Arize AI

Arize AX is an AI engineering platform from Arize AI for observing and evaluating AI agents, including voice agents. It provides a unified session and trace view that combines audio, transcripts, latency metrics, tool calls, and evaluation results, allowing failures such as dead air, interruptions, transcription errors, and incorrect tool actions to be investigated together. The platform supports tracing real-time audio with OpenInference semantic conventions, audio-native evaluations for factors such as sentiment, latency, interruptions, and task success, and agent experiments that test fixes against failed traces. It is available through the Arize AX product interface and a terminal-based setup.

Arize Skills is a set of installable skills for AI coding agents, maintained by Arize, that guides agents through adding observability, creating datasets, running experiments and evaluations, and optimizing prompts for LLM applications. The skills use the ax CLI to interact with Arize and include workflows for tracing and debugging applications, OpenInference-based instrumentation, dataset management, experiments, LLM-as-judge evaluators, annotations, prompt optimization, provider credentials, and production monitoring. They can be installed into agents such as Cursor, Claude Code, Codex, GitHub Copilot, and Windsurf through npx, the repository's installers, the ax CLI, or a Claude Code plugin. The repository is licensed under MIT.

Alex is Arize's in-product agent assistant for creating evaluators for AI applications. In the demonstrated use case, it helps create an evaluator intended to prevent an application from giving bomb-building instructions.

ResolveAI is an AI SRE platform for operating production systems, providing managed on-call and SRE agent teams for alert triage, incident investigation, root-cause analysis, recurring issue remediation, and operational automation. Its agents investigate across code, infrastructure, telemetry, observability data, knowledge bases, and production context supplied through Hivemind, which tracks production state, alerts, recent changes, on-call questions, and incident context. In a demonstrated workflow, a Grafana alert received through Slack triggers an investigation that builds a causal chain of evidence and rules out competing explanations before proposing or taking governed actions. ResolveAI agents can mitigate and restore services, escalate to engineers with context, supply production context to coding agents, support custom SRE agents for workflow-specific automation, and integrate with existing engineering tools. The platform combines model orchestration, context engineering, causal reasoning, governed actions, learning systems, evaluations, and domain models with frontier models.