> For the complete documentation index, see [llms.txt](https://docs.probe.splx.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.probe.splx.ai/updates/product-updates/july-2025.md).

# July 2025

## Analyze With AI

Quickly turn probe run results into clear, actionable insights with **Analyze with AI**. The feature highlights key attack methods, and suggests **Dynamic Remediation Tasks** to guide your next steps. It’s designed to save time and make complex red-teaming data easier to understand.

Learn more in our [docs](https://docs.probe.splx.ai/platform/probe-run/analyze-with-ai) and on our [blog & video](https://splx.ai/blog/analyze-red-teaming-data).

## Custom Policies

Create and manage custom compliance rules with **Custom Policies**, enabling you to define workspace-specific policies with sections and items mapped to probes for live compliance tracking. Policies can be imported or exported via JSON for easy setup and sharing.

Learn more in our [compliance docs](/ai-red-teaming/probe/compliance.md#custom-policies).

## OpenAI-Complatible API Connection

You can now connect targets that are designed with an **OpenAI-style API interface**. This allows Probe to seamlessly interact with models and services that follow the same request/response format as OpenAI’s API.

Learn more on dedicated [connection page](/ai-red-teaming/probe/target/index/openai-compatible-api.md).

## Platform Rebranding

The SPLX Platform has been updated to match our **new visual identity**.

## Improvements & Tweaks

### Test & Probe Run Improvements

* **Credit Display:** Starting a new test run now shows the cost in credits before execution.
* **Delete Test Runs:** You can now delete a test run. This action is permanent and cannot be reversed.
* **Failed Conversations:** Failed conversations are now highlighted in test case details for easier navigation.
* **Improved Navigation:** Test cases can be navigated sequentially with next/previous buttons in the details view.
* **Execution Insights:** End execution time and failure rate are now displayed in both test run and probe run views.

### Reports

* **Custom Branding:** Add your organization’s logo in settings to display it at the top of all SPLX Platform generated reports.

### Targets & Connections

* **Amazon Bedrock:** Additional LLM configuration inputs are now supported.
* **Test Connection:** Redesigned view now shows request/response details in collapsible, copyable sections for easier debugging.


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://docs.probe.splx.ai/updates/product-updates/july-2025.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.