Know who asked
OCI IAM validates the signed-in identity before the agent workspace opens, linking each request to an authenticated subject.
Identity verified
Traceable · accountable · powered by OCI
Every AI action,
Every AI action,
fully traceable.
Meridian Guard connects authenticated identity, OCI Responses, model-generated SQL, Oracle DeepSec enforcement, results, and independent audit records in one verifiable trail.
OCI IAM Verified identity
OCI Responses Observable function calls
Oracle Database Correlated execution evidence
From identity to evidence
Every action has a trace.
Meridian Guard retains each model-generated SQL attempt—including syntax failures—and correlates it with the authenticated user, DeepSec end-user context, Oracle result, and independent evidence sources.
See what ran
OCI Responses selects function calls and generates SQL. Meridian Guard records the exact statements, DeepSec context, and Oracle results for review.
Actions recordedVerify authorized scope
Oracle DeepSec evaluates the propagated end-user context before returning governed data.
Context enforcedGuarded demonstration architecture
Dynamic requests. Enforced boundaries.
The model remains free to discover the accessible schema and iterate on SQL. The application passes the exact SQL through the Python thin driver while Oracle DeepSec determines the data authorized for the authenticated end-user context.
Correlated evidence available