit-blockapproved
91Actionsbulk-vendor-updatepending
Per-factor contribution chips on hover. Reapply tuned weights to 7 / 30 / 90 days of history.

What the score drives

A number that does something.

Auto-HITL routing

Cross the threshold and the runner opens an Approval in the Inbox, with a one-line explanation of which factors pushed it over.

Risk chip everywhere

A colored badge sits on every Reaction in Records and reaction lists. Tooltip shows the per-factor breakdown.

Tenant-tunable weights

Every weight is a setting. A compliance officer can dial classification up or novelty down without an engineer.

Replay on history

Reapply new weights to the last 7 / 30 / 90 days so a policy change reflects on past runs, not just future ones.

Bands, not noise

low / medium / high / critical so dashboards and alerts speak in plain risk language, not raw integers.

Feeds Advisory

High-risk patterns roll into Advisory's prioritization. The platform recommends what to tighten.

Score your own workflows.

Request a demo