How It Works

From Your Data to Business Decisions

Three steps. Your data stays in your warehouse. Fig learns your business, maps what causes what, and answers your questions with evidence — so every decision is grounded in your actual numbers.

1

Connect

Your Data Stays Where It Is

Connect Snowflake, BigQuery, or PostgreSQL. Fig reads your data with read-only access — no data copies, no pipelines, no data leaving your warehouse. Fig learns what's there: which tables exist, how they connect, what they measure. You stay in complete control of your data.

SnowflakeBigQueryPostgreSQL

Data source scanning

Every database and table discovered automatically.

Table profiling

Row counts, null rates, and value distributions at a glance.

Column type detection

Metrics, dimensions, dates, and IDs classified by AI.

Relationship discovery

Foreign keys and join paths identified across tables.

2

Build Knowledge Graph

Fig Learns What Drives Your Business

Fig's AI builds a map of your business — connecting metrics to what causes them. Revenue depends on Customer Count, which depends on Retention Rate. These causal relationships let Fig trace any metric movement to its root cause. Industry templates give you a starting point. You review and approve everything before it goes live.

Human-in-the-loop. Every metric, dimension, and relationship the AI proposes must be approved by your team before it enters the graph.

Automatic node discovery

Metrics, dimensions, KPIs, and tables detected from your data.

Causal relationship mapping

Revenue depends on Customer Count depends on Retention — all mapped.

Industry templates

Pre-built ontologies for healthcare, retail, finance, and more.

Human-in-the-loop review

Every proposed node and relationship is reviewed before it's live.

3

Analyze

Get Answers That Tell You What to Do

Ask “Why did revenue drop last quarter?” in plain English. Fig selects the right type of analysis for your question, traces the causal chain, and delivers a structured answer — with the actual numbers, where they came from, how confident Fig is, and what to do next. No dashboards to build. No queries to write. Just the answer.

Example Prompt

“Why did customer churn increase 15% last month, and which segments are most affected?”

Natural language queries

Ask 'Why did revenue drop?' and get a structured answer.

Algorithm auto-selection

Fig picks the right algorithm from 12 built-in options.

Evidence-backed answers

Every conclusion comes with data, its source, and confidence levels.

Structured reports

Charts, tables, causal chains, and actionable recommendations.

Why This Isn't Just Another BI Tool

BI tools show you what happened. Fig tells you why it happened, what caused it, and which accounts are responsible — backed by evidence from your own data.

Causal, Not Correlational

Fig maps how metrics actually cause and affect each other — not just which ones move together. When revenue drops, you see the full causal chain, not a scatter plot.

12 Built-In Algorithms

Root cause analysis, anomaly detection, concentration analysis, scenario planning, and 8 more. Fig selects the right algorithm automatically based on your question.

Knowledge Graph Foundation

Every analysis is grounded in a knowledge graph that maps your specific business structure — not generic patterns. Context-aware from day one.

Evidence, Not Guesses

Every answer includes the data it's based on, the data source, confidence levels, and the causal chain it traced. You can verify everything.

See It in Action

Connect your data warehouse and go from raw data to causal intelligence in under 5 minutes.