Risk Gate

Software componentHuman OversightExperience & Human Oversightarc:RiskGate

An oversight gate that scores proposed actions on impact factors such as financial amount, data deletion, external API calls, and customer reach, escalating by cumulative risk score.

Responsibility. Escalates actions whose assessed risk exceeds policy thresholds.

Also known as: Risk-based gate, Risk assessment, Risk-based oversight selector, High-stakes decision gate, Mandatory human checkpoint, Tiered oversight, Autonomy gradient, Materiality threshold routing

Variant of Oversight Gate abstract

When to choose. Choose when escalation must reflect action impact (financial amount, deletion, external calls, customer reach) regardless of agent confidence.

Direct neighbourhood (hover for relationship types)

Relationships

is configured by structural

escalates to dynamic

routes to dynamic

guards control

Agent Controller abstract Ch9.4 Ref9.02
Workflow Orchestrator abstract Ch10.1

alternative to variability

Design guidance

SHOULD implement organisational risk policies as explicit, auditable scoring rules.
SHOULD select oversight intensity from action reversibility, error consequence severity and operational scale.
SHOULD weigh financial impact, reversibility, stakeholder sensitivity and uncertainty when setting authority for a decision.
SHOULD escalate decisions in regulated or safety-critical domains (e.g., medical supply procurement) to humans regardless of confidence.

Quantitative guidance

As stated by the sources; verify before use.

Example scoring: >$10,000 = 3 pts, any deletion = 5, external API call = 2; >=5 requires approval, 3-4 shows risk details, <3 proceeds (Ch1.1A).
Code example: >$10k = 5, deletion = 5, external API = 3, >500 recipients = 4; >=5 approval, >=8 monitoring dashboard (Ch1.1B).
Layered production example: HITL for ~1% of actions, HOTL for ~10%, HOVL for ~89% (Ch9.2).
Prudential: 60% of claims process automatically, 40% escalate to human reviewers; $12M annual savings with 100% regulatory compliance (Ch10.1).
Reference thresholds: financial amounts over $10k, and any privacy, safety or regulatory impact, count toward the risk score; score > 2 escalates (Ref10.01).

Classification

Patterns: Risk-score escalationRisk-proportional oversight hierarchy (HITL/HOTL/HOVL)
Quality attributes: Safety (ISO/IEC 25010 | NIST AI RMF: safe)Transparency and accountability (NIST AI RMF: accountable and transparent)
Risks mitigated: Irreversible data deletionHigh financial lossBroad customer impact

Sources

Ch1.1A: T. Nguyen, "Designing User Interfaces for Intuitive Human-Agent Interaction," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.1A. ISBN: 9798244538229.
Ch1.1B: T. Nguyen, "Human-in-the-Loop Patterns and Accessible Design," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 1.1B. ISBN: 9798244538229.
Ch9.2: T. Nguyen, "Action Constraints and Permission Models," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.2. ISBN: 9798244538229.
Ch9.4: T. Nguyen, "Fairness and Bias Mitigation," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 9.4. ISBN: 9798244538229.
Ch10.1: T. Nguyen, "Conversational UI," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.1. ISBN: 9798244538229.
Ch10.2: T. Nguyen, "Proactive Agents," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.2. ISBN: 9798244538229.
Ch10.4: T. Nguyen, "Human-in-the-Loop," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.4. ISBN: 9798244538229.
Ch10.5: T. Nguyen, "Human-over-the-Loop," in Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam, 1st ed. 2026, ch. 10.5. ISBN: 9798244538229.
Ref9.02: "Responsible AI and Ethical Principles," unpublished reference note (02-Responsible-AI-Ethical-Principles.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note
Ref10.01: "Human-in-the-Loop Systems for Agent Interactions," unpublished reference note (01-Human-in-the-Loop-Systems.md), Mastering Agentic AI Systems: Guide for the NVIDIA NCP-AAI Exam supplementary materials, 2026. unpublished note