# New In Arize AX: Multi-Span Filters and Improved Playground Views - **Published:** 2026-01-06 - **Updated:** 2026-10-08 - **Authors:** Sanjana Yeddula - **Canonical:** --- ![](https://arize.com/wp-content/uploads/2026/01/December-Updates.jpg) 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 ![](https://storage.googleapis.com/arize-phoenix-assets/assets/images/multispan-filters.gif) ## 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. ![](https://storage.googleapis.com/arize-phoenix-assets/assets/images/playground-views-improved.gif) ## 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: - [Tracing An A2A Agent](https://arize.com/docs/ax/cookbooks/agents/tracing-a2a-agent) - [Tracing + Evaluating a Browser Use Agent with Llama 4](https://arize.com/docs/ax/cookbooks/agents/trace-evaluate-browser-use-agent-with-l-lama4) - [Red Teaming Agent](https://arize.com/docs/ax/cookbooks/agents/foundry-red-team) - [Evaluating and Improving AI Agents at Scale with Microsoft Foundry](https://arize.com/docs/ax/cookbooks/agents/evaluating-and-improving-ai-agents-at-scale-with-microsoft-foundry) ## 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. --- [More blog posts](https://arize.com/blog/sitemap.md)