Databricks databricks-ai-functions
Guides using Databricks AI Functions (LLM SQL functions) inside SQL and pipelines.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Databricks databricks-ai-functions, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
A Databricks Agent Skill for the AI Functions feature — calling LLMs directly from SQL (ai_query, ai_classify, etc.). It encodes function signatures and usage patterns. Generates SQL/pipeline code that runs against the user's Databricks warehouse.
Key features and capabilities
- AI Functions (ai_query etc.)
- LLM-in-SQL patterns
- Pipeline integration
Use cases
- Add LLM classification to a SQL pipeline
- Enrich a table with AI Functions