Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.meshai.dev/llms.txt

Use this file to discover all available pages before exploring further.

The EU AI Act requires organizations to classify AI systems by risk level. MeshAI supports four risk levels and provides AI-assisted suggestions to help you classify each agent.

​
Risk Levels

LevelDescriptionObligations
MinimalLow-risk agents (spam filters, recommendations)Basic monitoring only
LimitedAgents interacting with humans (chatbots, content generators)Transparency obligations — users must know they’re interacting with AI
HighAgents in critical domains (HR, finance, healthcare)Full compliance: audit trail, HITL, FRIA, human oversight
UnacceptableBanned use cases (social scoring, real-time biometric surveillance)Should not be deployed without safeguards and exemptions

​
Classify an Agent

curl -X POST https://api.meshai.dev/agents/agt_abc123/risk-classification \
  -H "Authorization: Bearer msh_YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "risk_level": "high",
    "justification": "Agent processes employee performance data for HR decisions"
  }'

{
  "success": true,
  "data": {
    "agent_id": "agt_abc123",
    "risk_level": "high",
    "justification": "Agent processes employee performance data for HR decisions",
    "classified_by": "user@company.com",
    "classified_at": "2026-03-17T10:00:00Z",
    "ai_suggestion": null
  }
}

​
AI-Assisted Suggestion

Not sure which level to assign? Use the suggestion endpoint. MeshAI analyzes the agent’s metadata (name, description, framework, use case) and suggests a risk level. 
curl https://api.meshai.dev/agents/agt_abc123/risk-classification/suggest \
  -H "Authorization: Bearer msh_YOUR_API_KEY"

{
  "success": true,
  "data": {
    "suggested_level": "high",
    "reasoning": "This agent processes employee performance data which falls under HR decision-making — a high-risk category under EU AI Act Annex III.",
    "confidence": 0.85,
    "relevant_articles": ["Article 6", "Annex III, Section 4"]
  }
}
AI suggestions are advisory only. A human must review and confirm the final classification. The suggestion is not recorded as the official classification until you call the classify endpoint.

​
Get Current Classification

curl https://api.meshai.dev/agents/agt_abc123/risk-classification \
  -H "Authorization: Bearer msh_YOUR_API_KEY"

​
What Changes by Risk Level

CapabilityMinimalLimitedHighUnacceptable
Basic monitoringYesYesYesYes
Transparency cardOptionalRequiredRequiredRequired
Audit trailBasicFullFullFull
HITL approvalOptionalOptionalRequiredRequired
FRIANoNoRequiredRequired
Incident reportingNoNoRequiredRequired
Human oversightNoOptionalRequiredRequired