EVA Decision Trust Level (DTL)

EVA Ecosystem Integration

Tool	Purpose	How to Use
37-data-model	Single source of truth for all project entities	GET http://localhost:8010/model/projects/49-eva-dtl
29-foundry	Agentic capabilities (search, RAG, eval, observability)	C:\eva-foundry\eva-foundation\29-foundry
48-eva-veritas	Trust score and coverage audit	MCP tool: audit_repo / get_trust_score
07-foundation-layer	Copilot instructions primer + governance templates	MCP tool: apply_primer / audit_project

Agent rule: Query the data model API before reading source files.

Invoke-RestMethod "http://localhost:8010/model/agent-guide"   # complete protocol
Invoke-RestMethod "http://localhost:8010/model/agent-summary" # all layer counts

---

Overview

EVA DTL is the real-time authorization engine for AI-driven decisions.

It replaces static trust scoring with dynamic, context-aware decision control.

DTL determines whether an actor (human, agent, system) is allowed to perform an action on data in a given context.

Core Concept

DTL(actor, action, data, context, time) ? Decision

Output:

• DTL state (ALLOW, DENY, etc.)
• Confidence
• Obligations
• Expiry

Principles

• Evidence-first (no evidence = no trust)
• Zero-trust (time-bound decisions)
• Policy-driven (rules over scores)
• Context-aware
• Multi-actor

DTL States

• ALLOW
• ALLOW_WITH_OBLIGATIONS
• CONDITIONAL_ALLOW
• HUMAN_REQUIRED
• RESTRICTED
• DENY

Components

• Trust Vector Engine
• Context Risk Engine
• Policy Engine
• Decision Engine