Arize AI

AI costs don’t always scale predictably with traffic. A retry loop, oversized context window, or unnecessarily expensive model can make a small number of traces disproportionately expensive. The post Cost Agent: find where your LLM and agent spend goes with your traces appeared first on Arize AI .

On 15 September, TypeSafe released Jev, and within a few weeks about 10 companies had shipped something that works the same way. OpenAI, Liquid, Cloudflare, AWS and PostHog all launched one, and an open clone called Kev showed up on Hugging Face in between. If you build agents or run evals, you now have a... The post Decision model benchmark: Jev, Kev, Liquid d1, and more appeared first on Arize AI .

Some agent failures are already in the trace. tracelint proves them on Phoenix OpenInference spans and fails CI, without an LLM judge. The post What agent traces can tell you without an LLM judge appeared first on Arize AI .

See how Arize uses Harbor and Phoenix to benchmark AI agents, MCP servers, skills, and CLIs in reproducible sandboxes, then inspect traces and annotations. The post How we benchmark AI agents and tools with Harbor and Arize Phoenix appeared first on Arize AI .

We benchmarked prompt caching across DeepSeek, GLM, GPT, and Claude using Harbor evals and Phoenix traces, so we could compare cache reuse, estimated cost, and latency on the same multi-turn shopping assistant agent. The post Prompt caching benchmark: high cache reuse doesn’t always mean lower cost appeared first on Arize AI .

MCP, CLI, and skills are three ways to extend an agent with the same platform. The question is no longer which one wins. It is where the agent runs, and who is asking. The post Introducing Arize AX MCP: When to use MCP, CLI, or skills appeared first on Arize AI .

Anthropic's Claude hillclimb loop designs evals and improves agents one change at a time. Here's how to run that loop against production traces in Arize AX. The post Claude’s hillclimb loop for AI agents: start with production traces appeared first on Arize AI .

How we built long-term memory for Alyx: why we chose one 8,000-character file over retrieval and knowledge graphs, and how we tested it. The post How we built long-term memory for Alyx: why we chose a file over a knowledge graph appeared first on Arize AI .

Alyx now remembers project goals, conventions, and decisions across sessions in Arize AX, helping you continue work on traces, evals, and experiments. The post Alyx now remembers your work across sessions with long-term memory appeared first on Arize AI .

This year agents at OpenAI, Anthropic, and Google escaped environments meant to contain them. What decided severity was time-to-detect and time-to-kill, from 12 minutes to seven months. NVIDIA's Open Agent Safety Platform puts a kill switch in hardware the agent can't reach. The post NVIDIA proposes an AI agent kill switch in silicon after a year of sandbox escapes appeared first on Arize AI .

Agents built and deployed on MongoDB’s Atlas Agent Engine can export OpenTelemetry traces to Arize AX, where teams can inspect each run, evaluate both the outcome and execution path, and test fixes before redeploying. The post Building production-ready AI agents with Atlas Agent Engine and Arize AX appeared first on Arize AI .