Retrieve Cortex Search (General availability)
The CORTEX_SEARCH_RETRIEVE table function is now generally available, allowing users to run low-latency Cortex Search queries directly from SQL.
Also shipped Nov 18, 2026Snowflake in November 2026 →
Genie Code CLI is now generally available
Databricks has made the Genie Code CLI generally available, aligning its management with workspace Genie Code. Administrators can oversee a single Genie Code budget across both the CLI and workspace, while users can apply free monthly usage in the CLI.
Smart Routing now supports external models for coding agents (Beta)
Databricks added support for routing coding-agent subagents to external model providers in the Unity Gateway Managed Configuration beta.
V3 progress control | CodeRabbit Cloud, V3 review settings preview
CodeRabbit updated progress controls in the V3 review settings preview, allowing progress_updates configuration to control review-progress reporting format.
Hyperdrive, Workers VPC - Custom CA and client certificates (mTLS) for Workers VPC
Cloudflare Workers VPC now supports custom certificate authority (CA) verification and mutual TLS (mTLS) authentication for private VPC Services.
Amazon OpenSearch Memory is now generally available
Amazon OpenSearch Memory is now generally available as a serverless capability in Amazon OpenSearch Service to store, extract, and retrieve persistent memory for AI agents.
Introducing the Apache Spark Optimization Agent for AWS Glue ETL
AWS Glue ETL introduced the Apache Spark Optimization Agent, which analyzes completed Spark runs to deliver automated cost and performance recommendations.
More from Snowflake Cortex AIEvery Snowflake Cortex AI release →
AI_EXTRACT citations (Preview)
Snowflake Cortex AI_EXTRACT now supports citations that link extracted values to source documents. This feature enables users to verify results and review information in context.
Cortex Agent SDK (General availability)
The Cortex Agent SDK is now generally available for Python and TypeScript. It enables developers to build applications that run Cortex Agents, stream responses, and manage long-running conversations.
Prompt caching for Cortex AI Functions
Prompt caching for Snowflake Cortex AI_COMPLETE functions is now generally available. This feature reduces costs and latency by caching shared content like system prompts or few-shot examples across multiple requests.
Data governance policy inheritance for Cortex Search (Public Preview)
Data governance policy inheritance for Cortex Search is now available in Public Preview. When you set INHERIT_DATA_GOVERNANCE_POLICIES = TRUE on a Cortex Search service, the service honors the row access policies and masking policies on its base table, so query results reflect each caller's own access instead of the service owner's.
AI_COMPLETE adds support for Snowflake Decision (Preview)
Snowflake Cortex AI_COMPLETE now supports Snowflake Decision in public preview, a model for high-throughput classification and decision-making on unstructured data.
AI_EXTRACT accuracy improvements (Preview)
Snowflake improved the accuracy of AI_EXTRACT for field, list, table, and layout extraction.
AI_COMPLETE adds support for Twelve Labs Pegasus 1.5 (General availability)
Snowflake Cortex AI_COMPLETE now supports the Twelve Labs Pegasus 1.5 video understanding model. This allows users to analyze video content and extract structured insights using natural language prompts.
Cortex AI Function Optimization for more efficient AI implementations (General availability)
Snowflake Cortex AI Function Optimization is now generally available. It allows users to evaluate multiple model candidates and prompts against consistent datasets to improve performance and manage costs.