> ## Documentation Index
> Fetch the complete documentation index at: https://arize-ax.mintlify.site/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# October 2025

## API-Driven Monitors

October 30, 2025

<Frame>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/api-driven-monitors.png" alt="API-Driven Monitors" />
</Frame>

We now have API-Triggered Monitors:  A monitor type that **only evaluates when triggered via API call**, instead of on a fixed schedule. Ideal for teams running evaluations after events like batch ingestions, model retraining, or CI/CD workflows.

## Automatic Threshold Ranges for Monitors

October 30, 2025

You can now set **upper and lower bounds** using our new **Auto Threshold** options!

Arize can **automatically determine the right threshold** for your alerts based on your **historical data.** This is ideal for **most users** who want to start monitoring without manually tuning thresholds.

## Data Fabric

October 29, 2025

<Frame>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/data-fabric.avif" alt="Data Fabric" />
</Frame>

We're excited to introduce [**Data Fabric**](/docs/ax/security-and-settings/data-fabric), a new capability that automatically synchronizes production trace data, evaluations, and annotations from Arize into your cloud data warehouse every 60 minutes in Iceberg format—giving you an always-current, query-ready source of truth.

## New Timeline Tab for Traces

October 28, 2025

<Frame>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/trace_timeline.png" alt="New Timeline Tab for Traces" />
</Frame>

You can now see a timeline view when you click into a trace! The new timeline view is right next to the Trace Tree and Agent Graph tabs, and it shows the execution flow and duration of each span.

## Tags

October 24, 2025

<Frame>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/tags-ui.png" alt="Tags UI" />
</Frame>

Tags are a lightweight way for you to organize and label your entities across the Arize Platform. You can use tags to:

* Describe source (`from-prod`, `EHR-record`)
* Encode purpose (`ab-test`, `regression-test`)
* Indicate readiness (`golden`, `deprecated`)
* Group by config (`threshold-0.85`, `cohort_5`)

Tags live at the `Space` level, under Space Settings. They can be reused across entities that belong to that space (Datasets, Experiments, and more). More on [Tags](/docs/ax/security-and-settings/tags).

## Sort Datasets and Experiment Listing Table

October 22, 2025

<Frame>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/sort-datasets-and-experiments.png" alt="Sort Datasets and Experiment Listing Table" />
</Frame>

You can now sort your datasets and experiments by name, number of experiments, creation date, and more!

## Support for Tool Call IDs in OpenInference Messages

October 15, 2025

This update introduces full support for `tool_call_id` and `tool_call.id` in OpenInference message semantics. These identifiers are now stored alongside input and output messages. Tool call IDs now appear in the trace slideover's input/output and attributes tabs.

## Add Data Region to Login Page

October 14, 2025

<Frame>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/arize-ai-data-region.png" alt="Add Data Region to Login Page" />
</Frame>

We’ve added a **Data Region** selector to the login page, allowing users to choose their preferred data region during sign-in. This helps ensure compliance and improved performance based on regional data needs.

## Add Auth Failures to Tracing

October 13, 2025

This release adds tracing for authentication failures, enabling better visibility and debugging of auth-related issues across systems.

## Total Traces on Stats Bar

October 12, 2025

<Frame>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/total-trace-stats.png" alt="Total Traces on Stats Bar" />
</Frame>

Your projects now display the total number of traces directly in the Stats Bar at the top for quicker visibility into overall activity.

## Support for GPT OSS Models on Bedrock

October 10, 2025

<Frame>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/gpt-oss-support.png" alt="Support for GPT OSS Models on Bedrock" />
</Frame>

We’ve added support for GPT open-source models available on Bedrock — try them out now in the Prompt Playground!

## Expanded LLM Support

October 5, 2025

Expanded LLM model support to include Claude models on Bedrock and Vertex, Titan Text Premiere, Amazon Nova Premiere, Gemini 2.5 Flash/Pro, and new GPT OSS and DeepSeek models —offering broader coverage across top providers.

<details>
  <summary>Full List of Newly Supported Models</summary>

  Vertex

  * Claude sonnet 4.5
  * Claude Opus 4.1
  * Claude Sonnet 4
  * Claude Opus 4
  * Gemini 2.5 flash
  * Gemini 2.5 pro
  * Gemini 2.5 flash lite
  * Gemini 2.5 flash lite preview

  Bedrock

  * Claude sonnet 4.5
  * Claude Opus 4.1
  * Claude Sonnet 4
  * Claude Opus 4
  * Nova Premiere
  * Deepseek v3
  * DeepSeek r1
  * gpt-oss-120b
  * gpt-oss-20b
</details>

## Dashboard Widget Time Setting

October 3, 2025

<Frame>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/dashboard-time-widget.png" alt="Dashboard Widget Time Setting" />
</Frame>

You can now define time settings per widget in dashboards! This enhancement adds flexibility by letting you set custom time ranges at the widget level — without losing the ability to apply a global dashboard time range. It’s a powerful way to dig deeper into data and run more tailored analyses.

## Autocomplete for Annotations on Datasets

October 1, 2025

<Frame>
  <img src="https://storage.googleapis.com/arize-phoenix-assets/assets/images/annotation-autocomplete.png" alt="Autocomplete for Annotations on Datasets" />
</Frame>

You can now autocomplete annotation variables when editing eval templates in the playground or directly from dataset slideovers. This makes building and managing evals faster and more intuitive.
