What is dataface.ai?
dataface.ai is on-source conversational analytics. Ask a question in plain English, and it generates read-only SQL from your schema metadata and runs it on the systems you already own. No warehouse copy, no pipeline.
dataface.ai turns a question in plain English into an answer from the systems you already run.
The short version
Connect a database or upload files, ask a question, and get a formatted result with a chart. The question and your schema metadata go to the model, the model returns SQL, and that SQL runs read-only on your infrastructure under credentials you control. Only the result set comes back.
What makes it different
Conventional tools move the data to the analytics: a pipeline to build, a warehouse copy to license, and a second copy of regulated data to secure and audit. dataface.ai moves the questions to the data instead, so neither the pipeline nor the copy exists.
Who it is for
Teams that wait in an analyst queue for answers already sitting in their own systems, most often where copying the data is the expensive part.
Where it is today
The product is live and access is invite-only, through a scoped pilot against one governed use case with your own data.
Where this comes from
See it against your own data
A pilot is scoped to one governed use case and time-boxed to eight to twelve weeks, with success criteria agreed before it starts.
Get started freeRelated questions
- How do you run analytics without moving our data?dataface.ai reads your schema and a few example values per column, generates read-only SQL, and executes it on the source system itself. Your tables are never copied: no pipeline, no warehouse copy, no second place to secure.
- What does the LLM actually see from our data?By default the model sees your catalog: table names, column names, types, and a few example values per column. It never receives your tables, and it only sees query results if a user turns on AI analysis.
- How do you stop an AI from writing to or damaging our database?Generated SQL is SELECT-only. INSERT, UPDATE, DELETE and DDL are blocked, queries are parameterized against injection, and every request passes both a workspace gate and a datasource gate.
- Can we run this entirely inside our own network?Yes. Enterprise agreements cover dedicated, VPC, and on-premise deployment, with edge execution on your own infrastructure at a reduced credit rate.