Arize demos grading Claude agents with Phoenix

Arize's Laurie Voss demoed Phoenix evals for Claude agents: OpenTelemetry traces log each step, code checks verify deterministic results, and LLM judges grade meaning against rubrics. Testing a Haiku 4.5 to 5.5 upgrade, faithfulness improved over threefold but cost quadrupled; he stressed that "looks good to me" is not a test suite.

• Meta says Claude tool triggered No Kings Instagram suspension2026-10-19
• Developer builds free WhatsApp MCP on Cloudflare2026-10-19
• User says Qwen3.8 27b flashed router firmware after Claude refused2026-10-18
• Developer runs Fish Audio Drama 3 on a 16GB AMD card2026-10-18
• Anthropic seeks outside input on Claude's values; final say questioned2026-10-18