POL-009 · Customer-facing

Toxicity detection

Compiled into the runtime gateway and evaluated inline on every prompt, tool call and completion in scope. Owned by Customer Experience.

Triggers / 30d

44

blocks, masks and escalations

Integrations bound

3

enforced at each connection

Severity

medium

owner Customer Experience

Added latency

7 ms

p99 within the 60 ms budget

Rule definition

Compiled expression

When

  • toxicity > 0.4 on output

Then

  • rewrite
  • warn agent

Policy as code

apiVersion: truint.ai/v1
kind: RuntimePolicy
metadata:
  id: POL-009
  name: "Toxicity detection"
  owner: "Customer Experience"
  scope: "Customer-facing"
spec:
  severity: medium
  mode: enforce
  when:
    - "toxicity > 0.4 on output"
  then:
    - "rewrite"
    - "warn agent"

Governance metadata

Policy ID
POL-009
Owner
Customer Experience
Scope
Customer-facing
State
Enforcing inline
Catalog version
2026.07.3
Last change
2026-07-22 · approved by AI Council

Recent evaluations

Decisions where this rule fired

11:41:22Dispute Resolution Agent· emp-20265allow

Classify chargeback dispute DSP-4412 and draft the outcome.

11:40:45Dispute Resolution Agent· emp-20349allow

Classify chargeback dispute DSP-4412 and draft the outcome.

11:33:18Dispute Resolution Agent· emp-20503allow

Classify chargeback dispute DSP-4412 and draft the outcome.

11:34:19Dispute Resolution Agent· emp-20442allow

Classify chargeback dispute DSP-4412 and draft the outcome.

11:29:02Dispute Resolution Agent· emp-20170allow

Classify chargeback dispute DSP-4412 and draft the outcome.