Dia
Let your business ask its own questions. Keep control of the answers.
Dia is a self-hosted analytics platform. People ask in plain English. Dia answers from your Oracle, SQL Server or Postgres data using only the business definitions your data team approved, and it cannot change a single row.
Or ask this site. It answers from the pages here, with sources.
The worry
What stops teams from putting AI on their data.
It will join the wrong tables.
Once your data team has approved the business model, code chooses the joins from relationships a person approved. The AI reads the question. It never invents a join.
It will run something destructive.
Every query is checked in code before it runs. Anything that writes is refused, even a DELETE hidden in a larger statement. Connections are read-only unless an administrator decides otherwise.
We will not know how it got the answer.
Each answer shows the SQL it ran, the definitions it used and the assumptions it made, so anyone can check it before it is used.
Why now
Every board is asking for AI on company data. Every data team knows the risk: a model that writes its own SQL against production, answers nobody can check, and data that leaves the building. Dia was designed for the team that has to say yes to the first and no to the second.
A week with Dia
The AI reads the question. Code does the rest.
Monday, finance asks which vendors are late and by how much. Dia answers from accounts payable, with a chart by region. Wednesday, an analyst opens the same answer in the workbench, profiles the invoice table and adds a data-quality rule so duplicates are caught. Friday, IT reads the audit log: every question, every query, who asked, what ran.
01AI
Understand
The AI works out what you're asking
02
Resolve
Matched to business terms your team approved
03
Plan
Code picks the joins. The AI never does.
04
Check
Anything that would change data is refused
05
Answer
A table, a chart, and the assumptions behind them
In Dia the AI never invents a join. It can only use relationships a person has approved, so every answer traces back to definitions your team agreed on.
One platform
The chat is the front door.
Dia is one platform from the first byte to the last chart. It brings your data in and streams it, queries it across every source, keeps it in a governed lakehouse, and lets people ask, see and act on it. The chat is the front door. Everything behind it is the same product.
01
Bring data in
Change capture, streams and files from the systems you run.
Databases · Change capture · Streams · Files · APIs
02
Query it
One SQL over every source, fast enough for a dashboard.
Federated SQL · Workbench · Profiling · Quality rules · Plans
03
Keep it
A lakehouse with history, a catalog, your own storage.
Lakehouse · Time travel · Catalog · Object storage
04
Use it
Ask, explore, dashboards, stories, agents and lineage.
Ask · Explore · Dashboards · Stories · Agents · Lineage · MCP
Who it's for
Built for the people who answer for the numbers.
Data and analytics leaders
who want the business to ask its own questions without losing control of what the answers are built on.
Analysts and engineers
who spend their days writing the same SQL for other people, and want a workbench with profiling, quality rules and lineage in one place.
IT and security teams
who will only let AI near production data if it provably cannot change it, and if it runs on their own servers.
Fits your stack
It fits the stack you have.
Databases
- PostgreSQL
- MySQL
- Oracle
- SQL Server and Azure SQL
- SQLite
- DuckDB
- BigQuery
- Trino, and the engines it federates
Files
- CSV
- Excel
- JSON
- Parquet
Documents
- Confluence
- Jira
- SharePoint
Sign-on
- Keycloak
- Microsoft Entra ID
- Any OIDC provider
Models
- OpenAI
- Azure OpenAI
- Anthropic
- Ollama, on your own hardware
Results
Measured, with the method.
Every result on this site links to how we measured it and the data we used.
Who we are
Satvi is a software company in Atlanta. We build Dia. Our founder spent twenty years building governed data platforms inside large enterprises and watched every generation of self-service BI promise that the business could ask its own questions. Dia is the first time the answer can be trusted, because the AI is kept to the one job it is good at and the data team stays in control of everything else.
See Dia on data like yours.
A guided demo takes about forty minutes. Bring a question your team gets asked every week.