Defense in depth
Validate input, constrain generated SQL, and enforce read-only execution instead of relying on the system prompt.
A natural-language-to-SQL chatbot built into a security dashboard, enabling users to query complex data in plain English instead of navigating multiple views and filters. Built solo from prompt engineering to Kubernetes deployment.
Users needed to answer complex security questions without manually combining dashboard views and filters, while the system still had to protect private enterprise data and prevent generated queries from becoming an execution risk.
Validate input, constrain generated SQL, and enforce read-only execution instead of relying on the system prompt.
Externalized configuration allows reviewed prompt changes without rebuilding the application.
Confidential. Evaluation used a reviewed set of representative security questions and checked generated SQL for validity, read-only behavior, execution, and answer usefulness.
Implementation details and source code are not public because this is a private repository.