Releasesby GlyphWhat's new in Sigma
AI Customize first agent message (Beta) Customize the first message sent by a Sigma agent. You can set a fixed message or a specific prompt for a generated message. For example, modify an agent to send a specific text greeting like "Welcome to Sigma!" as a fixed message, instead of the agent using the AI provider to generate a message.
Also shipped Jul 10, 2026Sigma Computing in July 2026 →
Online Feature Store (Public Preview)
Online Feature Store is now available in public preview. Serve the latest feature values with low-latency online retrieval backed by Snowflake Postgres for real-time ML applications such as fraud detection, recommendations, and personalization.
Databricks-provided MCP Services will GA soon
Databricks-provided MCP Services for SaaS applications such as Slack, GitHub, Atlassian, and Google Drive will soon be generally available, with both read and write operations enabled by default. Admins and users can disable MCP Services and individual tools in Unity Gateway . See Connect agents to tools with MCP Services .
Secrets in Unity Catalog (Public Preview)
You can now store, govern, and access secrets as securable objects in Unity Catalog. A Unity Catalog secret uses the three-level namespace ( catalog.schema.secret ) and is governed by Unity Catalog privileges, so you can apply the same access controls and auditing that you use for other data assets. See Secrets in Unity Catalog .
Dreams research preview adds Claude Fable 5 and Claude Sonnet 5
Dreams, in research preview, now supports Claude Fable 5 and Claude Sonnet 5.
Agentic autofix for code scanning alerts in public preview
Agentic autofix is now in public preview for all code scanning alerts. It remediates alerts generated by CodeQL and third-party scanning tools by working across your codebase the way a developer would, it explores relevant files, proposes a fix, and reruns the original analysis to confirm the fix closes the alert before opening a pull request for your...
supabase-js will require TypeScript 5.0+ from January 31, 2027
@supabase/supabase-js will require TypeScript 5.0 starting January 31, 2027, dropping support for TypeScript 4.7 to 4.9.
More from SigmaEvery Sigma release →
What's new in Sigma
AI Add data model tables as data sources for agents (Beta) You can now add relevant data model tables as data sources for Sigma agents. For instructions, see Build Sigma agents . Assistant in build mode: formula join keys (Beta) In workbooks, Sigma Assistant in build mode can join tables on formulas and expressions, not just raw columns.
What's new in Sigma
AI Anthropic as an AI provider (Beta) Add an Anthropic API key to use models from Anthropic with Sigma AI features. When you set up Anthropic as your external AI provider, you use Anthropic for the LLM model and must also configure a second AI provider with an embeddings model available. For more details, see Add Anthropic as an AI provider .
What's new in Sigma
AI Monitor MCP queries You can now use the "kind":"mcp" tag to monitor queries sent by the Sigma MCP server. This can be helpful to monitor costs or usage associated with the MCP server. See Monitor MCP queries for more information.
What's new in Sigma
AI Sigma plugin for ChatGPT You can now install the Sigma MCP server for ChatGPT in one click using the Sigma plugin. For more information, see Use the Sigma MCP server . Support for Amazon Bedrock AI provider (GA) Amazon Bedrock is now a supported AI provider, letting you use Anthropic foundation models with Sigma AI-powered features.
What's new in Sigma
AI AI column support for Databricks connections (Beta) You can now create and use AI columns on Databricks connections. AI columns allow you to construct dynamic prompts that reference specific table columns, which can be helpful for tasks like enriching, summarizing, and classifying data. See Create AI Columns (Beta) .
What's new in Sigma
AI Agent skill for the Sigma CLI The sigma-cli skill provides instructions and reference materials that an AI assistant can use to call the Sigma REST API from the command line with the Sigma CLI. For more information, see Install skills for AI assistants .
What's new in Sigma
AI Build and interact with Sigma agents (Beta) Build agentic solutions natively in Sigma with Sigma agents . Agents provide AI capabilities to a dashboard or application based on a predefined context of the data elements in a workbook.
What's new in Sigma
AI New model used for Gemini and BigQuery AI providers If you use Gemini as your AI provider through an API key or a BigQuery connection, Sigma now uses Gemini 3.6 Flash as the LLM. For more details, see Set up an AI provider .