AI needs more than data
Large language models are exceptional at language, not at your business. Without context they guess, without metadata they drift, without governance they become a risk.
DBAsk gives AI the missing knowledge layer: what each table means, how objects relate to one another, and how SQL should be written.
The metadata engine, not the model, is what makes DBAsk trustworthy
The model matters, but it's what DBAsk builds between the model and your data that turns a question into SQL you can check.
From source systems to a plain English question
DBAsk sits alongside your existing ETL, warehouse, and BI tools, it doesn't replace them.
Built in four steps, entirely in your environment
Your Data, Your Database
DBAsk connects to the relational database you already run, or we provision SovereignDB as your managed foundation. You run the SQL yourself and see results on your own screen, like a database client, nothing is stored or passed to the model but metadata.
Isolated AI Engine
The AI model is deployed wherever you choose: public cloud, private cloud, on-prem or air-gapped. It only ever sees your metadata, never your raw data, and nothing is stored outside your environment.
DBAsk Intelligence
The metadata engine and AI interface are built on top, turning plain English questions into transparent, reviewable SQL grounded in your actual business definitions.
Human-in-the-Loop Review
DBAsk generates the SQL and shows its sources, but never runs it. A person on your team always reviews, approves, and executes it, DBAsk never acts on its own.
DBAsk gives you the SQL, not the answer
DBAsk never hides the SQL, and never runs it for you. The metadata and business definitions behind it are shown too, so your team can check it's correct. If anything is unclear, explain mode walks through the query and sets out which objects were used and why.
SELECT region, SUM(revenue) * 0.08 AS projected_loss FROM sales.fact_revenue WHERE region = 'North' GROUP BY region;
One platform, two ways to deploy
The full DBAsk platform either way: private AI engine, metadata layer, ongoing support. The only difference is what's underneath: your database, or a fully managed SovereignDB instance.
AI on Your Database
Add private AI to the relational database you already run
- AI server & API, deployed to your environment
- Metadata repository built inside your existing database
- Ongoing metadata support & consulting included
AI + Managed Database (SovereignDB)
We build and host the entire platform for you
- AI server & connecting API, provided by us
- We set up & manage the relational database (SovereignDB)
- Metadata repository created & populated within this new DB
A note on DBAaaS: it can be added to Bring Your Own Database for day-to-day DBA operations. With Fully Managed, we already operate SovereignDB, so it's not a separate add-on there. Keeping metadata current is data governance, included as part of DBAsk either way.
What DBAsk delivers
Ask Anything, In Plain English
Business users ask questions naturally, analysts get complex SQL in seconds. No query language required on either side.
Metadata Intelligence
DBAsk continuously discovers and documents your data: glossary, table and column definitions, relationships, and business rules.
Transparent SQL
DBAsk never hides the query. Every result comes with the SQL, sources, and definitions used, so you can verify before you trust.
Explain Mode
Ask DBAsk to explain the SQL it just generated. It breaks down which objects it used and why, and the metadata behind each choice, so a reviewer can check the logic without reading the query line by line.
Full Observability
Every AI interaction, query, and data access event is logged and auditable, supporting your own GDPR and sector-specific compliance requirements.
Sovereign by Design
Deployed wherever you choose, public cloud, private cloud, on-prem or air-gapped. No raw data egress, ever, only metadata reaches the model.
VLDB Managed
Our specialists handle deployment, metadata curation, model performance, and ongoing support, without touching your underlying data.
Designed for every team, built for organisations that can't expose data
No raw data ever reaches the model, so it suits every team that touches the data, and sectors where exposure isn't an option.
Business Users
Ask questions naturally. No SQL required, and no waiting on a report queue.
Analysts
Generate complex SQL in seconds, then inspect, refine, and run it with full confidence in the source.
SQL Developers & DBAs
Review and approve every generated query before it runs, and let DBAsk automatically document data assets instead of maintaining a wiki no one reads.
Data Governance
Centralise business definitions and canonical metrics so every team works from the same source of truth.
Regulated Industries
Law firms, financial services, and healthcare organisations get AI-assisted insight with the guarantee that raw data never reaches the model, full audit trails included.
CIOs & IT Leaders
Safely scale enterprise AI with governance, security, and observability built in from day one.
Want DBAsk bundled with database operations, pipelines and data models, as one managed service? See DBAI Platform.
Stop asking AI to guess. Teach it.
Talk to our specialists about deploying DBAsk and giving your teams reviewable, transparent SQL.