Responsive spacing across design and CSS
Auto layout's auto spacing now has two new options, “Around” and “Evenly”, alongside the existing default auto spacing behavior now called “Between”.
Also shipped Aug 21, 2026Figma in August 2026 →
Version targeting for Cortex Agent and Cortex Analyst evaluations (General availability)
Cortex Agent and Cortex Analyst evaluations now let you control the versioned configuration used for scoring: Version targeting pins the configuration under evaluation, not the agent behavior that gets evaluated: each run invokes the agent again and scores a newly generated trace.
CoCo automations in CLI and Snowsight (Preview)
CoCo automations in the CoCo CLI and CoCo in Snowsight are now available in public preview. Automations let you schedule recurring, unattended CoCo runs that execute in a Snowflake-managed sandbox. Each run creates a Cortex thread that you can inspect and continue in CoCo. Automations created from one surface can be monitored and managed from the other.
Upcoming end of life for the Supervisor API
The Supervisor API (Beta) reaches end of life on September 30, 2026. After that date, the API is no longer available. Databricks recommends migrating to custom agents on Databricks Apps . See Supervisor API (Beta) (deprecated) .
Consumer access to query Unity Gateway services will become generally available
Querying Unity Gateway model services and model provider services with Consumer access is currently opt-in through the Consumer access to Unity Gateway Public Preview . When this capability becomes generally available, consumer access users will be able to query these services without the preview enabled.
Monitor all AI activity with the unified trace table (Beta)
The unified trace table is in Beta . It captures every request and response across your Unity Gateway services into one Unity Catalog table in OpenTelemetry format, giving you a single place to monitor, debug, secure, and audit all AI activity. See Monitor all AI activity using the unified trace table .
Default Python package repositories are GA for Lakeflow pipelines and classic compute
Configuring default Python package repositories is now generally available for Lakeflow pipelines and for classic compute created via the UI and API. Workspace admins can set private or authenticated registries as the workspace default for these workloads. See Configure default package repositories .
More from FigmaEvery Figma release →
Erase and drag to fill for vector editing
Vector editing in Figma now brings familiar interactions to precise edits on the canvas.
Enterprise-managed authorization for MCP is now generally available
Admins on Enterprise and Organization plans can centrally manage Figma MCP server's connection to AI agents (e.g. Claude) through their identity provider (e.g. Okta), so users don't have to authenticate individually or click through repeated consent prompts.
Recommend resources you want users to discover and use
Admins can now choose which resources (skills, templates, libraries, and Make kits) are recommended to your organization or workspace.
Open the agent chat panel in a new window
You can now open the agent chat panel into a new window on the Figma desktop app for both macOS and Windows. It stays visible when you work with other tools or switch tabs.
Get responsive text across screens with text wrap
Text wrap makes your text responsive with two new options: Balance and Pretty. Set either on a text layer, a text style, or an individual paragraph in text settings.
Try skills from the Community and make your own with the Figma agent
We've added more ways to discover, create, and share skills for the Figma agent.
Figma MCP: Run Weave tools, right from your favorite agent
Starting today, you can run your Figma Weave tools from Codex, Claude, or Cursor using the Figma MCP server.
Updates to generative plugins and shaders
At Config, we launched the ability build your own custom generative plugins and shaders by prompting the Figma agent. Now, you can do more with those generative plugins and shaders with animations and interactions, publishing capabilities, and access to the code.