Composer's Prompt menu has a new option. The feature uses your role, industry, and any topics you provide to create between three and nine clear, structured prompts. These prompts follow our recommended prompt format, similar to those created using the Improve prompt feature.

The provider configuration table now shows both available and total subscription quotas, limits deployment selections to available capacity, and improves the readability of long provider details by truncating text and expanding it on hover. When switching providers, the table also defaults to the first available option.

Selecting files and folders from the file system is now smoother and more intuitive, making it easier to attach the right content to your conversations.

The Admin dashboard is now focused on the AI Adoption. Per user token usage is now available directly on the dashboard.

Newly created deployments now default to the Global Standard configuration, providing more consistent availability and performance out of the box.

Provider setup and management have been refined for a more reliable configuration experience.

Rate-capture job now automatically retries when the upstream service is temporarily rate limited, improving the reliability of usage and cost data.

Web search and document generation now provide clearer in-progress status details, making it easier to understand what the assistant is doing during longer-running requests. Model reasoning indicators have also been refined so internal status content does not appear in the final response.

A new guided wizard simplifies provider configuration and helps administrators complete setup more efficiently. The wizard also displays provider save errors instead of failing without clear feedback.

The favicon configuration experience now informs administrators that customers may need to perform a hard refresh before a newly configured favicon appears.

AI Portal now accounts for cached tokens when tracking model usage and normalizes model pricing to a per-million-token rate. Improved mapping between model variants and their billing models provides administrators with more accurate usage and spend calculations.

Files has been redesigned to give you a more organized and consistent view of your content.

Added support for Anthropic Opus 5 and OpenAI GPT-5.5.

You can now organize your work in the prompt library by clicking on files. Files lands you directly in your private folder and lets you browse your prompts.

GPT-5.6 is now available as a selectable model, giving you access to the latest generation of capabilities within your conversations.

The message composer has been refined with a series of interface updates and fixes for a smoother, more reliable prompt-writing experience.

Added keyboard shortcuts to help you navigate and work more quickly throughout the interface.

The "Improve Prompt" feature now produces cleaner, better-organized results. Improved prompts now clearly separate context, goals, and output format, and use significantly less markdown—reserving headings for "Identity" and "Instructions" while keeping the rest as plain text for easier reading.

The model selector now visually highlights the currently selected model, making it easier to see which model is active at a glance when choosing between options.

The right sidebar in the composer has been replaced with a menubar, providing a more streamlined and familiar layout for accessing composer actions.

AI Portal now automatically provisions an embeddings model, so retrieval-augmented generation (RAG) is ready to use without additional manual setup.

Blocking operations across file processing and related services were moved to asynchronous execution. This improves overall responsiveness and reliability, particularly when handling resource-intensive uploads.