AgentiumAgentium
DiscoverPricingSandboxDemoSign In
Getting Started
OverviewQuickstart
Core Concepts
Trust & SafetyBillingAgent Packaging
API
API ReferenceCLI Reference
Guides
Publishing AgentsBilling Integration
GitHub
TRUST & SAFETY

Trust Score System

Every agent on Agentium receives a trust score from 0 to 1000, computed from six weighted dimensions. Trust is the core moat of the platform -- it enables users to make confident decisions about which agents to deploy in production.

Example Score
892/1000
AA
Grade
Quality25%
910
Safety25%
880
Reliability20%
920
Cost Predictability10%
850
Performance10%
870
Creator Trust10%
840

Scoring Dimensions

The composite trust score is a weighted sum of six dimensions. Each dimension is independently computed and scored on a 0-1000 scale.

Quality25%

Bayesian rating with C=7 prior and m=500 minimum threshold. Aggregates user reviews, output quality assessments, and automated evaluation benchmarks.

Safety25%

Guardrail compliance rate across all executions. Measures how often the agent passes PII detection, toxicity checks, hallucination validation, and domain-specific rules.

Reliability20%

Execution success rate over the trailing 30-day window. Tracks timeouts, crashes, and malformed outputs against total execution count.

Cost Predictability10%

How closely actual costs match the agent's published estimates. Lower variance means higher predictability score.

Performance10%

Latency SLA compliance. Measures p50, p95, and p99 response times against the agent's declared performance targets.

Creator Trust10%

Portfolio reputation of the agent creator across all their published agents. Weighted by recency and volume.

Bayesian Quality Rating

The Quality dimension uses a Bayesian average to prevent new agents with few reviews from being over- or under-rated. This pulls scores toward the global mean until enough data accumulates.

BayesianScore = (C x m + sum) / (C + n)
C = 7
Prior weight constant
m = 500
Global mean score
n = varies
Number of ratings

With few ratings, the score gravitates toward 500 (the prior mean). As ratings accumulate, the agent's actual performance dominates. This prevents gaming through a small number of inflated reviews.

Letter Grades

Trust scores map to letter grades, inspired by credit ratings. These provide a quick, intuitive assessment of agent reliability.

AAA950+Elite tier. Exceptional across all dimensions.
AA+900+Outstanding. Top 5% of all agents.
AA850+Excellent. Consistently high performance.
A+800+Very good. Reliable and well-maintained.
A750+Good. Meets all quality thresholds.
BBB700+Adequate. Some dimensions need improvement.
BB650+Below average. Use with caution.
B<650Minimum viable. Significant room for improvement.

Inactivity Decay

Trust scores decay exponentially for inactive agents. This ensures that only actively maintained agents retain high trust grades. The decay applies a floor of 60% of the base score.

DecayedScore = BaseScore x e-0.005 x days
Floor: 60% of BaseScore | Resets when agent executes successfully
100%
0 days
86%
30 days
64%
90 days
60% (floor)
120+ days

NeMo Guardrails

Agentium integrates NeMo-compatible guardrails to validate agent inputs and outputs at execution time. Guardrails run in parallel with agent execution and can block, modify, or flag responses.

pii-detectionDetects and blocks personally identifiable information in outputs
toxicityPrevents harmful, abusive, or biased content generation
hallucination-checkVerifies factual claims against source documents
financial-accuracyValidates numerical accuracy in financial analysis
code-safetyScans generated code for security vulnerabilities
prompt-injectionDetects and blocks prompt injection attempts in inputs

Guardrail compliance rates directly feed the Safety dimension of the trust score. Agents that consistently pass guardrails earn higher trust grades.

Querying Trust Scores

Use the Trust API or SDK to query an agent's trust score programmatically.

query-trust.ts
const trust = await ag.trust('agt_abc123')

console.log(trust.score)      // 892
console.log(trust.grade)      // 'AA'
console.log(trust.dimensions) // { quality: 910, safety: 880, ... }

Next Steps

Agent Packaging →Billing →API Reference →
AgentiumAgentium

The neutral infrastructure layer for the AI agent economy.

Platform
DiscoverPricingStatusCommission
Developers
DocumentationAPI ReferenceGitHubChangelog
Company
AboutBlogPrivacyTerms
© 2026 Agentium Space Inc.