@ArizePhoenix: Trace-level annotations everywhere - trace scores now appear as peer columns in the trace header (next to Status, Cost …
Summary
Arize Phoenix announces trace-level annotations now display as peer columns in the trace header and as a section in the project stats panel, with live updates during streaming.
View Cached Full Text
Cached at: 06/25/26, 12:08 AM
🔖 Trace-level annotations everywhere - trace scores now appear as peer columns in the trace header (next to Status, Cost & Latency) and as their own section in the project stats panel, with live updates while you stream. https://t.co/21qVLYQtMr
Similar Articles
@ArizePhoenix: • Faster trace analysis: use natural-language filters, one-click chart zoom, and dedicated annotation columns. • Expand…
Arize Phoenix announces updates including faster trace analysis with natural-language filters and an expanded REST API for managing retention assignments and model providers.
@ArizePhoenix: Customizable visualizations of your agent traces are here. Track cache hits, online eval degradations, tool call errors…
Arize Phoenix announces customizable visualizations for agent traces, enabling real-time tracking of cache hits, online eval degradations, and tool call errors in production.
@ArizePhoenix: Agent traces and trajectories are growing increasingly longer and more complex. We've seen some traces 1000s of spans d…
Arize Phoenix announces addition of trace search functionality to handle increasingly long and complex agent traces, allowing users to search across traces and view call stacks for spans.
@ArizePhoenix: Were buzzing with use-cases at @arizeai - so many optimizations to be made. Trace every judgement Jev makes with one li…
Arize Phoenix launches instrumentation support for tracing TypeSafe AI judgments, integrating with multiple developer tools and coding agents.
@ArizePhoenix: Phoenix 17.7.0 makes your token usage legible. New token detail charts break prompt + completion tokens into their part…
Phoenix 17.7.0 adds token detail charts that break down prompt and completion tokens into subcategories, with pan, zoom, and live-stream capabilities for better observability of AI model token usage.