MLflow 3.6.0 now supports @OpenTelemetry end-to-end! 🚀 Combine traces from Python, Java, Go, Rust & frameworks like FastAPI, Django, OpenAI, LangChain, DSPy—all unified in MLflow for full observability. Get vendor neutrality, broad ecosystem compatibility, and unified

🔗 Visit MLflow OpenTelemetry documentation:

🌟 Star the MLflow GitHub repo:

Samraj wrote an excellent blog on the Claude Agent SDK and MLflow! Give it a read on the MLflow blog. 🔗 Dive in:

Have questions? Ask away! 👇 We'll answer during the Q&A portion of today's meetup.

MLflow Community Meetup | November 12, 2025

Join us for the next 𝗠𝗟𝗳𝗹𝗼𝘄 𝗢𝗳𝗳𝗶𝗰𝗲 𝗛𝗼𝘂𝗿𝘀 on Wednesday, November 19 at 3PM SGT, for an open Q&A session with MLflow maintainers and contributors! 🎊 Whether you're managing models in production, experimenting with LLM workflows, or exploring new features in

MLflow’s optimize_prompts() API automatically refines prompts using your evaluation metrics and training data, boosting performance and consistency while reducing manual tuning. 🚀 This experimental feature streamlines prompt enhancement across agent frameworks with optimization

MLflow 3.6.0 just landed. Thanks to MLflow maintainers and the community. 🔗 Check it out: https://t.co/SI4fWECYkQ Big rocks include: 👉 Full OpenTelemetry Support in MLflow Tracking Server 👉 Session-level View in Trace UI 👉 New Supported Frameworks in TypeScript Tracing SDK

Full room, great energy, and tons of practical insights at yesterday’s Terminal-Bench 2.0 meetup in SF! 🙌 Danny Chiao (Engineering Lead, @Databricks) provided a hands‑on tour of building high‑quality agents faster with MLflow, and Alex Shaw (Member of Technical Staff,

Building agents doesn’t have to take weeks. Prototype a production‑ready agent with the Claude Agent SDK and add observability and evaluation with MLflow—go from idea to measurable results in hours. 🚀 See how autotracing captures inputs, outputs, and metadata, and how MLflow

Only a few days left until the 𝗧𝗲𝗿𝗺𝗶𝗻𝗮𝗹 𝗕𝗲𝗻𝗰𝗵 𝗠𝗲𝗲𝘁𝘂𝗽 at @databricks HQ! 🚀 📣 Join the #MLflow community this Thursday for an evening of demos, discussions, and new announcements from Terminal Bench 2.0. Hear from Danny Chiao on building high-quality agents

Two weeks from today — don’t miss it! 🙌 📣 Join the next 𝗠𝗟𝗳𝗹𝗼𝘄 𝗖𝗼𝗺𝗺𝘂𝗻𝗶𝘁𝘆 𝗠𝗲𝗲𝘁𝘂𝗽 on November 12 to explore the latest in AI observability and agent tracing. Featuring two exciting talks: 🔹 𝗖𝗹𝗮𝘂𝗱𝗲 𝗖𝗼𝗱𝗲 & 𝗔𝗴𝗲𝗻𝘁 𝗦𝗗𝗞 𝗧𝗿𝗮𝗰𝗶𝗻𝗴 (Samraj

Evaluating GenAI models isn’t just about accuracy—cost, time, and detailed key-level metrics matter too. 🚀 In this video, #MLflow Ambassador Shrinath Suresh shows how to go beyond accuracy and capture richer evaluation metrics. By the end, you’ll have a richer evaluation

Have you heard of GEPA? 🔥 GEPA has quickly become one of the most popular prompt optimization techniques in AI—and through our collaboration with @DSPyOSS, #MLflow now makes it easier than ever to apply GEPA to your agents. MLflow brings GEPA to where your traces and eval

Join #MLflow at the upcoming Terminal Bench Meetup at @Databricks HQ on November 6! 🎉 Learn how to build high-quality agents faster with MLflow from Danny Chiao and discover the new, exciting features from Terminal Bench 2.0. 👏 Plus, enjoy food, drinks, and great conversations

Want to learn more? Join us on November 12 for our next #MLflow Community Meetup where we will cover Claude Code & Claude Agent SDK Tracing. ✅ Bring your questions and get answers in real-time! Register:

Want to learn more? Join us on November 12 for our next #MLflow Community Meetup where we will cover Claude Code & Claude Agent SDK Tracing. ✅ Bring your questions and get answers in real-time! Register:

Building agentic applications is complex, but it doesn’t have to be slow. In this blog, Samraj Moorjani shows how to go from idea to measurable results in hours using the Claude Agent SDK with MLflow for observability and evaluation. What you’ll learn: 🔸 Rapid prototyping with