Semantic Engine

Your data has
a knowledge graph.

Datural builds a living map of every table, column, and relationship across all your sources. When you ask a question, the engine already knows where to look.

The problem

AI tools dump your entire schema into a prompt and pray

Most NL-to-SQL products take your question, paste the full database schema into an LLM, and hope it picks the right tables. With 30 tables it works. With 300 it hallucinates. With multiple sources it falls apart entirely.

Datural's approach

The engine understands before it queries

When you connect a source, Datural doesn't just read the schema — it builds a knowledge graph of what your data means. Relationships, business terms, naming patterns. When you ask a question, the engine retrieves only the tables that matter and hands the LLM a focused, precise context.

01

Instant understanding

Connect a database and the engine maps every table, column, and relationship in seconds. It generates human-readable descriptions so "acct_ltv_q4" becomes "account lifetime value, quarterly."

02

Semantic search, not string matching

Ask about "revenue" and the engine finds your "order_total" column. Ask about "churn" and it surfaces "subscription_cancelled_at." It understands meaning, not just names.

03

Cross-source intelligence

Users in Postgres. Events in MongoDB. Metrics in Databricks. The engine discovers that these sources share concepts and builds bridges between them automatically.

04

Focused context, not schema dumps

A 200-column database gets distilled to the 5 tables that matter for your question. The LLM sees exactly what it needs — nothing more, nothing less. Hallucinations drop dramatically.

05

Gets smarter with every question

Confirm a query is correct and the system remembers. Next time someone asks a similar question — across your whole team — the answer comes back instantly, without touching the LLM.

06

Transparent and auditable

Every answer traces back to specific tables, joins, and SQL. You see exactly which sources were used, how they connected, and why. No black boxes.

Under the hood

1

Connect and harvest

Point Datural at your databases. The engine crawls the schema, discovers relationships — explicit and implicit — and builds a knowledge graph with semantic descriptions for every entity.

2

Retrieve with precision

When you ask a question, the engine finds the exact tables needed through semantic matching and graph traversal. It constructs the minimal context — typically 3 to 7 tables out of hundreds — and hands it to the LLM.

3

Execute across sources

The LLM generates queries in each source's native language. Postgres gets SQL. MongoDB gets aggregation pipelines. Results are normalized and merged into a single, unified answer.

4

Learn and harden

Every confirmed answer strengthens the graph. Verified queries become cached routes. Business terms solidify into definitions. The engine gets faster, cheaper, and more accurate over time.

Schema dump vs. semantic engine

CapabilityTypical NL-to-SQLDatural
Context strategyEntire schema in promptGraph-selected subset
Accuracy at scaleDegrades past ~30 tablesScales to hundreds
Cross-source queriesAutomatic
Learning from usageEvery confirmed query
Repeat question costFull LLM call every timeCached, instant
Relationship discoveryExplicit FKs onlyExplicit + inferred + semantic
TransparencyPrompt in, SQL outFull table + join trace

Stop dumping schemas.
Start understanding data.

See how the semantic engine turns your databases into a knowledge graph that answers questions with precision.

Request a demo