arize-phoenix

arize-phoenix.bsky.social

09 October 2026 21:35

As agents gain capabilities due to skills, MCPs, and codemode, evaluating agents becomes increasingly more difficult because you need to test across multiple environments and harnesses. Arize Phoenix your benchmarking Harbor runs so pinpointing improvements and regressions becomes tractable.

arize-phoenix

arize-phoenix.bsky.social

09 October 2026 21:35

We put PXI, Claude Code, and Codex through the same tasks with Harbor + Phoenix Even when agents succeeded, their traces told different stories: tool calls, latency, and efficiency. Join Oct 8 at 11am PT / 2pm ET to learn how to compare agents and inspect ATIF traces. luma.com/arizeai-ben...

arize-phoenix

arize-phoenix.bsky.social

09 October 2026 21:35

We’re going live in 30 minutes for our webinar on Benchmarking AI Agents & Tool Use with Harbor and Arize Phoenix! Join here: luma.com/arizeai-ben...

arize-phoenix

arize-phoenix.bsky.social

09 October 2026 21:34

new baselining capabilities for experiments Now when you have a baseline set on your experiments or when you care comparing two experiments, you can see the deltas of your evals, tokens, latency and cost so you  can quickly identify regressions and improvements.

Arize AI

arize.bsky.social

19 September 2026 05:51

For all you Codex fans out there, we've just added support for Codex as the harness for your managed agents. Configure your managed agents with Codex as the harness, select your models, skills, attach repos, and define your task. Then let your managed agent rip!