Core Concepts

Understand the AI engine, multi-model ensemble, and confidence scoring system that power 3X.

Platform Architecture

01

Connect

Read-only metadata extraction via native connectors

02

Extract

Schema structure & small data samples (5 rows)

03

AI Process

Multi-model ensemble analysis & enrichment

04

Export

JSON, HTML, Markdown, or PDF documentation

Secure In-Memory Processing: Data is never persisted after the session

Read-Only Extraction

We extract schema metadata and small samples (5 rows) only. No bulk data movement.

In-Memory Processing

All AI analysis happens in-memory. Data is not persisted after the session.

AI Description Generation

3X uses an ensemble of three advanced AI models (Claude, GPT-4, and our fine-tuned custom model) to analyze your data from multiple angles.

Naming Conventions

Translates technical column names into human-readable labels (e.g., cust_id → Customer ID).

Data Patterns

Infers semantic meaning from actual data formats (regex matching & sampling).

Relationships

Analyzes foreign keys to understand how business entities relate to each other.

Confidence Scoring

Trust but Verify

Every generated description gets a 0-100% confidence score. This prioritization engine helps you focus your manual review where it matters most.

Score RangeMeaningRecommendation
90-100%High ConfidenceMinimal review needed. Likely accurate.
70-89%Medium ConfidenceQuick verification recommended.
< 70%Low ConfidenceHuman review strongly recommended.

Intelligent PII Detection

Our multi-layered approach combines pattern matching, semantic analysis, and data sampling to detect sensitive data automatically.

Contact Info

Emails, Phone Numbers, Physical Addresses

Personal IDs

SSNs, National IDs, Passport Numbers

Financial

Credit Card Numbers, Bank Account Details

Health

Medical Record Numbers, Health IDs

Human-in-the-Loop Workflow

80/20Split

The Philosophy

AI handles the 80% of straightforward documentation. Humans focus their expertise on the 20% requiring complex business context.