Arize AI shipped a hosted MCP server for its Arize AX observability platform, exposing 45 tools plus server_info across projects, traces, datasets, experiments, evaluators, monitors, and prompts, conn…
Anthropic's Lance Martin published "Automating eval design and hillclimbing with Claude" on September 28, adding two commands to the claude-api skill: /claude-api build-eval, which interviews the user…
Arize shipped long-term memory for Alyx, its AI engineering agent inside Arize AX, as a single structured text file per user and space capped at 8,000 characters that the agent reads in full on every …
Arize AX has added long-term memory to Alyx, its AI engineering agent, enabling it to retain project goals, conventions, preferences and prior decisions across sessions, and the feature is enabled by …
NVIDIA published the Open Agent Safety Platform, a reference design that places agent monitoring and a kill switch in a BlueField-4 data processing unit sitting on what NVIDIA calls the node's only pa…
Arize AI is a launch partner for MongoDB's Atlas Agent Engine, a new platform for building, deploying, and governing AI agents in production, with Arize AX adding trace-level observability and evaluat…
A Peking University research team led by Haoran Ye trained the behavior of a specialized agent harness into Qwen3.5-9B via a method called harness distillation, raising the small model's average task …
Anthropic's Claude Opus 5.5 cut em dash usage to 2 occurrences across 57,000 words of output, down from 12.9 per 1,000 words in Opus 5, according to an independent evaluation run by Arize employee Jim…
Arize AX now integrates directly with TypeSafe AI, bringing native Jev-as-a-Judge evaluations into the Arize evaluation workflow, the company announced. In an Arize benchmark for hallucination detecti…
Arize AI's Jev 1.13.0 classifier matched LLM judges on accuracy while its returned probability strongly predicted its own correctness across 36,190 judgments, according to an Arize benchmark spanning …
Arize published a tutorial showing how to connect TypeSafe's Jev to Arize AX through a remote evaluator that scores recorded agent spans after the agent responds, returning a yes/no label and a probab…
A benchmark of 23,325 judgments across the RAGTruth and SummEval human-labeled datasets found that TypeSafe's Jev matched Claude Opus 5 at 87% accuracy on held-out hallucination detection at roughly 1…
TypeSafe AI's purpose-built decision model Jev returned guardrail decisions faster and cheaper than OpenAI's GPT-5.4 nano in a dealership chatbot demo, according to a comparison published by Arize. Th…
Daytona cofounder and CEO Ivan Burazin said the agents he uses fail more often because they cannot access the tools they need than because of the model itself, and that he does not want agents operati…
Arize AI shipped sessions as a first-class unit of work in Arize AX between August 6 and September 18, letting users annotate, queue, preview, and filter whole conversations rather than individual spa…
TypeSafe AI released Jev, its first System One model, which returns typed answers with probability distributions for classification, scoring, and routing tasks in 70ms to 500ms at $0.042 per million i…
Arize AI's Signal agent in Arize AX now performs the first pass on production AI failures, scanning tracing projects on a schedule, grouping recurring failure patterns into issues, and writing investi…
Arize AI's Agent Experiments in Arize AX demonstrated that a prompt fix intended to make an e-commerce agent safer can degrade other workflows, with average task completion falling from 0.89 to 0.72 i…
Anthropic's Claude Code and Codex now have non-engineering variants in Claude Design and Codex Work, and Anthropic's revenue has been growing 10x year over year, according to a blog post by Arize. The…
Arize AI software engineering intern reported cutting coding agent costs from about $100 to $15–$20 per run by routing the main loop of a Slack bot workflow to Kimi K3 Max, delegating supporting work …