2025-11-20

Structured Outputs Support for Playground

This release adds full structured output support to the playground, giving users precise control over the fields an LLM must return. Models that implement the OpenAI API schema (including OpenAI, Azure, and compatible custom endpoints) now support structured outputs end-to-end. When saving prompts, the structured output JSON is stored alongside other LLM parameters for seamless reuse. Tooltips have also been added to clearly indicate when a model or provider does not support structured outputs.

2025-11-10

Session Annotations

This release introduces Session Annotations, making it easier than ever to capture human insights without disrupting your workflow. You can now add notes directly from the Session Page—no context switching required.Annotations are supported at two levels:

Input/Output Level: Attach insights to specific output messages, automatically linked to the root span of the trace.
Span Level: Dive deeper into a trace and annotate individual spans for precise, context-rich feedback.

Together, these capabilities make it simple to highlight issues, call out successes, and integrate human feedback seamlessly into your debugging and evaluation process.

2025-11-05

Integrations Revamp

This release delivers major improvements to how integrations are managed, scoped, and configured. Integrations can now be targeted to specific orgs and spaces, and the UI has been refreshed to clearly separate AI Providers from Monitoring Integrations.A new creation flow supports both simple API-based setups and flexible custom endpoints, including multi-model configurations with defaults or custom names. Users can also add multiple keys for the same provider, enabling more granular control and easier management at scale.

2025-11-03

OpenInference TypeScript 2.0

See the OpenInference TypeScript Core package for more details.

Added easy manual instrumentation with the same decorators, wrappers, and attribute helpers found in the Python openinference-instrumentation package.
Introduced function tracing utilities that automatically create spans for sync/async function execution, including specialized wrappers for chains, agents, and tools.
Added decorator-based method tracing, enabling automatic span creation on class methods via the @observe decorator.
Expanded attribute helper utilities for standardized OpenTelemetry metadata creation, including helpers for inputs/outputs, LLM operations, embeddings, retrievers, and tool definitions.
Overall, tracing workflows, agent behavior, and external tool calls is now significantly simpler and more consistent across languages.

2025-10-30

API-Driven Monitors

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.

2025-10-30

Automatic Threshold Ranges for Monitors

You can now set upper and lower bounds using our new Auto Threshold options!Arize AX 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.

2025-10-29

Data Fabric

We’re excited to introduce Data Fabric, a new capability that automatically synchronizes production trace data, evaluations, and annotations from Arize AX into your cloud data warehouse every 60 minutes in Iceberg format—giving you an always-current, query-ready source of truth.

2025-10-28

New Timeline Tab for Traces

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.

2025-10-24

Sort Datasets and Experiment Listing Table

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

2025-10-15

Support for Tool Call IDs in OpenInference Messages

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.

2025-10-14

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.

2025-10-13

Add Auth Failures to Tracing

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

2025-10-12

Total Traces on Stats Bar

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

2025-10-10

Support for GPT OSS Models on Bedrock

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

2025-10-05

Expanded LLM Support

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.

2025-10-03

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.

2025-10-01

Autocomplete for Annotations on Datasets

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.

2025-09-28

Experiment Annotations on Experiment Compare Page

Annotations are now visible directly on the Experiment Compare page, making it easier to review context and insights alongside your experiment results. This streamlines analysis by keeping annotations and metrics in one place.

2025-09-27

Autosave Annotations

Annotations on the Experiment Compare page now autosave immediately after selection, removing the need to manually save them. Experiment annotations are also displayed on the experiment compare page.

2025-09-26

Improved Sessions View

Text in Session bubbles now wraps automatically, ensuring all content stays visible for a smooth sessions experience.

2025-09-24

Dashboard Rework Enhancements

Dashboards now support per-widget time range selection and improved legend display options, giving users more granular control and clearer data visualization. These updates make it easier to tailor each dashboard view to your specific analysis needs.

2025-09-22

Large Dataset Runs in Playground

The Playground now supports running on an unlimited number of rows, with a new “Load 100 more” button to make adding records easier. This is the first iteration of scalable runs, and we’ll continue improving the usability in upcoming updates.

2025-09-19

Session and Trace Evals

Session- and trace-level evaluations are available across all Arize tiers. This unlocks the ability to evaluate at different levels (span, trace, and session), which is crucial for building and monitoring agents.

2025-09-17

Alyx: Synthetic Data Generation Skill

You can now generate synthetic datasets directly in Playground using Alyx. This makes it easier to quickly create sample data for testing and experimentation without needing external tools.

2025-09-15

Position Dashboard Widgets Freely

Users can now position widgets freely, including adding gaps for layout flexibility.

2025-09-11

Annotations Config: Optimization Direction

Added support for defining optimization direction on categorical and continuous configs. The optimization_direction field now lives within their respective config columns, improving logical grouping.

2025-09-10

Improved Annotator Selection for New Labeling Queues

The annotator selection flow has been refined: users are grouped into Annotators and All Other Users (with group-level select all), and the interface now clearly highlights “You.”

2025-09-09

Search in Settings

All settings tables now include search bars, making it easier to quickly find what you need.

2025-09-08

Dashboard Improvements

Dashboards have been reworked with a richer experience: clickable legends and new widget creation forms for line charts, bar charts, experiments, monitors, and statistics.

2025-08-29

Delete Annotation Queues

You can now delete annotation queues directly from the queues listing using the “more” button, or remove multiple queues at once with checkboxes in the queues table.

2025-08-26

Playground View Defaults

The playground now loads the most recent view by default, so you can pick up right where you left off.

2025-08-20

Trace Total Cost Views

The trace tab (table view) now displays the total cost at the root span, making it easier to understand overall usage at a glance.

2025-08-19

Experiment Traces Improvements

The new traces page slide-over enhances the experiment tracing experience, with hover buttons now always visible, experiment traces added to the overflow menu, and search functionality added to the Experiments List Page.

2025-08-18

Dataset Management Upgrades

The Datasets interface has been improved with CSV upload fixes, search capabilities on the Datasets List Page, and REST API support for dataset deletion.

2025-08-16

Color maps and diffing functionality have been improved, and the trace metadata now uses experiment IDs for better consistency. The experiment compare headers also feature a pinned experiment button for easier navigation.

2025-08-15

Dataset Filtering & REST API Updates

Datasets now support improved filtering capabilities, better column organization following semantic conventions, and expanded REST API coverage for listing datasets and examples.Text areas on dataset example pages can now expand to full column width, and dataset filter history is now preserved.

2025-08-14

Dedicated Agent Graph Tab

The tracing interface now includes a dedicated Agent Graph tab, making it clearer to visualize and explore agent interactions within traces.

2025-08-13

Alyx Copilot API Advancements

Copilot API now supports structured output, improved frontend message parsing, and streamlined post-processing workflows, delivering a major upgrade to the AI assistant architecture.

2025-08-12

Playground Performance Updates

Playground data loading has been improved to boost reliability and performance. Fixed missing metrics displays for AWS Bedrock models, ensuring smoother and more consistent evaluation workflows.

2025-08-11

Project UX Enhancements

The Projects page now features improved navigation and usability, with the addition of Tasks Provider to simplify task and evaluation management.

2025-08-07

Support for GPT-5 in Prompt Playground

Prompt Playground now supports GPT-5, giving users access to the latest OpenAI model for experimentation and evaluation.

2025-08-06

Trace Interactivity Improvements

Hover states have been added for trace costs, and spans in traces are now clickable—making it easier to explore cost details and navigate through trace data.

2025-08-04

Revamped Eval and Tasks Experience

The Evals experience has been upgraded with a redesigned Tasks page and updated slideovers that for a cleaner workflow. A save button has been added to Evals slideovers, counters in Datasets now stay up to date, and evaluators automatically refresh from datasets.

2025-08-05

Expanded Annotation Configuration Capabilities

Annotations now support up to five labels per configuration, giving teams more flexibility to capture nuanced judgments and tailor evaluation workflows to their needs.This release also adds improved validations, clearer table views, and multiple UI and labeling queue enhancements for a smoother annotation workflow.

2025-08-04

Image Support for Datasets and Labeling Queues

Datasets now support images in both datasets and labeling queues, with updated column groupings, clearer example ID displays, and reference tokens in headers. This release also introduces download tooltips for datasets and experiments, making it easier to export data directly from the UI.

2025-08-02

Experiment Comparison & Data Visualization Improvements

The Experiments page has been redesigned with improved UX and richer charting, including new select components and diffing support on the compare page for clearer side-by-side analysis.Average aggregate metrics are now shown in experiment headers. Usability fixes such as expandable/collapsible tables, editable experiment names, and updated column headers make workflows smoother.

2025-07-18

Preview Examples in Evals UI

Now supports previewing examples while editing eval templates, making it easier to refine and validate your evals.

2025-07-18

OpenInference Java

OpenInference Java is now available, providing a comprehensive solution for tracing AI applications using OpenTelemetry. Fully compatible with any OpenTelemetry-compatible collector or backend like Arize.Included in this release:

openinference-semantic-conventions: Java constants for capturing model calls, embeddings, and tool usage.
openinference-instrumentation: Core utilities for manual OpenInference instrumentation.
openinference-instrumentation-langchain4j: Auto-instrumentation for LangChain4j applications.

All libraries are published and ready to add to your build to initialize tracing and capture rich AI traces.Learn more:

2025-07-16

Alyx Build Eval Skill

You can now build and run evals directly with Alyx. The new UX enables full interaction with Alyx to create multiple evals in the same flow, run evals on experiments and datasets, and list available evals for easy tracking.When building an eval in the Evals & Tasks tab, find the Alyx button to get started with this feature. More enhancements coming soon!

2025-07-12

Prompt Hub Release Tags

You can now tag prompts in Prompt Hub as Production, Staging, or with custom labels to keep your workflow organized. This makes it easy to track which prompts are live, in testing, or under development.

2025-07-12

Prompt Learning

With Prompt Optimization Tasks, you can now optimize prompts in a few clicks using human or automated feedback loops, versioned releases, and CI-friendly workflows—no more trial-and-error.Key Features:

Auto-generate the best prompt from your labeled dataset
Promote the best prompt to production in Prompt Hub
Evaluate auto-generated prompts side-by-side with originals on the Experiments page

Check out the documentation to learn more.

2025-07-11

Arize Tracing Assistant

The Arize Tracing Assistant is now live, bringing docs, examples, and tracing help directly into your IDE or LLM—no guesswork, no tab hopping:

Instantly look up instrumentation guides without leaving your editor
Drop in working tracing examples to adapt immediately
Ask tracing questions in plain language and get answers as you debug

Fully supported on Cursor and Claude Desktop. Instrument faster, debug confidently, and bring Arize AX tracing into your workflow with zero friction.Available now on PyPI: https://pypi.org/project/arize-tracing-assistant/Check our documentation to learn more.

2025-07-10

Saved Filters for Traces

You can now save up to 7 filters on the Traces page to quickly revisit your most-used views. Just create a filter and hit “Save” to pin it for easy access.

2025-07-02

Customizable Hotkey for Alyx

Alyx now supports a default hotkey for quickly adding context and opening chat:

macOS: ⌘ + L
Windows: Ctrl + L

You can also customize this hotkey anytime in the settings modal to match your workflow.

2025-07-01

Cost Tracking

You can now monitor model spend directly in Arize with native cost tracking. Supporting 60+ models and providers out of the box, this flexible feature adapts to various cost structures and team needs, making it easy to track and manage your AI spend in-platform.

2025-06-25

Arize Database (ADB)

We’re excited to introduce Arize Database (ADB), the powerful engine behind all Arize AX instances. Built for massive scale and speed, ADB processes billions of traces and petabytes of data with high efficiency.Its robust architecture supports real-time ingestion, bulk updates, and fast querying, powering even the heaviest AI workloads reliably. ADB has long been the unsung hero of our platform, and we’re proud to bring it to light.

Introducing ADB: Arize’s Proprietary OLAP Database

Arize AI

2025-06-25

Playground Views

The new Prompt Playground lets you save views including prompts, dataset selections, comparison views, messages, and model selections. You can iterate and test variations seamlessly in one environment and share optimal views with your team to accelerate prompt development and evaluation.

2025-06-25

Prompt Learning

We’re excited to launch Prompt Learning, a new workflow in Arize to accelerate prompt iteration and evaluation. With Prompt Learning, you can:

Run prompt optimization experiments directly in Arize
Incorporate text-based judgments from humans and LLMs
Tune and compare prompt variants to systematically improve agent behavior

Agent Trajectory Evaluations

With Agent Trajectory Evaluation you can assesses the sequence of tool calls and reasoning steps your agent takes to solve a task. Key benefits:

Path Quality: See if your agent is following expected, efficient problem-solving paths.
Tool Usage Insights: Detect redundant, inefficient, or incorrect tool call patterns.
Debugging Visibility: Understand internal decision-making to resolve unexpected behaviors, even when outcomes appear correct.

Session-level Evaluations

You can now evaluate your agents across entire sessions with new session-level evaluations, enabling deeper insight beyond trace-level metrics. Assess:

Coherence: Does the agent maintain logical consistency throughout the session?
Context Retention: Is it effectively remembering and building on prior exchanges?
Goal Achievement: Does the conversation accomplish the user’s intended outcome?
Conversational Progression: Is the agent navigating multi-step tasks in a natural, helpful way?

These evaluations help ensure your agents are effective not just at each step, but across the full journey. More information on Session-level Evaluations.

2025-06-25

Agent and Multi-Agent Visualization

Easily inspect and debug multi-agent workflows with the new **Agent Visibility **feature. Alongside Traces and Spans, the new Agents tab auto-generates an interactive flowchart showing how agents, tools, and components interact step-by-step. With Agent Visibility, you can:

Visualize agent workflows end-to-end
Debug bottlenecks and errors with clarity
Link agents to traces and spans for deeper insights
Accelerate orchestration iteration and refinement

It works automatically across frameworks like Agno, Autogen, CrewAI, LangGraph, OpenAI Agents, and SmolAgents. More on agent tracing.

2025-06-25

Alyx MCP Assistant

All Alyx skills are accessible via MCP, allowing seamless integration into your existing workflows. You can leverage the full suite of Alyx debugging and analysis tools wherever you build, without needing to switch contexts.This means you can debug traces directly from your IDE while building in environments like Cursor, or connect through Claude Code to identify improvement areas. Refer to the video below for setting up Alyx via MCP in Cursor.

2025-06-25

Arize Copilot v3: Alyx & Trace Troubleshooting

We are excited to introduce Alyx, our major upgrade to our Copilot assistant. You can now drop context anywhere across the app and open copilot with the magic of ctrl+L to instantly pull context for smarter, faster help.We’re also introducing Trace Troubleshooting — a new Copilot skill that lets you navigate the entire trace to pinpoint issues. Built with O3 under the hood, you can now:

@ specific spans
Use existing span skills for span questions or evals
Let Copilot traverse and diagnose like a pro
Ability to customize the hot key if you don’t want to use Ctrl + L

2025-06-20

New Homepage & Onboarding Experience

We’ve just rolled out a revamped onboarding flow to guide first-time users smoothly into either Tracing or Experiments.

2025-05-20

Realtime Trace Ingestion for All Arize AX Instances

Realtime trace ingestion is now supported across all Arize AX tiers, including the free tier.Previously, this feature was only available for enterprise AX users and within our open-source platform, Phoenix. It is now fully rolled out to all users of Arize AX.No configuration changes are required to begin using realtime trace ingestion.

2025-05-11

More OpenAI models in prompt playground and tasks

We’ve added support for more OpenAI models in prompt playground and evaluation tasks. Experiment across models and frameworks quickly.

2025-05-09

Sleeker display of inputs and outputs on a span

We’ve improved the design of the span page to showcase the functions, inputs, and outputs, to help you debug your traces faster!

2025-05-07

Attribute search on traces

Now you can filter your span attributes right on the page, no more CMD+F !

2025-05-05

Column selection in prompt playground

You can now view all of your prompt variables and dataset values directly in playground!

2025-05-02

Latency and token counts in prompt playground

We’ve added latency and token counts to prompt playground runs! Currently supported for OpenAI, with more providers to come!

2025-04-28

Major design refresh in Arize AX

We’ve refreshed Arize AX with polished fonts, spacing, color, and iconography throughout the whole platform.

2025-04-26

Custom code evaluators

You can now run your own custom python code evaluators in Arize against your data in a secure environment. Use background tasks to run any custom code, such as URL validations, or keyword match. Learn more

2025-04-25

Security audit logs for enterprise customers

Improve your compliance and policy adherence. You can now use audit logs to monitor data access in Arize. Note: This feature is completely opt-in and this tracking is not enabled unless a customer explicitly asks for it. Learn more

2025-04-24

Larger dataset runs in prompt playground

We’ve increased the row limit for datasets in the playground, so you can run prompts in parallel on up to 100 examples.

2025-04-24

Evaluations on experiments

You can now create and run evals on your experiments from the UI. Compare performance across different prompt templates, models, or configurations without code. Learn more →

2025-04-24

Cancel running background tasks

When running evaluations using background tasks, you can now cancel them mid-flight while observing task logs. Learn more →

2025-04-21

Improved UI for functions in prompt playground

We’ve made it easier to view, test, and validate your tool calls in prompt playground. Learn more →

2025-04-15

Compare prompts side by side

Compare the outputs of a new prompt and the original prompt side-by-side. Tweak model parameters and compare results across your datasets. Learn more →

2025-04-14

Image segmentation support for CV models

We now support logging image segmentation to Arize. Log your segmentation coordinates and compare your predictions vs. your actuals.Learn more →

2025-04-11

New time selector on your traces

We’ve made it way easier to drill into specific time ranges, with quick presets like “last 15 minutes” and custom shorthand for specific dates and times, such as 10d ,4/1 - 4/6, 4/1 3:00am . Learn more →

2025-04-07

Prompt hub python SDK

Access and manage your prompts in code with support for OpenAI and VertexAI. Learn more

pip install "arize[PromptHub]"

2025-04-04

View task run history and errors

Get full visbility into your evaluation task runs, including when it ran, what triggered it, and if there were errors. Learn more →

2025-04-02

Run evals and tasks over a date range

Easily run your online evaluation tasks over historical data.

2025-03-24

Test online evaluation tasks in playground

Quickly debug and refine your prompts used by your online evaluators by loading them prefilled into prompt playground. Learn more →

2025-03-01

Select metadata on the sessions page

Dynamically select the fields you want to see in your sessions view.

2025-02-27

Labeling queues

Use Arize to annotate your data with 3rd parties. Learn more →

2025-02-20

Expand and collapse your traces

You can now collapse rows to see more data at a glance or expand them to view more text.

2025-02-14

Schedule your monitors

Schedule for monitors to run hourly, daily, weekly, or monthly.

2025-02-14

Improved traces export

Specify which columns of data you’d like to export when exporting data via the ArizeExportClient by specifying columns .

primary_df = client.export_model_to_df(
    columns=['context.span_id', 'attributes.llm.input'] # <---- HERE
    space_id='',
    model_id='',
    environment=Environments.TRACING,
    start_time=datetime(2025, 3, 25),
    end_time=datetime(2025, 4, 25),
)

2025-02-14

Create dataset from CSVs

You can now create datasets through many methods, from traces, code, manually in the UI, or CSV upload. Read more

2025-02-14

OTEL tracing Via HTTP

Support for HTTP when sending traces to Arize! See GitHub for more info.

tracer_provider = register(
    endpoint="https://otlp.arize.com/v1/traces",     # NEW
    transport=Transport.HTTP,                        # NEW
    space_id=SPACE_ID,
    api_key=API_KEY
    project_name="test-project-http",
)

2025-01-21

Voice application tracing and evaluation

Audio tracing: Capture, process, and send audio data to Arize and observe your application behavior.Evaluation: Assess how well your models identify emotional tones like frustration, joy, or neutrality.

Voice App Tracing

2025-01-21

Dashboard colors

We’ve added new ways to plot your charts, with custom colors and better UX!

2024-12-19

Prompt hub

Manage, iterate, and deploy your prompts in one place. Version control your templates and use them across playground, tasks, and APIs. Read more

2024-12-19

Managed code evaluators

Use our pre-built, off-the-shelf evaluators to evaluate spans without requiring requests to an LLM-as-a-Judge. These include Regex matching, JSON validation, Contains keyword, and more!

2024-12-19

Create experiments from playground

Quickly experiment with your prompts across your datasets. All you have to do is click “Save as experiment” Read more

2024-12-19

Monitor alert status

See exactly how and when your monitors are triggered

2024-12-19

LangChain Instrumentation

Support for sessions via LangChain native thread tracking in TypeScript is now available. Easily track multi-turn conversations / threads using LangChain.js.

2024-12-05

Analyze your spans with Copilot

Extract key insights quickly from your spans instead of trying to decipher meaning in hundreds of spans. Ask questions and run evals right in the trace view.

Span Chat Evaluation

2024-12-05

Generate dashboards with Copilot

Building dashboard plots just got way easier. Create time series plots and even translate code into ready to go visualizations.

Dashboard generator

The Custom Metric skill now supports a conversational flow, making it easier for users to iterate and refine metrics dynamically

2024-12-05

View your experiment traces

Experiment traces for a dataset are now consolidated accessed under “Experiment Projects”.

Experiment Projects

2024-12-05

Multi-class calibration chart

For your multi-class ML models, you can see how your model is calibrated in one visualization

Calibration Chart

2024-12-05

Log experiments in Python SDK

You can now log experiment data manually using a dataframe, instead of running an experiment. This is useful if you already have the data you need, and re-running the query would be expensive. SDK Reference

arize_client.log_experiment(
    space_id=SPACE_ID,
    experiment_name="my_experiment",
    experiment_df=experiment_run_df,
    task_columns=task_columns,
    evaluator_columns={"correctness": evaluator_columns},
    dataset_name=dataset_name,
)

2024-11-07

Create custom metrics with Copilot

Users can generate their desired metric by having copilot translate natural language descriptions or existing code (e.g., SQL, Python) into AQL. Learn more →

Copilot Custom Metric Skill

2024-11-07

Summarize embeddings with Copilot

Copilot now works for embeddings! Users can select embedding data point and Copilot will analyze for patterns and insights. Learn more →

Copilot Embedding Summarization Skill

2024-11-07

Local explainability support for ML models

Local Explainability is now live, providing both a table view and waterfall style plot for detailed, per-feature SHAP values on individual predictions. Learn more →

Local Explainability Support

2024-11-07

See experiment results over time

Visualize specific evaluations over time in dashboards. Learn more →

Experiment Over Time Widget

2024-11-07

Function calling replay in prompt playground

Now users can follow the full function calling tutorial from OpenAI and iterate on different functions in different messages from within the Prompt Playground.

Full Function Calling Replay

2024-11-07

Vercel AI auto-instrumentation

User can now ingest traces created by the Vercel AI SDK into Arize. Learn more →

2024-11-07

Track sessions and context attributes in instrumentation

You can add metadata and context that will be picked up by all of our auto instrumentations and added to spans. Learn more →

2024-10-24

Easily test your online tasks and evals

Users now have the option to to test a task, such as online eval, by running it once on existing data, or apply evaluation labels to older traces. Learn more →

2024-10-24

Experiment filters

Users can now filter experiments based on dataset attributes or experiment results, making it easy to identify areas for improvement and track their experiment progress with more precision. Learn more →

Filtering experiments by experiment name

2024-10-03

Embedding traces

With Embeddings Tracing, you can effortlessly select embedding spans and dive straight into the UMAP visualizer, simplifying troubleshooting for your genAI applications. Learn more→

Embedding traces in action

2024-10-03

Experiments Details Visualization

Users can now view a detailed breakdown of labels for their experiments on the Experiments Details page.

Experiments details visualization

2024-10-03

Support for o1-mini and o1-preview in playground

****We’ve added full support for all available OpenAI models in the playground including the o1-mini and o1-preview.

2024-10-03

Improved auto-complete in playground

We’ve added better input variable behavior, autocompletion enhancements, support for mustache/f-string input variables, and more.

2024-10-03

Filter history

We now store the last three filters used by a user! Users can easily access their filter history in the query filters dropdown, making it simpler to reuse filters for future queries.

Filters history

2024-10-03

Tracing quick filters

Apply filters directly from the table by hovering over the text to reveal the filter icon.

Quick filters

2024-10-03

New arize-otel package

We made it way simpler to add automatic tracing to your applications! It’s now just a few lines of code to use OpenTelemetry to trace your LLM application. Check out our new quickstart guide which uses our arize-otel package.

2024-10-03

Easily add spans to datasets

Easily add spans to a dataset from the Traces page using the “Add to Dataset” button.

"Add to Dataset" & "Setup Task" buttons"

See more

History

​Structured Outputs Support for Playground

​Session Annotations

​Integrations Revamp

​OpenInference TypeScript 2.0

​API-Driven Monitors

​Automatic Threshold Ranges for Monitors

​Data Fabric

​New Timeline Tab for Traces

​Tags

​Sort Datasets and Experiment Listing Table

​Support for Tool Call IDs in OpenInference Messages

​Add Data Region to Login Page

​Add Auth Failures to Tracing

​Total Traces on Stats Bar

​Support for GPT OSS Models on Bedrock

​Expanded LLM Support

​Dashboard Widget Time Setting

​Autocomplete for Annotations on Datasets

​Experiment Annotations on Experiment Compare Page

​Autosave Annotations

​Improved Sessions View

​Dashboard Rework Enhancements

​Large Dataset Runs in Playground

​Session and Trace Evals

​Alyx: Synthetic Data Generation Skill

​Position Dashboard Widgets Freely

​Annotations Config: Optimization Direction

​Improved Annotator Selection for New Labeling Queues

​Search in Settings

​Dashboard Improvements

​Delete Annotation Queues

​Playground View Defaults

​Trace Total Cost Views

​Experiment Traces Improvements

​Dataset Management Upgrades

​Experiments Refinements

​Dataset Filtering & REST API Updates

​Dedicated Agent Graph Tab

​Alyx Copilot API Advancements

​Playground Performance Updates

​Project UX Enhancements

​Support for GPT-5 in Prompt Playground

​Trace Interactivity Improvements

​Revamped Eval and Tasks Experience

​Expanded Annotation Configuration Capabilities

​Image Support for Datasets and Labeling Queues

​Experiment Comparison & Data Visualization Improvements

​Preview Examples in Evals UI

​OpenInference Java

​Alyx Build Eval Skill

​Prompt Hub Release Tags

​Prompt Learning

​Arize Tracing Assistant

​Saved Filters for Traces

​Customizable Hotkey for Alyx

​Cost Tracking

​Arize Database (ADB)

Introducing ADB: Arize’s Proprietary OLAP Database

​Playground Views

​Prompt Learning

​Agent Trajectory Evaluations

​Session-level Evaluations

​Agent and Multi-Agent Visualization

​Alyx MCP Assistant

​Arize Copilot v3: Alyx & Trace Troubleshooting

​New Homepage & Onboarding Experience

​Realtime Trace Ingestion for All Arize AX Instances

​More OpenAI models in prompt playground and tasks

​Sleeker display of inputs and outputs on a span

​Attribute search on traces

​Column selection in prompt playground

​Latency and token counts in prompt playground

​Major design refresh in Arize AX

​Custom code evaluators

​Security audit logs for enterprise customers

​Larger dataset runs in prompt playground

​Evaluations on experiments

​Cancel running background tasks

​Improved UI for functions in prompt playground

Structured Outputs Support for Playground

Session Annotations

Integrations Revamp

OpenInference TypeScript 2.0

API-Driven Monitors

Automatic Threshold Ranges for Monitors

Data Fabric

New Timeline Tab for Traces

Tags

Sort Datasets and Experiment Listing Table

Support for Tool Call IDs in OpenInference Messages

Add Data Region to Login Page

Add Auth Failures to Tracing

Total Traces on Stats Bar

Support for GPT OSS Models on Bedrock

Expanded LLM Support

Dashboard Widget Time Setting

Autocomplete for Annotations on Datasets

Experiment Annotations on Experiment Compare Page

Autosave Annotations

Improved Sessions View

Dashboard Rework Enhancements

Large Dataset Runs in Playground

Session and Trace Evals

Alyx: Synthetic Data Generation Skill

Position Dashboard Widgets Freely

Annotations Config: Optimization Direction

Improved Annotator Selection for New Labeling Queues

Search in Settings

Dashboard Improvements

Delete Annotation Queues

Playground View Defaults

Trace Total Cost Views

Experiment Traces Improvements

Dataset Management Upgrades

Experiments Refinements

Dataset Filtering & REST API Updates

Dedicated Agent Graph Tab

Alyx Copilot API Advancements

Playground Performance Updates

Project UX Enhancements

Support for GPT-5 in Prompt Playground

Trace Interactivity Improvements

Revamped Eval and Tasks Experience

Expanded Annotation Configuration Capabilities

Image Support for Datasets and Labeling Queues

Experiment Comparison & Data Visualization Improvements

Preview Examples in Evals UI

OpenInference Java

Alyx Build Eval Skill

Prompt Hub Release Tags

Prompt Learning

Arize Tracing Assistant

Saved Filters for Traces

Customizable Hotkey for Alyx

Cost Tracking

Arize Database (ADB)

Playground Views

Prompt Learning

Agent Trajectory Evaluations

Session-level Evaluations

Agent and Multi-Agent Visualization

Alyx MCP Assistant

Arize Copilot v3: Alyx & Trace Troubleshooting

New Homepage & Onboarding Experience

Realtime Trace Ingestion for All Arize AX Instances

More OpenAI models in prompt playground and tasks

Sleeker display of inputs and outputs on a span

Attribute search on traces

Column selection in prompt playground

Latency and token counts in prompt playground

Major design refresh in Arize AX

Custom code evaluators

Security audit logs for enterprise customers

Larger dataset runs in prompt playground

Evaluations on experiments

Cancel running background tasks

Improved UI for functions in prompt playground

Compare prompts side by side

Image segmentation support for CV models