# October 2025

## SaaS Platform Migration from Azure to AWS

* We have migrated both our EU and US SaaS environments from Azure to AWS for all users who rely on our cloud-hosted SaaS platform.

## AI Asset Management Improvements

### Issues Page

* Introduced a unified **Issues dashboard** with full visibility into pending and resolved issues, including severity breakdowns, environment, asset types, and detection timestamps.
* Added an **Issue Detail view** that displays asset metadata, issue descriptions, recommended actions, and supports commenting.
* Implemented a **resolution workflow** that allows users to mark issues as resolved with specific resolution types (e.g., *Not reproducible*) and add notes for auditability.
* Added a **changelog** to track all issue status updates and reviewer actions.

<figure><img src="https://1029475228-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2Fi12bk7lo75SODuwcRCQp%2Fuploads%2FqF2a2kCJGs96BbPn7PF7%2Fprobe.splx.ai_w_31_ai-assets_issues_tab%3Dpending%20(2).png?alt=media&#x26;token=9b0397ed-cde0-42a3-b393-d4ad63dd587c" alt=""><figcaption><p>Figure 1: Issue Details on Issues Page</p></figcaption></figure>

### Overview Page

* Updated **AI Asset Management Overview** page to include an issues summary table showing the five most recent issues, along with a severity pie chart that highlights the total number of issues across Critical, High, Medium, and Low levels.

### Models Page

* Each discovered model can now be marked as **Approved**, **Unreviewed**, or **In Review**.
* A status distribution section has been added to the **Models** page to visualize these categories.
* The **Models** page now also includes a table listing all issues related to models.

## Model Benchmarks

* Our [Model Benchmarks](https://docs.probe.splx.ai/ai-benchmarks/model-benchmarks) have been extended to include results for the following models:
  * CodeLlama-13b-Instruct-hf
  * CodeLlama-34b-Instruct-hf
  * CodeLlama-7b-Instruct-hf
  * Phi-4
  * Qwen2.5-Coder-1.5B-Instruct
  * Qwen2.5-Coder-14B-Instruct
  * Qwen2.5-Coder-32B-Instruct
  * Qwen2.5-Coder-7B-Instruct
  * Qwen3-30B-A3B-Instruct-2507
  * Qwen3-4B-Instruct-2507
  * Qwen3-Next-80b-A3B-Instruct
  * Qwen3-Next-80b-A3B-Thinking

## Improvements & Tweaks

* Added an **AI Analysis** flag to analyzed probe runs, visible on Probe Cards in the Overview page and in the Probe table on the Test Run page.
* Added **tooltips** across AI Assets to provide clear explanations of key terms.
* **AI Runtime Protection** now automatically saves policy changes.
* Added **OAuth authentication** to the REST API Connector, enabling integration with Targets that require token-based authentication. For more details, refer to the [REST API](https://docs.probe.splx.ai/ai-red-teaming/probe/target/index/rest-api) connection page.