System Settings

SA

Fraud Detection Thresholds

Configure the risk score boundaries that determine transaction routing decisions. Changes take effect immediately on the live stream.

Risk Score Band Preview
APPROVE
FLAG
BLOCK
0 40 70 100

Transactions with risk score at or above this value are sent to the Review Queue for analyst inspection.

40

Transactions at or above this score are automatically blocked. Must be greater than the Flag threshold.

70

Time window (minutes) for counting repeated transactions from the same user/IP.

Number of transactions within the window that triggers a velocity fraud flag.

Minimum km between two transactions for them to be flagged as impossible travel.

Transactions from these MCC categories receive a +15 risk score penalty automatically.

Gambling Crypto Exchange Wire Transfer Cash Advance

AI Model Configuration

Select the Gemini models powering each agent in the fraud detection pipeline. Higher-tier models increase accuracy and cost.

Pattern Detector
First-pass statistical analysis
Tier 1
Avg latency~320ms
Cost/1K calls$0.04
Accuracy94.2%
Risk Scorer
Context-aware risk quantification
Tier 2
Avg latency~750ms
Cost/1K calls$0.35
Accuracy97.1%
Decision Orchestrator
Final APPROVE / FLAG / BLOCK ruling
Tier 3
Avg latency~1.2s
Cost/1K calls$1.25
Accuracy99.3%

Controls output randomness. Lower = more deterministic decisions.

0.10

Maximum time before an agent call is aborted and fallback rule fires.

Used by all agents. Stored in .env — never logged or transmitted.

Budget & Cost Controls

Set hard spending limits and configure the adaptive routing engine that degrades gracefully as budget runs low.

Current Period Spend
$0.00 / $10.00
12% utilized Healthy

Hard cap. Agent calls are suspended when this is reached.

Soft cap — triggers alerts at 80%, 90%, 100%.

When spend counters are reset to zero.

At each utilization level, the system automatically routes to a cheaper model tier.

0–60%
Full Pipeline
All 3 Gemini agents active
%
Degraded Mode
Flash models only
%
Rule-Only Mode
No AI calls, heuristics only

Send Slack / email alerts at 80%, 90%, and 100% budget utilization.

Dynatrace Integration

Connect FinSentinel to your Dynatrace environment for observability, self-healing, and SRE automation.

Not Connected

Your Dynatrace SaaS or Managed endpoint.

Requires: metrics.read, events.ingest, problems.read

Allow the monitor to auto-remediate problems detected by Dynatrace.

Stream fraud KPIs (risk scores, decision counts) as custom metrics.

Connect Gemini agents to Dynatrace via the Model Context Protocol server.

How often the self-monitor queries Dynatrace for open problems.

Notification Rules

Configure alert channels and the conditions that trigger them. Alerts fire in real-time as transactions are processed.

Email
Slack
Webhook
Critical
Fraud rate exceeds % in any 5-minute window
Critical
Budget utilization exceeds % of daily limit
Warning
Single transaction risk score above
Warning
Dynatrace problem opened with severity P1 or P2
Info
Routing tier degraded from Full Pipeline to Degraded Mode

Agent Pipeline Configuration

Control which agents are active in the fraud detection pipeline and tune their individual behavior.

Pattern Detector
Active
Geo Validator
Active
Risk Scorer
Active
Orchestrator
Active
Pattern Detector
Statistical anomaly detection on transaction history
Geo Validator
Impossible-travel and high-risk country detection
CN RU NG VN
Risk Scorer
Assigns 0-100 risk score with SHAP-style reasoning

How frequently the system processes a new simulated transaction. Lower = more Gemini calls = higher cost.

10s