Arize AI

Arize Data Fabric now supports Databricks, helping teams sync production agent traces, evaluations, and annotations into customer-owned storage for governed analysis in Unity Catalog. The post Bring production agent traces from Arize into Databricks Unity Catalog appeared first on Arize AI .

Can an AI agent use a database as if it were a filesystem? Arize compared a Postgres-backed filesystem abstraction with a SQL skill and found that locality, accuracy, and maintenance cost favored the skill-based approach. The post PostgresFS vs. SQL skills: should AI agents fake a filesystem? appeared first on Arize AI .

Arize reduced median support resolution time from 22 hours to roughly 2.5 hours by building AI-native internal workflows for context gathering, debugging, escalation, and continuous improvement. The post How Arize built AI-native support workflows that cut resolution time in half appeared first on Arize AI .

In May 2026, a malicious version of a popular VS Code extension spent 18 minutes in the marketplace before anyone caught it. In that time it ran on roughly 6,000... The post How to detect credential theft in AI agent harness traces appeared first on Arize AI .

Phoenix crossed 10,000 GitHub stars. Here is how the open-source AI observability project grew from a Jupyter notebook extension into a community-shaped platform for traces, evals, OpenInference, and agents. The post Phoenix at 10,000 stars on GitHub: How an open source AI observability project grew by following its community appeared first on Arize AI .

Arize AX is adding managed agents, full-agent experimentation, expanded multimodal support, and Harness-as-a-Judge to help teams observe, evaluate, and improve production agents. The post Building the AI factory for self-improving agents: What’s new in Arize AX appeared first on Arize AI .

Microsoft's open trust stack for AI agents puts ASSERT and Agent Control Specification on top of OpenInference, connecting evaluation, runtime controls, and observability through a shared trace contract. The post Microsoft’s open trust stack runs on OpenInference appeared first on Arize AI .

Fine-tuning isn't dead, but the way most teams iterate on AI products has split in two. A tiny fraction run continuous RL against their own environments; everyone else has moved the iteration loop out of the model and into the harness. Here's why, and what the 99% should do instead. The post The end of fine-tuning: Why evals, context, and traces matter more appeared first on Arize AI .

Models got smart enough to cheat their benchmarks, and outcome-only scores stopped measuring what we thought they measured. The fix, full trace analysis, is the same methodology production AI teams have needed all along. The post AI benchmarks are breaking. Trace analysis is what comes next. appeared first on Arize AI .

Hermes from NousResearch is a strong open-source agent harness. This post examines how its runtime loop, context management, tool scoping, session infrastructure, and orchestration patterns map to a modern agent harness architecture. The post How Hermes implements an open source agent harness architecture appeared first on Arize AI .

A practical comparison of production AI evaluation harnesses, including what to look for across instrumentation, evaluators, online evals, CI gates, and agent workflows. The post The best eval harness for production AI and agents: A comparison appeared first on Arize AI .