What does it take to get started, and how long until we see value?
Connect a source, ask a question, get an insight. A formal evaluation runs as a scoped pilot of eight to twelve weeks against one governed use case with your own data.
The three steps
- Connect. Add a database or upload files. Schema and metadata are discovered automatically and the connection is tested live before it is saved.
- Ask. A question in plain English becomes safe, read-only SQL, executed on the source.
- Insight. Formatted results, an automatically chosen chart, and a full-page analytics view when the answer deserves one.
The formal path
A pilot is time-boxed to eight to twelve weeks and scoped to one governed use case, using your own data. It includes a guided security and architecture review, sandbox and datasource setup, and success criteria plus conversion terms agreed up front, so the evaluation ends in a decision rather than an extension.
What to bring
One use case that currently waits on an analyst, one source that can accept a governed read-only connection, and the ten questions your team actually asks about that use case. Those ten become the golden set the pilot is scored against.
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
- 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.
- 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.