Case Studies

How Sgraal prevents costly AI agent failures across regulated industries.

FINTECH PREVENTED

Preventing a $2.3M trading error

The Problem

An algorithmic trading agent prepared to execute a large position based on a memory entry referencing a 2024 SEC ruling. The entry had timestamp_age_days: 0 — presenting stale regulatory data presented as current.

Detection

Sgraal's timestamp integrity layer detected content-age mismatch: the content referenced "Q2 2024" and "deprecated framework" while claiming to be freshly created. Result: timestamp_integrity: MANIPULATED.

Result

omega_mem_final: 71.5
recommended_action: BLOCK
timestamp_integrity: MANIPULATED
pipeline_latency: 18ms
estimated_loss_avoided: $2.3M
HEALTHCARE PREVENTED

Stopping a medical triage drift

The Problem

A medical triage AI gradually expanded its diagnostic authority across 8 agent hops. By hop 6, it was recommending treatments outside its authorized scope — each individual hop looked plausible.

Detection

Sgraal's identity drift layer detected authority expansion keywords accumulating across the chain: "elevated to", "authorized to execute", "standing authority". Result: identity_drift: MANIPULATED at hop 4.

Result

omega_mem_final: 100
recommended_action: BLOCK
identity_drift: MANIPULATED
hops_contained: 4 of 8
authority_expansion_score: 1.0
LEGAL PREVENTED

Catching fabricated legal precedent

The Problem

Three independent research agents all confirmed a fabricated case citation as "verified precedent." No single agent had conflicting information — the consensus appeared genuine.

Detection

Sgraal's consensus collapse layer detected self-reinforcing agreement from a single root source. All three entries had near-identical trust scores with zero conflict — statistically implausible. Result: consensus_collapse: MANIPULATED.

Result

collapse_ratio: 5.2
recommended_action: BLOCK
consensus_collapse: MANIPULATED
attack_surface_level: CRITICAL
naturalness_level: FABRICATED

These are synthetic scenarios based on real corpus attack patterns. No actual client data is represented.

Try it now Read the whitepaper