Releasesby GlyphAI Functions Asynchronous API (Beta)
You can now use the AI Functions Asynchronous API to run ai_parse_document , ai_extract , or ai_classify asynchronously on up to 50,000 requests from a JSONL file in a Unity Catalog volume. The batch writes one result for each request to a file in a volume. Workspace admins can turn on the AI Functions Asynchronous API preview from the Previews page .
Also shipped Nov 9, 2026Databricks in November 2026 →
AlloyDB AI smart batching and sentiment analysis are generally available
AlloyDB AI smart batching for AI functions and the ai.analyze_sentiment function are now generally available on PostgreSQL 17 and later. Smart batching improves query performance by offloading AI operations asynchronously.
BigQuery compute cost attribution is available in preview
BigQuery now supports compute cost attribution in preview, allowing users to track billed compute charges at the project level based on reservation capacity usage for FinOps reporting.
BigQuery jobs explorer performance troubleshooting is generally available
BigQuery jobs explorer now provides generally available tools for troubleshooting query performance and comparing job and system performance to diagnose regressions.
BigQuery pipeline task concurrency limits are generally available
Users can now specify the maximum number of concurrently executed tasks when creating or scheduling BigQuery pipelines.
BigQuery adds Zstandard compression functions in preview
BigQuery now supports Zstandard (Zstd) compression and decompression functions for bytes and string values in GoogleSQL, currently available in preview.
AWS Glue adds 100 new native connectors for popular SaaS applications
AWS Glue now includes 100 native connectors for SaaS and REST API applications, enabling data integration without custom code. These connectors allow teams to reuse connections across ETL jobs with existing permission models.
More from Agent Bricks and Mosaic AIEvery Agent Bricks and Mosaic AI release →
Provision Claude desktop with MDM using Unity Gateway
Admins can now use Unity Gateway to provision the Claude desktop app machine-wide via MDM, including pre-configured models, MCP servers, and skills for macOS users.
Anthropic Claude Fable 5.2 is now available on Unity Gateway
Anthropic Claude Fable 5.2 is now available on Unity Gateway. You can access this model using Foundation Model APIs . Customers are responsible for ensuring their compliance with applicable terms .
Allow ChatGPT and Claude as partner platforms in context-based ingress policies
Context-based ingress policies now allow traffic from ChatGPT and Claude as partner platforms, enabling hosted MCP clients to connect to Databricks workspaces.
Google Gemini 4 Carbon is now available on Unity Gateway
Google Gemini 4 Carbon is now available via Foundation Model APIs on Unity Gateway.
Text and binary inputs for protobuf requests to custom model serving endpoints (Public Preview)
Custom model serving endpoints now support text and binary data as KServe v2 BYTES tensors in protobuf requests. This feature is in public preview.
Budget alerts can now trigger webhooks (Beta)
You can now configure budgets to trigger webhooks when spend thresholds are exhausted, so budget events can be routed to incident, ticketing, or automation tools. See Trigger custom webhooks .
Bring your own ChatGPT subscription to Codex with Unity Gateway
Users can now connect their own ChatGPT subscriptions to Codex and ChatGPT desktop via Unity Gateway. This allows requests to be billed to the user's subscription while maintaining centralized access governance.
Write custom service policies in Python (Beta)
Users can now write custom service policies as Python functions in Unity Catalog. This allows for complex rules, such as regex or external guardrail calls, that cannot be expressed in SQL.