New In Arize AX: Multi-Span Filters and Improved Playground Views

Arize AX released a raft of new updates to close out December of 2025. From improved playground views to multi-span filters, here’s are some highlights. Multi-Span Filters Filter traces using multiple span conditions with: AND, OR, NOT operators for combining conditions Indirectly Calls (->) and Directly Calls (=>) relationship filters Up to 5 filters to...

Arize AX released a raft of new updates to close out December of 2025. From improved playground views to multi-span filters, here’s are some highlights.

Multi-Span Filters

Filter traces using multiple span conditions with:

  • AND, OR, NOT operators for combining conditions
  • Indirectly Calls (->) and Directly Calls (=>) relationship filters
  • Up to 5 filters to find complex patterns like “spans where A calls B, but not C” or “traces containing both X and Y”
  • Parentheses to build complex queries and pinpoint the traces that matter

Improved Playground Views

The Prompt Playground page is now Playgrounds, where you can use your Playground Views! This change allows you to easily navigate to a configuration of the prompt playground you’ve saved. A playground view saves a complete snapshot of your current prompt playground session, allowing you to preserve your work, share configurations with teammates, or return to previous experiments. Here’s what’s saved in a view:

  • LLM Config (provider, model selection, model params, custom endpoint settings)
  • Prompt Setup (messages, roles, message content, tool and function calls)
  • Generated Results (when setup with datasets)
  • Connected Datasource (dataset or span)

If you want to start a playground from scratch, you can create a view using the + Playground button at the top of the Playgrounds page.

Realtime Ingestion for all new Arize AX Spaces

Any spaces created on or after 12/5/25 will use realtime ingestion by default! This eliminates the delay between sending traces and seeing them in the platform, giving you instant visibility into your production workloads.

New Cookbooks Added

New Arize AX cookbooks include:

New Model Support

Releases expand LLM model support to include GPT-5.2 models as well as Opus and Haiku 4.5 models in the playground and online tasks.

Get the latest on AI & Observability

Sign up for our newsletter, The Evaluator—and stay in the know with updates and new resources:

Don’t ship vibes.

Arize gives AI teams observability and evals to understand and improve agent performance.