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.
Layered, and each layer assumes the one above it failed.
The query itself
Only read queries are permitted. INSERT, UPDATE, DELETE and DDL statements are blocked rather than discouraged. Queries are parameterized throughout, so a prompt that tries to smuggle SQL through a question does not get a second statement executed.
The authorization path
Every query passes two gates: workspace access, then datasource permission. Both must allow it. A user who has been granted a workspace but not a source inside it does not reach that source, which is what "zero data spillage" means in practice.
The credentials
Connection credentials are encrypted at rest with AES-256-GCM. Session passwords live in Fernet vaults with a one hour TTL, so a password supplied for one working session does not become a stored secret.
The escape hatch for the strictest cases
If a system may not accept an inbound connection at all, the enterprise tier runs execution on your own infrastructure, inside your network boundary.
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.
- 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.