David B.

For those attending Microsoft Ignite this week: come say hi, check out our VIP dinner and book some time with us: https://arize.com/microsoft-ignite-2025

By popular demand, tomorrow's virtual evals workshop will focus on LLM-as-a-judge 101! RSVP: https://luma.com/tmipn699

Lots of new Arize AX features shipped in October! Full rundown: https://arize.com/blog/new-in-arize-ax-tags-data-fabric-automatic-threshold-ranges-for-monitors-and-more/

Tomorrow's community paper reading will focus on the latest paper from Meta: "ARE: scaling up agent environments and evaluations." We're thrilled to host one of the paper's authors — Grégoire Mialon, Research Scientist at Meta Superintelligence Labs — to walk us through the research and its implications. There will be a live Q&A session, so bring your questions! RSVP: https://luma.com/ksxzalzf

👋 PMs: this one's for you! Tomorrow, Aman K., Head of Product at Arize AI and creator of one of the most popular Maven courses focused on training up AI PMs, will share a concrete playbook for creating alignment between product and engineering and sharing ownership over evaluation - so your next AI product launch isn’t just good, it’s trusted. RSVP: https://luma.com/v8tbolt4

🌆 NYC: join us tomorrow at betaworks for an evening of technical talks, demos, and food/drinks. On the agenda:

RSVP required: https://luma.com/arizeoctnycbuildersmeetup

Hope to see some of you at NVIDIA GTC this week! Things we’re excited to show off and premiere at the event: 🟢 Nick L., taking advantage of Arize's early access as an NVIDIA Inception startup, will be benchmarking local LLMs with Arize Phoenix on the NVIDIA DGX Spark. 🟢 Richard Y. will show how to create a data flywheel for AI agents leveraging Arize AX and NVIDIA NeMo Customizer and NIM (read his blog on this!) See where to find us and book a meeting with our on-site team including Eric Senzig and Greg C. 📅 ✴️ https://arize.com/nvidia-gtc-dc

Tara Bogavelli of ServiceNow will cover her trending paper "AgentArch: A Comprehensive Benchmark to Evaluate Agent Architectures” at our next community paper reading next week with hosts Priyan J. and Parth S.. The paper provides a comprehensive enterprise-specific benchmark evaluating 18 distinct agentic configurations across state-of-the-art large language models. It examines four critical agentic system dimensions: orchestration strategy, agent prompt implementation (ReAct versus function calling), memory architecture, and thinking tool integration. RSVP 👉 https://luma.com/ujqpz2ey