JevModel
JevModel is a structured decision model playground, API and decision-flow console. It turns text or JSON into Choice, Score and Noul answers with probabilities. It calls the Jev API from one Console and uses human approval before publishing any decision output. Use cases: content
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for JevModel, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
JevModel is a structured decision model playground, API and decision-flow console. It turns text or JSON into Choice, Score and Noul answers with probabilities. It calls the Jev API from one Console and uses human approval before publishing any decision output. Use cases: content moderation, spam filtering, support triage, ticket routing, priority, sentiment, prompt-injection screening.
Key features and capabilities
- Turn text or JSON into Choice
- Score and Noul answers with probabilities
- Build decision flows and process batches
- Call the API from one Console
- Content moderation and spam filtering
- Support triage and ticket routing
- Sentiment and prompt-injection screening
AIVSS capability and automation profile
Autonomy level 2: Agent drafts; human executes
Additional agentic capability factors
- Context-aware adaptation
- Non-deterministic behavior
- Goal-directed planning
Self-reported capability indicators; the AIVSS threat-model score below is generated separately and is not a certification.