Here's what's new in our latest update:

Visualization and Analysis Agent

Explore your simulations through natural language. The agent reasons about your domain and data to suggest useful visualizations, and creates, updates, and removes filters — isosurfaces, slices, clips, and streamlines — from plain-language requests. It resolves surfaces by informal names and boundary conditions, controls visibility, and manages colormaps, surface representations, and grid axes. Batch multiple requests in a single message to build a complete scene in one go.

Account wide Agent Settings

You can now set account-wide default instructions for Luminary Agents from a new "Agent Defaults" page in the Administration section. These instructions will automatically apply to all assistant sessions across your account, making it easier to establish consistent agent behavior for your organization.

Meshing Improvements

Mesh deformation now properly respects symmetry planes and their combinations, ensuring that deformations remain symmetric across these boundaries.

Here's what's new in our latest update:

Improvements to Project Management

Project copying now runs as a background task, allowing you to continue working while the copy completes. To prevent accidental duplicate copies and associated costs, you can now only run one project copy operation at a time.

Updated meshlibs

Updated mesh processing libraries to support NX 2512 and Solid Edge 2026 file formats. This enables you to import and work with CAD files created in these latest software versions.

Here's what's new in our latest update:
​

Model Selection

You can now choose which AI model to use in the AI Assistant. A model selector has been added to help you pick the option that best fits your needs.
​

Geometry Check

The Check Geometry operation now runs without a Cancel button. We've improved the messaging to clearly indicate that this operation may take some time to complete.

Improved MCP Server Capabilities

You can use the MCP server to supports data generation at scale with pipelines.

Simulation Naming for DoE

You can now include simulation names directly in your CSV file when uploading designs of experiments (DoE).

Improved Compute Efficiency

We are migrating Luminary Mesh Adaptation (LMA) Standard jobs to our new ARGO-based compute infrastructure. This release improves resource efficiency.

Here's what's new in our latest update:
​

Support for Opus-4.8

The AI assistant now uses Claude Opus 4.8, the latest version of Anthropic's most capable model, providing improved performance and accuracy for complex tasks and conversations.
​

Here's what's new in our latest update:
​

Improvements to Hypersonic Flows

You can now select a radiative equilibrium wall energy condition option for more accurate modeling of steady-state hypersonic flows.
​

New Turbulence Models

There are two new turbulence modeling options for SST: a "sust" modification that helps maintain freestream turbulence levels, and the Hellsten rotation correction that improves accuracy in rotation-dominated flow regions.

Here's what's new in our latest update:
​

Moment Distribution Visualization

The moment distribution visualization is now available in the user interface as a 2D plot, making it easier to analyze and understand moment data alongside the existing force distribution visualization.
​

Results Table

The Results table now includes a "Mesh Strategy" column that displays how each simulation's mesh was created (LMA, Max Count, Target Count, or Minimal). You can search, sort, and filter results by mesh strategy to better organize and compare your simulations.

Here's what's new in our latest update:
​

Import OnShape Configurations

You can now retrieve configuration parameters from OnShape Part Studios, making it easier to work with parameterized CAD models in your workflows.
​

Results Table

The results table has additional columns

• Time column
• Material columns (with Type and Material for each material)
• Physics columns (with Name, Viscous model and Turbulence model for each physics).

Here's what's new in our latest update:
​

AI Assistant Updates

Web Search

The AI assistant can now search the web in real time to answer questions about current information — such as the latest software documentation, recent research, or up-to-date product details — going beyond what is stored in its knowledge base. This capability is available across all main-app assistant agents, including the supervisor, setup, data analytics, and recommender agents.
​

Latest Models

The AI assistant now uses latest Opus 4.7 and GPT 5.5 models for various tasks on the platform

Here's what's new in our latest update:
​

New Colormap

You can select Fast from the colormap picker in the visualization UI, alongside existing options like Rainbow, Cool to Warm, and Plasma.
​

Deduplicate Pipeline Job Creation

An optional `request_id` parameter is now available. This can be used as an idempotency key to deduplicate pipeline/job creation across multiple logically identical requests.

Here's what's new in our latest update:
​

Automatic Streamline Seed Placement

The Python SDK now includes AutoStreamlines, a new filter that automatically determines optimal seed placement for streamline visualizations using a data-driven approach. This removes the need to manually configure seed positions, making it easier to generate accurate flow visualizations with less setup.

Web Search in the Notebook AI Assistant

The Notebook Assistant is able to do web searches to fetch the latest information about coding tasks and others.