Evidence tier Source Confirmed · 4 captures on record
What the publisher says
As described on AWS Marketplace.
Arize AX is the all-in-one AI Agent Engineering platform that powers the next generation of self-improving agents and applications - from development to live production. With tools for prompt optimization, full trace observability, agent evaluation, and live monitoring, Arize helps AI teams build generative AI systems faster, improve performance, and scale with confidence.
Built for modern agent architectures and deployed in your AWS environment, Arize AX integrates seamlessly with Amazon Bedrock Agents and popular open-source frameworks.
Show the rest of the publisher’s description (8 more lines)
-Prompt IDE for Optimization: Design, test, compare, and evolve prompts in a powerful environment with live inputs, outputs, and integrated evaluation results.
-Application Agent-Level Observability and Tracing: Visualize every step of agent behavior - prompts, tools, memory, routing, and LLM outputs - with minimal code using the Arize OpenInference instrumentation.
-LLM and Agent Evaluation: Run offline and online LLM-as-a-Judge evaluations to assess accuracy, tool-calling, planning, and goal achievement.
-Self-Improving Agent Workflows: Drive closed-loop improvement by combining trace analysis, evaluation feedback, and golden data sets into continuous iteration.
-Datasets and Experiments: Use curated and/or human-annotated datasets to run controlled experiments across prompt strategies, agent configurations, or toolchains, and measure performance impact over time with built-in analytics
-Copilot Assistant (Alyx): Navigate traces, surface anomalies, and ask natural-language questions about agent performance - all in-product.
-Real-Time Monitoring & Alerts: Define custom metrics, monitor latency, token usage, or failures, and set alerts to stay ahead of production issues.
-Machine Learning Observability and Computer Vision: Monitor, troubleshoot, and improve traditional ML and CV models alongside LLM agents - tracking drift, bias, and performance across tabular, image, and multimodal datasets.
Highlights
Highlighted by the publisher on AWS Marketplace.
Agent and LLM Application Observability: Gain full visibility into the behavior of your AI agents and LLM-powered applications. Arize captures and visualizes every step - user inputs, routing logic, tool calls, memory access, and model outputs - using tree-structured traces. With native support for Amazon Bedrock Agents and open frameworks, observability is seamless and code-light.
Enable Self-Improving Agents: Go beyond static deployments. Arize enables closed-loop agent improvement by combining observability, online evaluation, and structured experimentation. Debug issues faster, test changes safely, and continuously evolve agent behavior in response to real-world usage and feedback.
Prompt IDE and Evaluation: Optimize prompts with Prompt IDE, purpose-built for fast iteration and testing. Compare prompt versions side by side, analyze agent responses, and apply online or offline LLM as a Judge evaluations to measure quality, correctness, and performance at scale.
Agent build and provenance
See the full provenance
The layer-by-layer build, the evidence behind each claim, the risk basis and the cross-marketplace links are open to any account. Some rows are disclosed, some the source leaves Unknown; a free account shows you which.
Compliance
- FedRAMPConfirmedNot listed90%, registry-checkedNo FedRAMP Marketplace entry matched this vendor's domain, checked 2026-08-27registry recordas observed 2026-08-27
Confirmed means matched to a public authoritative registry. Claimed means the vendor or its listing states it, not yet cross-checked. A framework not shown was not found in any source we hold, which is not evidence against it. Not listed means a scoped registry check found no match for this vendor's domain: a No is a scoped registry check, not a compliance judgment. Confidence bands: 95% domain-verified, 90% registry-checked, 80% self-attested, 70% weak signal. Self-attested items marked “vendor's site” are gathered from the vendor's own website and are not verified by us.
Vendor
External enrichment
Plans and pricing as listed
1 listed- Units
Refund terms
As stated by the publisher on AWS Marketplace.
No returns or refunds.
Sources
Publisher resources
4 linksLinked repositories
Unknown means this listing does not publish a repository. It is not a statement that the code is closed, and a linked repository is not a claim that the publisher wrote it: the registry computes that relationship privately and does not publish it.
Evidence risk is the share of the build you cannot see before you deploy, not a security rating. Sign in to see the layer-by-layer basis for this band.