### Product newsletter: Updates and new features for June 2026 ### AI agent observability #### Evaluations #### Agents #### Inference #### Safety and scoring ### Build models #### Computer Vision #### NLP #### MLOps #### LLM ### About Weights & Biases #### Integrations #### W&B releases #### Events ### Recent Reports - [**Track, guard, and remediate AI usage with W&B Weave and CrowdStrike Falcon AIDR**](/content/wandb_fc/crowdstrike-aidr/reports/Track-guard-and-remediate-AI-usage-with-W-B-Weave-and-CrowdStrike-Falcon-AIDR--VmlldzoxNzI1OTczNA/index.html) Learn how Weave and CrowdStrike Falcon AI Detection and Response can help ensure internal AI systems are handling sensitive data appropriately Jul 15, 2026 - [**Tabular ML didn't die. It was just waiting for agents**](/content/wandb_fc/tabular-nomad/reports/-Tabular-ML-didn-t-die-It-was-just-waiting-for-agents--VmlldzoxNzQwMzQ5Ng/index.html) Learn how our tabular data agent, took #1 on the MLE-bench tabular slice with two golds, three above-median, four-for-four valid submissions. Jul 06, 2026 - [**Introducing CoreWeave ARIA: AI Research and Iteration Agent**](/content/wandb/aria/reports/Introducing-CoreWeave-ARIA-AI-Research-and-Iteration-Agent--VmlldzoxNzM1MzA4Mg/index.html) Your experiments are already tracked. Now let the agent read them, analyze them, and help you turn every experiment into continuous improvement. Jun 29, 2026 - [**We'll be at the AI Engineer World's Fair - Come Say Hi**](/content/wandb_fc/event-announcements/reports/We-ll-be-at-the-AI-Engineer-World-s-Fair-Come-Say-Hi--VmlldzoxNzM0MjQ1NA/index.html) Join Weights & Biases by CoreWeave at AI Engineer World’s Fair in SF. Visit booth UG 24 for demos, swag, speaker sessions, and new Weave agent tracing features. Jun 25, 2026 - [**How to structure effective Agent Skills and evaluate whether they actually work**](/content/ai-team-articles/agent-skills/reports/How-to-structure-effective-Agent-Skills-and-evaluate-whether-they-actually-work--VmlldzoxNjg5MzMwMw/index.html) Improve your Vibe Coding Skills using Agent Skills and evaluate them with Skills Bench and W&B Weave Jun 23, 2026 - [**ART-Optimized Megatron (AOM): 12x higher training throughput**](/content/wandb_fc/product-announcements-fc/reports/ART-Optimized-Megatron-AOM-12x-higher-training-throughput--VmlldzoxNzMxNzY1MA/index.html) How we massively improved training throughput on our open source ART training library Jun 23, 2026 - [**Building a production-grade MLOps pipeline for VLA models**](/content/byyoung3/finetune-gr00t-n1d6/reports/Building-a-production-grade-MLOps-pipeline-for-VLA-models--VmlldzoxNjgxOTMxMA/index.html) This report covers the development of a compact vision-language-action model built around Gemma 3 270M. Jun 11, 2026 - [**Getting started with embodied chain-of-thought (ECoT)**](/content/ai-team-articles/ecot-pipeline-demo/reports/Getting-started-with-embodied-chain-of-thought-ECoT---VmlldzoxNjczMTg0OQ/index.html) Learn how to get started with Embodied Chain-of-Thought, a robotics reasoning approach that helps vision-language-action models plan, explain, and execute grounded actions. Jun 11, 2026 - [**Governance workflows for AI agents: an evidence-backed review gate on W&B Weave**](/content/wandb-smle/responsible-ai/reports/Governance-workflows-for-AI-agents-an-evidence-backed-review-gate-on-W-B-Weave--VmlldzoxNzEyNTg5OQ/index.html) A technical walkthrough of an open-source AI governance toolkit that turns scattered evals, red-team runs, and approvals into one reproducible review gate, with every finding traced in W&B Weave. Jun 08, 2026 - [**Tutorial: Benchmarking Claude Opus 4.8 honesty with BeHonest and W&B Weave**](/content/byyoung3/claude_4/reports/Tutorial-Benchmarking-Claude-Opus-4-8-honesty-with-BeHonest-and-W-B-Weave--VmlldzoxMjkzNjAzNA/index.html) How honest is Claude Opus 4.8 compared to 4.7? We ran both models through the BeHonest benchmark and logged every result into W&B Weave. Jun 05, 2026 - [**New in W&B Weave: Observability and continuous improvement for production agents**](/content/wandb_fc/product-announcements-fc/reports/New-in-W-B-Weave-Observability-and-continuous-improvement-for-production-agents--VmlldzoxNzAzMTcxNg/index.html) We're shipping a new set of capabilities that make Weave the best tool to raise and maintain agent quality in production. Here's what you need to know. Jun 02, 2026 - [**Build a Robotics Data Flywheel on CoreWeave using NVIDIA Cosmos 3**](/content/wandb_fc/nvidia-cosmos/reports/Build-a-Robotics-Data-Flywheel-on-CoreWeave-using-NVIDIA-Cosmos-3--VmlldzoxNzA3MzA2Ng/index.html) A foundation is large-scale synthetic data and compute, a requirement that is no longer an issue when teaming up with CoreWeave and NVIDIA. Jun 02, 2026 - [**Product newsletter: Updates and new features for May 2026**](/content/wandb_fc/product-announcements-fc/reports/Product-newsletter-Updates-and-new-features-for-May-2026--VmlldzoxNzA3MzAzNA/index.html) From a brand new CoreWeave Sandboxes offering to updates in Models and to our iOS app, here's what we released in May. Jun 01, 2026 - [**Running agents in production with Google’s Gemini Managed Agents**](/content/byyoung3/bug-finder/reports/Running-agents-in-production-with-Google-s-Gemini-Managed-Agents--VmlldzoxNjk1NDIyMQ/index.html) In this article, we will use the Gemini Managed Agents API to build a small bug-finder agent. May 28, 2026 - [**Building a text-to-SQL agent**](/content/wandb_fc/ai-builders/reports/Building-a-text-to-SQL-agent--VmlldzoxNzAyMDIwNQ/index.html) In the second edition of our AI Builders series, learn how to build a text-to-SQL agent May 26, 2026 - [**Introducing the W&B MCP Server: An agent-native interface for your experiments and traces**](/content/wandb_fc/product-announcements-fc/reports/Introducing-the-W-B-MCP-Server-An-agent-native-interface-for-your-experiments-and-traces--VmlldzoxNjk0MDE5OQ/index.html) Our MCP server is generally available now. Built as primitives so the agent can do the rest. May 21, 2026 - [**Product newsletter: Updates and new features for April 2026**](/content/wandb_fc/product-announcements-fc/reports/Product-newsletter-Updates-and-new-features-for-April-2026--VmlldzoxNjczMDY2Mg/index.html) From universally available automations to brand new Weave dashboards, here are the big features we released in April May 04, 2026 - [**Training a Gemma-3 powered VLA model**](/content/byyoung3/finetune-gr00t-n1d6/reports/Training-a-Gemma-3-powered-VLA-model--VmlldzoxNjQ5MzQwNw/index.html) This report covers the development of a compact vision-language-action model built around Gemma 3 270M. Apr 29, 2026 - [**From sequence to structure: Tracking protein fold prediction with W&B**](/content/Lorenzo-Team/proteus-fold/reports/From-sequence-to-structure-Tracking-protein-fold-prediction-with-W-B--VmlldzoxNjUyOTgwNw/index.html) Learn how to track protein fold prediction using ESMFold and Weights & Biases. Explore a complete biotech pipeline, from 3D structure visualization and pLDDT tracking to Bayesian sweeps and model versioning. Apr 27, 2026 - [**Building an AI agent for interior design**](/content/wandb_fc/ai-builders/reports/Building-an-AI-agent-for-interior-design--VmlldzoxNjY1NjY5MA/index.html) In the inaugural edition of our AI Builders series, learn how to build an AI agent for home decor Apr 24, 2026 - [**Tutorial: Building a production-ready fraud triage Copilot**](/content/mostafaibrahim17/ml-articles/reports/Tutorial-Building-a-production-ready-fraud-triage-Copilot--VmlldzoxNjA3MjczOQ/index.html) Build, evaluate, guard, and monitor an LLM fraud analyst end-to-end with W&B Weave. Apr 23, 2026 ### Conclusion Iterate on AI agents and models faster. Try Weights & Biases today.