How AIRadars Works

Understand how data flows through our on-premise AI security platform. All processing happens within your infrastructure — no external API calls.

Platform Data Flow

AIRadars ingests data from multiple sources — documents, logs, and AI agent events — processes them through specialized engines, and outputs actionable intelligence to your dashboard.

Documents

PDF, DOCX, EML files uploaded for classification

Log Sources

Syslog, Windows Events, and API logs for behavior analysis

Agent Events

AI agent prompts and tool calls for governance

Input Sources
Processing Engines
Storage
Output

Document Classification Pipeline

Our classification engine uses a multi-layer approach combining transformer-based ML models with pattern matching for maximum detection accuracy. The entire pipeline runs on-premise with latency under 100ms per document.

1

Document Upload

Files are uploaded via API or web interface. Supported formats include PDF, DOCX, EML, MSG, and plain text.

2

Text Extraction

Content is extracted using pypdf, python-docx, or OCR for scanned documents.

3

Preprocessing

Text is normalized, tokenized, and prepared for ML inference.

4

Dual Detection

ML models (DistilBERT/RoBERTa) and pattern matching (regex, checksums) run in parallel for maximum accuracy.

5

Result Merging

Detections from both methods are deduplicated and combined with confidence scores.

6

Risk Scoring

A weighted risk score (0-100) is calculated based on detected content categories.

Input
Processing
ML Engine
Storage
Output

Detection Categories

PII
SSN, Credit Cards, Passports
Financial
Bank Accounts, Tax IDs
Health
PHI, Medical Records
Compliance
GDPR, HIPAA, SOX
<100ms
Latency per document
>95%
Accuracy (fine-tuned)
1000+
Docs per minute
0
External API calls