Data and AI releases

670 this month · 176 companies

arize-phoenix: v16.3.0

UpdateNot yet verified

16.3.0 (2026-05-27) Features Add drag-to-zoom for project metric charts (4fe68f8) agents: add skills capability to PXI agent (5ef9729) expand PXI settings model selector (bbe5cb9)

AI agents

Read on github.com

Also shipped May 27, 2026Arize AI in May 2026 →

Deprecation Notice

The Gemini 2.5 Flash family of models is deprecating in October. Start testing newer models now to ensure a smooth migration. For more details on Gemini model deprecations, see Google's Gemini deprecations page . For the full list of supported models and pricing tiers, see the Voice Agent LLM Models documentation .

Deprecation
Source ↗

Frustration Analytics , Debugger on User Profile Timeline

What: The User Profile Timeline now surfaces frustration signals directly alongside behavioral events – error events with distinct styling, key properties inline, error-focused filtering, and quick links to Session Replay. This gives you a chronological view of exactly what a specific user experienced.

GA
Source ↗

GitHub CLI 2.93.0

Security A security vulnerability has been identified, and fixed, that would incorrectly include authorization header in API requests to TUF repository mirrors via gh attestation , gh release verify , and gh release verify-asset commands. Users are advised to update gh to version v2.93.0 as soon as possible.

Update
Source ↗

More from phoenixEvery phoenix release →

arize-phoenix: v16.2.0

16.2.0 (2026-05-26) Features agents: Make assistant accessible over modal overlays (7b6af22) Bug Fixes confine token counts to LLM spans at ingestion (5d4f34f)

Update
Source ↗

arize-phoenix: v16.1.0

16.1.0 (2026-05-26) Features agents: adds skill for creating a new eval dataset, a new dat... (1989790) agents: Resize detached PXI assistant panel (1a387a3) dashboards route (b43ddb4) pxi: add assistant hotkey tooltip (6ebb79f) pxi: add floating assistant panel (d3a34c0) pxi: smoother shimmer + glyph in chat loading (6295e18) ui: use trace icon for project...

Update
Source ↗

arize-phoenix: v16.5.0

16.5.0 (2026-06-01) Features add playground save prompt tool (1641957) agent: rewind, fork, and copy controls for chat messages (f5df5ec) agents: add annotate-spans skill for the PXI agent (4b4f7a7) agents: add read_prompt_tools and write_prompt_tools to PXI (66a412b) agents: add summary argument to PXI bash tool for UI preview (16039bd) sandbox: seed...

Update
Source ↗

arize-phoenix: v16.4.0

16.4.0 (2026-06-01) Features Add no-data chart overlays (792aa92) agent: collapse agent context pills into a deck (f1e0e2e) agent: make PXI quick actions dynamic per page context (e60ba32) agents: add Claude Opus 4.8 support to PXI (f13fd0b) agents: add span annotation tool (4c8262c) agents: Floating chat drag, resize, style improvements (79d8afe) agent...

Update
Source ↗

arize-phoenix: v17.1.0

17.1.0 (2026-06-02) Features playground: add PXI load_dataset tool (96678ef) pxi: LLM-evaluator authoring for the PXI agent (1ead013) skill loading display (73185b4) warning colors, search off icon (7ec6ace) Bug Fixes server: don't let docs MCP init failure abort server startup (c31598d)

Update
Source ↗

arize-phoenix: v17.0.0

17.0.0 (2026-06-02) MIGRATION.md ⚠ BREAKING CHANGES - server: add system settings with admin-managed assistant enablement and trace recording policy Features - server: add system settings with admin-managed assistant enablement and trace recording policy (7f41cb4)

Update
Source ↗

arize-phoenix: v16.6.0

16.6.0 (2026-06-02) Features add PXI playground model switching tool (ad2013a) agents: add web search globe toggle to agent chat (1fed5aa) pxi: code-evaluator authoring (cef8f13) Documentation add Go LLM provider integration docs (352cb3c)

Update
Source ↗

arize-phoenix: v16.0.0

16.0.0 (2026-05-21) MIGRATION.md ⚠ BREAKING CHANGES - Sandboxing and Code Evaluators Features Phoenix now lets you compose evaluation strategies in code. Most eval tooling hands you a fixed menu of judge templates. Real evaluation is rarely that tidy. Code Evaluators enable you to build evaluation criteria the way you want.

Update
Source ↗