6 articles
Databricks operates a large-scale LLM inference platform serving frontier models with 120T+ tokens monthly.
Prompt caching reduces redundancy in LLM inference by reusing computation for identical prompts across multiple requests.
Databricks enables storing OpenTelemetry AI traces in Unity Catalog as Delta tables, improving observability for production AI agents.
Databricks Genie and TabPFN combine to enable business users to ask predictive questions in natural language through a multi-agent orchestrator.
Databricks introduces the industry's first certification for context engineering in AI agent systems.
Claroty's AI library automates CPS asset identification and vulnerability management.
