Graph Intelligence Overview

How Quint’s graph-native reasoning engine scores AI agent actions

Status varies per capability. The forward-chaining engine, compliance ontology, and action taxonomy are shipped. The GNN, Memgraph co-processor, and graph-structured RAG are roadmap — see each page’s banner and the ML Roadmap for advancement triggers.

Graph Intelligence

Quint’s risk scoring is not a single model output. It’s a weighted composition of four signal layers, each producing a sub-score that contributes to a final 1-100 result. This makes every score fully explainable — you can decompose any score into its contributing signals.

Architecture Components

Scoring Algorithm

4-layer composite scoring with configurable weights, confidence computation, and LLM fallback triggers

Forward-Chaining Engine

90+ inference rules across 16 compliance frameworks with agenda-based fixed-point evaluation

Graph Neural Network

SubgraphGNN with 13 node types, 20 edge types, multi-task learning for risk classification

Graph-Structured RAG

Compliance articles and mitigations retrieved from Memgraph and injected into LLM prompts

Memgraph Co-Processor

Graph-native reasoning with centrality scoring, community detection, and impact propagation

Compliance Ontology

1,948+ nodes, 1,075+ edges across 16 compliance frameworks including SOC 2, EU AI Act, HIPAA, GDPR, PCI-DSS, ISO 27001, ISO 42001, NIST AI RMF, and more

Action Taxonomy

Canonical domain:scope:verb event classification with 7 domains and 150+ actions

The quint-graph Package

The graph intelligence layer is extracted as a standalone Python package:

from quint_graph import GraphReasoner

reasoner = GraphReasoner()

result = reasoner.evaluate(
    event=event_data,
    policies=customer_policies,
    tenant_id="customer-uuid"
)

print(result.score)        # 1-100
print(result.risk_level)   # none | low | medium | high | critical
print(result.confidence)   # 0.0 - 1.0
print(result.violations)   # List of policy violations
print(result.fired_rules)  # Which inference rules fired

Key Stats

Metric	Value
Inference rules	90+
Compliance frameworks	16
Ontology nodes	1,948+
Ontology edges	1,075+
Evaluation time (forward-chaining)	< 1ms
GNN node types	13
GNN edge types	20
Total hot-path latency	< 50ms
LLM fallback rate	~15-25% of events
Test suite	194 tests

Feature Flags

All advanced capabilities are gated behind feature flags (default False):

Flag	Default	Purpose
graph_reasoner_enabled	True	Primary forward-chaining engine
memgraph_enabled	False	Memgraph enrichment co-processor
memgraph_enrich_enabled	False	Centrality-weighted enrichment
memgraph_event_store_enabled	False	Write events to graph DB
gnn_enabled	False	SubgraphGNN structural scoring